1
0
mirror of https://github.com/xmrig/xmrig.git synced 2025-12-07 07:55:04 -05:00

Compare commits

...

788 Commits

Author SHA1 Message Date
Jean-Pierre De Jesus DIAZ
22feb9e1e7 Merge f0f6d1666c into d5a8f8a5ae 2023-06-22 07:34:56 +02:00
xmrig
d5a8f8a5ae Merge pull request #3288 from SChernykh/dev
KawPow: fixed data race when building programs
2023-06-19 17:40:24 +07:00
SChernykh
d94d052e6c KawPow: fixed data race when building programs
`uv_queue_work` can't be called from other threads, only `uv_async_send` is thread-safe.
2023-06-19 12:32:28 +02:00
XMRig
ae2b7e3348 Merge branch 'Spudz76-dev-addApiRebind' into dev 2023-06-07 20:49:34 +07:00
XMRig
7d7f30701f Code cleanup. 2023-06-07 20:48:56 +07:00
XMRig
e80fc25789 Merge branch 'dev-addApiRebind' of https://github.com/Spudz76/xmrig into Spudz76-dev-addApiRebind 2023-06-07 20:12:58 +07:00
XMRig
ff53be5f3b Merge branch 'benthetechguy-readme' into dev 2023-06-07 00:52:37 +07:00
XMRig
6981e68ae3 Merge branch 'readme' of https://github.com/benthetechguy/xmrig into benthetechguy-readme 2023-06-07 00:52:03 +07:00
XMRig
c7e541d84f Disallow direct use of HwlocCpuInfo class. 2023-06-07 00:32:09 +07:00
XMRig
a2ae17b4c4 Code cleanup. 2023-06-06 23:15:58 +07:00
XMRig
554b60966b Fixed compatibility with hwloc 1.11. 2023-06-06 02:30:10 +07:00
xmrig
0378aa8df4 Merge pull request #3236 from MrFoxPro/dev
fix(cuda): receive CUDA loader error on linux too.
2023-06-05 23:07:38 +07:00
XMRig
6dbd46a891 Added new CMake options ARM_V8 and ARM_V7. 2023-06-04 20:32:05 +07:00
XMRig
055db83142 Added new ARM CPU names. 2023-06-04 19:36:53 +07:00
XMRig
cdd5dff337 v6.19.4-dev 2023-06-03 21:14:26 +07:00
XMRig
bc5fe8f456 Merge branch 'master' into dev 2023-06-03 21:13:51 +07:00
XMRig
0bc87345c4 v6.19.3 2023-06-03 19:59:18 +07:00
XMRig
f17d31e61a Merge branch 'dev' 2023-06-03 19:57:36 +07:00
xmrig
e6bf4c0077 Update CHANGELOG.md 2023-06-02 22:12:18 +07:00
xmrig
ff79b8fce4 Merge pull request #3280 from SChernykh/dev
Updated example scripts
2023-06-02 17:47:13 +07:00
SChernykh
af87369e4f Updated example scripts
- Hashvault is top 1 pool now, so changed it to a smaller pool
- node.xmr.to doesn't exist anymore
2023-06-02 09:34:26 +02:00
Jean-Pierre De Jesus DIAZ
f0f6d1666c fixup! Allow using system libfmt 2023-05-29 20:15:44 +02:00
Jean-Pierre De Jesus DIAZ
0399b6b6bb Allow using system libfmt
Signed-off-by: Jean-Pierre De Jesus DIAZ <me@jeandudey.tech>
2023-05-29 20:15:44 +02:00
xmrig
65fc16d5ac Merge pull request #3275 from SChernykh/dev
RandomX: fixed `jccErratum` list
2023-05-26 18:25:57 +07:00
SChernykh
826e23b4c4 Fixed jccErratum list 2023-05-26 12:46:59 +02:00
Tony Butler
548fbb9f71 Add API rebind polling 2023-05-23 16:49:43 -06:00
xmrig
02d45834e1 Merge pull request #3273 from SChernykh/dev
RandomX: fixed undefined behavior
2023-05-23 20:18:32 +07:00
SChernykh
1252a4710e RandomX: fixed undefined behavior
Using an inactive member of a `union` is an undefined behavior in C++
2023-05-23 14:40:12 +02:00
xmrig
5891f1f06b Merge pull request #3271 from SChernykh/opt_genprog
RandomX: optimized program generation
2023-05-22 05:25:32 +07:00
SChernykh
5dcbab7e3a RandomX: optimized program generation 2023-05-21 17:44:20 +02:00
xmrig
7b51e23aa0 Merge pull request #3254 from SChernykh/dev
Tweaked auto-tuning for Intel CPUs
2023-04-19 12:29:58 +07:00
SChernykh
7f7fc363e1 Tweaked auto-tuning for Intel CPUs
Alder Lake and newer CPUs have exclusive L3 cache and benefit from more threads until L3+L2 is filled.
2023-04-18 21:20:45 +02:00
XMRig
c4e1363148 #3245 Improved algorithm negotiation for donation rounds by sending extra information about current mining job. 2023-04-07 23:35:05 +07:00
XMRig
a2e9b3456d v6.19.3-dev 2023-04-04 00:34:54 +07:00
XMRig
4790318685 Merge branch 'master' into dev 2023-04-04 00:34:22 +07:00
XMRig
038c4fbe34 v6.19.2 2023-04-03 22:15:40 +07:00
XMRig
d65d34ef36 Merge branch 'dev' 2023-04-03 22:14:58 +07:00
xmrig
af6647f377 Update CHANGELOG.md 2023-04-03 20:34:35 +07:00
xmrig
8f9adc02c0 Merge pull request #3241 from SChernykh/dev
Sync with changes from proxy
2023-04-03 20:28:38 +07:00
SChernykh
5e0079f012 Sync with changes from proxy 2023-04-03 15:01:40 +02:00
xmrig
dc5e341778 Merge pull request #3240 from koitsu/dev-improve-cmd-files
Improve .cmd files when run by shortcuts on another drive
2023-04-01 12:30:33 +07:00
Jeremy Chadwick
0f81ab4c67 Improve .cmd files when run by shortcuts on another drive 2023-03-31 20:16:00 -07:00
Dmitriy Nikiforov
62a3a98e7d fix(cuda): receive CUDA loader error on linux too. 2023-03-27 18:48:13 +05:00
XMRig
d31b3b7c76 Code style cleanup. 2023-03-25 20:56:25 +07:00
xmrig
e352109431 Merge pull request #3232 from moneromooo-monero/xhd-dev
DaemonClient: new X-Hash-Difficulty HTTP header optimization
2023-03-25 20:51:09 +07:00
moneromooo-monero
88b0385bfe DaemonClient: new X-Hash-Difficulty HTTP header optimization
If the caller knows the difficulty of a PoW hash a given nonce
yields, it can tell the callee via the X-Hash-Difficulty, which
may allow the callee to skip some processing if the difficulty
does not meet some criterion.

In my case, a merge mining proxy can know it's pointless trying
to submit the nonce to a chain with higher difficulty when the
nonce only meets the difficulty for a lower difficulty chain.
2023-03-25 09:48:54 +00:00
xmrig
9508332258 Merge pull request #3230 from SChernykh/dev
Fixed parsing of TX_EXTRA_MERGE_MINING_TAG
2023-03-25 12:39:04 +07:00
SChernykh
bc5c1f7e65 Fixed parsing of TX_EXTRA_MERGE_MINING_TAG 2023-03-24 22:42:26 +01:00
XMRig
22118330e3 v6.19.2-dev 2023-03-23 20:41:00 +07:00
XMRig
240f2450af Merge branch 'master' into dev 2023-03-23 20:40:23 +07:00
XMRig
6e856ca39c v6.19.1 2023-03-23 19:03:09 +07:00
XMRig
6047786f43 Merge branch 'dev' 2023-03-23 19:02:24 +07:00
xmrig
7b8ba9ac09 Update CHANGELOG.md 2023-03-23 18:10:43 +07:00
xmrig
02259fec05 Merge pull request #3228 from SChernykh/dev
Fix build with gcc 13
2023-03-23 18:02:47 +07:00
Matthew Smith
51728b2d55 Fix build with gcc 13
Now some header files are not included transistively with new
libstdc++.

Bug: https://bugs.gentoo.org/895226
2023-03-23 12:01:15 +01:00
XMRig
ebe818a5fb Resolved deprecated methods warnings with OpenSSL 3.0. 2023-03-07 23:51:03 +07:00
xmrig
790a71b030 Merge pull request #3218 from SChernykh/dev
Fix: `--randomx-wrmsr=-1` worked only on Intel
2023-02-27 11:17:01 +07:00
SChernykh
c62622b114 Fix: --randomx-wrmsr=-1 worked only on Intel 2023-02-26 22:31:55 +01:00
xmrig
fc643e2936 Merge pull request #3213 from SChernykh/dev
Fix for 32-bit clang 15
2023-02-19 15:47:28 +07:00
SChernykh
12b9b62ef7 Fix for 32-bit clang 15
Don't define `_mm_cvtsi128_si64` and `_mm_cvtsi64_si128` because clang 15 already has them in its headers.
2023-02-19 09:42:16 +01:00
XMRig
667f636c62 Fixed DnsUvBackend storage cleanup. 2023-02-09 21:45:50 +07:00
XMRig
81e87a6931 Revert changes to fix MSVC build. 2023-02-09 21:28:39 +07:00
XMRig
540b223eab Cleanup. 2023-02-09 13:55:11 +07:00
XMRig
75474be060 Fix warning. 2023-02-03 23:46:58 +07:00
XMRig
49f34e59a6 Partially resolved deprecated methods warnings in OpenSSL 3.0. 2023-02-03 23:08:54 +07:00
XMRig
223add4e22 v6.19.1-dev 2023-02-02 12:27:33 +07:00
XMRig
435fc86120 Merge branch 'master' into dev 2023-02-02 12:27:08 +07:00
XMRig
c0143b90ce v6.19.0 2023-02-02 11:51:11 +07:00
XMRig
c3cdffe86d Merge branch 'dev' 2023-02-02 11:50:29 +07:00
XMRig
8a4da33bea Update scripts/build.*.sh. 2023-01-30 00:19:55 +07:00
XMRig
1c7a339527 v6.19.0-dev (new config options added). 2023-01-29 11:16:37 +07:00
xmrig
490acd6e55 Update CHANGELOG.md 2023-01-29 11:13:28 +07:00
xmrig
6ecf57959b Merge pull request #3202 from SChernykh/dev
Solo mining: added job timeout (default is 15 seconds)
2023-01-29 11:12:22 +07:00
SChernykh
e2c58126e9 Solo mining: added job timeout (default is 15 seconds)
It's important to update jobs frequently to get new transactions into the block template. See https://rucknium.me/posts/monero-pool-transaction-delay/ for more details.
2023-01-28 19:42:02 +01:00
XMRig
0ed4b35cd3 Update hwloc for MSVC builds to 2.9.0. 2023-01-27 01:07:58 +07:00
xmrig
afe2aa4402 Update CHANGELOG.md 2023-01-23 20:54:46 +07:00
XMRig
3f7533a645 Update to latest sse2neon.h. 2023-01-23 20:45:02 +07:00
xmrig
6ef0409086 Merge pull request #3198 from SChernykh/dev
Fixed broken RandomX light mode mining
2023-01-21 22:05:25 +07:00
SChernykh
64b0d9562e Fixed broken RandomX light mode mining
RandomX VMs didn't get updated properly in light mode.
2023-01-21 16:02:47 +01:00
XMRig
770b71c69a #3185 Fixed macOS DMI reader. 2023-01-19 22:09:59 +07:00
xmrig
44642643f8 Merge pull request #3196 from SChernykh/dev
Show IP address for failed connections
2023-01-11 17:02:15 +07:00
SChernykh
273bb84df8 Show IP address for failed connections 2023-01-11 09:28:16 +01:00
xmrig
4d0b8c9daf Merge pull request #3182 from SChernykh/dev
DragonflyBSD compilation fixes
2022-12-17 20:24:01 +07:00
SChernykh
7d4d48e83b DragonflyBSD compilation fixes 2022-12-17 13:11:14 +01:00
xmrig
2ea37cdf37 Merge pull request #3180 from SChernykh/dev
Added ifdefs for DragonflyBSD
2022-12-16 21:29:24 +07:00
SChernykh
a02afe6d4f Added ifdefs for DragonflyBSD
Possible fix for #3179
2022-12-16 15:26:37 +01:00
XMRig
6e86dddc65 Bump the minimum CMake version in other places too. 2022-12-09 16:07:42 +07:00
xmrig
0171faffe7 Merge pull request #3176 from SChernykh/dev
Update cmake required version to 3.1
2022-12-09 15:24:54 +07:00
SChernykh
25decd1b7f Update cmake required version to 3.1
`set(CMAKE_CXX_STANDARD 11)` only works properly starting from cmake 3.1, see #3174
2022-12-09 09:21:40 +01:00
xmrig
354b9ddb34 Merge pull request #3163 from SChernykh/dev
Improved Zen 3 MSR mod
2022-11-18 11:38:45 +07:00
SChernykh
3ad6ab56a5 Improved Zen 3 MSR mod
+0.5% speedup on Ryzen 5 5600X
2022-11-17 23:32:36 +01:00
xmrig
1aa0e37b54 Merge pull request #3161 from SChernykh/dev
MSVC build: enabled parallel compilation
2022-11-15 13:20:41 +06:30
SChernykh
807c64ddb1 MSVC build: enabled parallel compilation 2022-11-15 07:45:54 +01:00
XMRig
5bf90704a6 #2869 2022-10-29 23:51:42 +07:00
xmrig
912d1e362b Merge pull request #3144 from Spudz76/dev-updateSSE2NEON
Update to latest sse2neon.h from github:DLTcollab/sse2neon
2022-10-24 13:50:54 +07:00
Tony Butler
eeb459506c Update to latest sse2neon.h from github:DLTcollab/sse2neon 2022-10-23 15:27:14 -06:00
XMRig
f4ec0287c4 v6.18.2-dev 2022-10-23 23:19:50 +07:00
XMRig
483d6ada3d Merge branch 'master' into dev 2022-10-23 23:19:06 +07:00
XMRig
28e81bd7c0 v6.18.1 2022-10-23 17:44:24 +07:00
XMRig
54e75bc7c4 Merge branch 'dev' 2022-10-23 17:43:38 +07:00
xmrig
c388113a30 Update CHANGELOG.md 2022-10-23 17:14:57 +07:00
xmrig
36afeec225 Merge pull request #3134 from SChernykh/dev
Added Zen4 to randomx_boost.sh
2022-10-10 03:37:06 +07:00
SChernykh
4b5e56416d Added Zen4 to randomx_boost.sh 2022-10-09 22:02:50 +02:00
xmrig
0d314d0469 Merge pull request #3132 from SChernykh/dev
RandomX: added MSR mod for Zen 4
2022-10-01 23:40:04 +07:00
SChernykh
7fc45dfb2d RandomX: added MSR mod for Zen 4
+0.8% faster on Ryzen 9 7950X
2022-10-01 18:33:04 +02:00
xmrig
2ba40edee0 Update CHANGELOG.md 2022-09-25 17:01:33 +07:00
xmrig
bc4dd11761 Merge pull request #3129 from SChernykh/dev
Fix: protectRX flushed CPU cache only on MacOS/iOS
2022-09-22 07:02:28 +07:00
SChernykh
7b52a41459 Fix: protectRX flushed CPU cache only on MacOS/iOS 2022-09-21 15:18:06 +02:00
xmrig
b5de214ff9 Merge pull request #3126 from SChernykh/dev
Don't reset when pool sends the same job blob
2022-09-19 19:03:17 +07:00
SChernykh
8bd3b393ef Update m_size only if blob was set successfully 2022-09-19 10:42:08 +02:00
SChernykh
9223c2f027 Don't reset when pool sends the same job blob 2022-09-19 10:35:36 +02:00
xmrig
6346d36d1b Merge pull request #3120 from SChernykh/dev
RandomX: optimized CFROUND elimination more
2022-09-16 22:50:51 +07:00
SChernykh
93c07e1d34 RandomX: optimized CFROUND elimination more 2022-09-16 14:11:27 +02:00
xmrig
0ba3000982 Merge pull request #3119 from SChernykh/dev
RandomX: optimized CFROUND elimination
2022-09-16 01:04:32 +07:00
SChernykh
f0e7de8c71 RandomX: optimized CFROUND elimination 2022-09-15 19:57:34 +02:00
xmrig
1c4eb6c5fe Merge pull request #3109 from SChernykh/dev
RandomX: added Blake2 AVX2 version
2022-08-26 01:52:22 +07:00
SChernykh
63e21dfe63 RandomX: added Blake2 AVX2 version
+0.1% speedup on AMD Zen2/Zen3 and Intel CPUs which support AVX2.
2022-08-25 20:39:54 +02:00
xmrig
b2d9dab2e3 Merge pull request #3075 from dev-0x7C6/master
Recognize armv7ve as valid ARMv7 target.
2022-08-19 02:30:27 +07:00
xmrig
4c57b60e59 Merge pull request #3082 from SChernykh/dev
Fixed GCC 12 warnings
2022-07-03 16:59:26 +07:00
SChernykh
e6c81d7166 Fixed GCC 12 warnings 2022-07-03 11:51:46 +02:00
xmrig
94840c70d8 Update README.md 2022-07-02 22:27:51 +07:00
XMRig
e1478bfa94 v6.18.1-dev 2022-06-26 18:32:12 +07:00
XMRig
6df6e15267 Merge branch 'master' into dev 2022-06-26 18:31:40 +07:00
XMRig
834ea44507 v6.18.0 2022-06-23 20:04:00 +07:00
XMRig
73dc0ffb7e Merge branch 'dev' 2022-06-23 20:03:29 +07:00
XMRig
e57641d6b1 v6.18.0-dev 2022-06-23 17:36:31 +07:00
XMRig
b324e34444 Update hwloc for msvc. 2022-06-23 16:45:54 +07:00
Bartłomiej Burdukiewicz
7e49fc828d Recognize armv7ve as valid ARMv7 target.
Docs: https://gcc.gnu.org/onlinedocs/gcc/ARM-Options.html

'armv7ve' - The extended version of the ARMv7-A architecture with support for virtualization.

Signed-off-by: Bartłomiej Burdukiewicz <bartlomiej.burdukiewicz@gmail.com>
2022-06-21 18:31:24 +02:00
XMRig
fdfbb60840 Update deps. 2022-06-19 13:39:32 +07:00
xmrig
ee51dec499 Merge pull request #3068 from SChernykh/dev
Better fix for daemon solo mining with ZMQ
2022-06-13 03:37:56 +07:00
SChernykh
575742078c Better fix for daemon solo mining with ZMQ 2022-06-12 22:32:50 +02:00
xmrig
6bab67bced Merge pull request #3067 from SChernykh/dev
Monero v15 network upgrade support and more house keeping
2022-06-13 01:16:34 +07:00
SChernykh
db9069897d Improved daemon ZMQ mining stability 2022-06-12 14:41:47 +02:00
SChernykh
30641b1bdf Fixed ZMQ debug log 2022-06-12 12:33:09 +02:00
SChernykh
45061f40d8 Monero v15 network upgrade support 2022-06-12 11:49:54 +02:00
SChernykh
9f70752090 Fixed debug GhostRider build 2022-06-12 11:47:56 +02:00
SChernykh
22d6a7525e Removed deprecated AstroBWTv1 and v2 2022-06-12 11:47:36 +02:00
benthetechguy
c0bce256e1 Add x86 to README 2022-05-31 21:15:37 -04:00
xmrig
09a7219651 Merge pull request #3055 from benthetechguy/patch-1
Add armv7 to README
2022-05-21 15:50:01 +07:00
benthetechguy
97869f3347 Add armv7 to supported architectures 2022-05-20 23:19:34 -04:00
xmrig
1bbbff7d17 Merge pull request #3054 from SChernykh/dev
Fixes for 32-bit ARM
2022-05-21 09:57:17 +07:00
SChernykh
97683e5719 Fixes for 32-bit ARM 2022-05-20 21:16:10 +02:00
xmrig
059d5d8421 Merge pull request #3051 from SChernykh/dev
Fixed unaligned memory read in DMI
2022-05-20 09:11:26 +07:00
SChernykh
285719cde4 Fixed unaligned memory read in DMI 2022-05-19 20:56:19 +02:00
xmrig
c877ba8145 Merge pull request #3042 from SChernykh/dev
Fixed being unable to resume from pause-on-battery
2022-05-06 02:14:52 +07:00
SChernykh
6793981066 Fixed being unable to resume from pause-on-battery
Fixes #3041
2022-05-05 21:13:02 +02:00
xmrig
1ae9a4e428 Merge pull request #3031 from SChernykh/dev
Fixed --cpu-priority not working sometimes
2022-04-20 07:44:33 +07:00
SChernykh
0e57053c5a Fixed --cpu-priority not working sometimes 2022-04-19 19:57:12 +02:00
xmrig
232d2d6dc5 Merge pull request #3020 from SChernykh/dev
Removed old AstroBWT algorithm
2022-04-15 16:03:26 +07:00
SChernykh
a3cb74f29b Removed old AstroBWT algorithm
It's not used anywhere now.
2022-04-15 10:59:31 +02:00
XMRig
56753d7c4a v6.17.1-dev 2022-04-06 01:58:24 +07:00
XMRig
f7b9e3ca67 Merge branch 'master' into dev 2022-04-06 01:58:03 +07:00
XMRig
56c95703a5 v6.17.0 2022-04-05 21:46:01 +07:00
XMRig
eadf272425 Merge branch 'dev' 2022-04-05 21:45:26 +07:00
XMRig
cb227a0a79 Merge branch 'dev' of github.com:xmrig/xmrig into dev 2022-04-05 15:15:47 +07:00
XMRig
4c171bea1e Disable donate for astrobwt/v2. 2022-04-05 15:15:03 +07:00
xmrig
e55a854314 Update CHANGELOG.md 2022-04-04 20:33:39 +07:00
XMRig
5bdfafd719 v6.17.0-dev 2022-04-04 20:17:40 +07:00
xmrig
15a2091837 Merge pull request #2991 from SChernykh/dev
Fixed compilation error
2022-03-24 22:46:33 +07:00
SChernykh
48bd09f730 Fixed compilation error 2022-03-24 16:38:47 +01:00
xmrig
21fb970949 Merge pull request #2990 from SChernykh/dev
Optimized keccak
2022-03-24 22:22:21 +07:00
SChernykh
23c12fc351 Optimized keccak
Big astrobwt/v2 speedup on non-AVX2 CPUs: **Core i7-2600 +64% (17 -> 28 kh/s)**
2022-03-24 13:10:03 +01:00
xmrig
71d193676a Merge pull request #2974 from SChernykh/dev
Fixed AstroBWT OpenCL config generation
2022-03-16 16:19:08 +07:00
SChernykh
baef34ba8c Fixed AstroBWT OpenCL config generation 2022-03-16 10:15:38 +01:00
xmrig
95a739d821 Merge pull request #2969 from SChernykh/dev
Dero HE (astrobwt/v2) OpenCL support
2022-03-15 08:51:46 +07:00
SChernykh
7b9135aadc Dero HE (astrobwt/v2) OpenCL support 2022-03-14 20:13:31 +01:00
xmrig
e6f694ca9e Merge pull request #2958 from SChernykh/dev
Fixed out of bounds access in astrobwt/v2
2022-03-10 06:40:34 +07:00
xmrig
afd79e7537 Merge pull request #2961 from SChernykh/derohe_cuda
Dero HE (astrobwt/v2) CUDA config generator
2022-03-10 06:37:30 +07:00
SChernykh
a2728af4f7 Dero HE (astrobwt/v2) CUDA config generator 2022-03-10 00:24:49 +01:00
SChernykh
65dbded9c4 Fixed out of bounds access in astrobwt/v2 2022-03-08 22:31:34 +01:00
XMRig
f25e65b5ac Update hwloc for MSVC builds. 2022-03-07 04:29:13 +07:00
XMRig
bbb19ea2f9 #2941 Update deps scripts. 2022-03-07 00:27:49 +07:00
xmrig
1c5b332add Merge pull request #2954 from SChernykh/dev
Dero HE fork support (astrobwt/v2 algorithm)
2022-03-06 04:18:43 +07:00
SChernykh
87fd0ea94a Added alternative algo names for Dero HE 2022-03-05 13:32:16 +01:00
SChernykh
4a42dca2cb Show block/miniblock counters more often 2022-03-05 10:00:39 +01:00
SChernykh
b674fafa0f DaemonClient: fixed broken coin setting 2022-03-05 09:56:30 +01:00
SChernykh
b5da73389f Dero HE fork support (astrobwt/v2 algorithm) 2022-03-05 00:31:18 +01:00
XMRig
bf5e38545c Fixed displayed DMI memory information for empty slots. 2022-03-01 02:50:30 +07:00
xmrig
f7543ada60 Merge pull request #2932 from SChernykh/dev
Fixed GhostRider with hwloc disabled
2022-02-16 19:23:26 +07:00
SChernykh
95e1705fc8 Fixed GhostRider with hwloc disabled 2022-02-16 08:13:48 +01:00
XMRig
2d0b07afbc v6.16.5-dev 2022-02-05 16:22:55 +07:00
XMRig
b33ccf0e0b Merge branch 'master' into dev 2022-02-05 16:21:19 +07:00
XMRig
4f5f9bdffb v6.16.4 2022-02-04 16:11:37 +07:00
XMRig
4d3e3daa6a Merge branch 'dev' 2022-02-04 16:10:58 +07:00
xmrig
802029e5f5 Update CHANGELOG.md 2022-02-04 15:14:46 +07:00
XMRig
14117e9658 #2910 Fixed donation for GhostRider/RTM. 2022-01-31 14:29:41 +07:00
xmrig
7ccb1d65f0 Merge pull request #2908 from Spudz76/dev-addMSVC2022
Add MSVC/2022 to version.h
2022-01-31 10:14:47 +07:00
Tony Butler
15de3cc16c Add MSVC/2022 to version.h 2022-01-28 21:09:24 -07:00
xmrig
124daa4afd Merge pull request #2898 from SChernykh/armv7
Fixed armv7 compilation
2022-01-26 23:38:45 +07:00
xmrig
5de1609b7d Merge pull request #2904 from SChernykh/dev
Fixed unaligned memory accesses
2022-01-26 23:26:03 +07:00
SChernykh
644f4cc017 Fixed unaligned memory accesses 2022-01-26 17:18:18 +01:00
XMRig
41a3f97060 v6.16.4-dev 2022-01-25 23:21:54 +07:00
XMRig
452080cfbd Merge branch 'master' into dev 2022-01-25 23:21:21 +07:00
XMRig
4f103b6b45 v6.16.3 2022-01-25 21:53:47 +07:00
XMRig
39609c9183 Merge branch 'dev' 2022-01-25 21:53:19 +07:00
xmrig
2adb7b2b74 Update CHANGELOG.md 2022-01-25 20:57:06 +07:00
SChernykh
3673137df6 Fixed armv7 compilation
Fix for error `Unsupported target. Must be either ARMv7-A+NEON or ARMv8-A.`
2022-01-25 12:37:41 +01:00
xmrig
faa7095865 Merge pull request #2893 from SChernykh/dev
KawPow OpenCL: use separate UV loop for building programs
2022-01-24 19:30:24 +07:00
SChernykh
e0701f9dad KawPow OpenCL: build next period only when it's not in cache 2022-01-24 13:28:58 +01:00
SChernykh
14aacf8636 KawPow OpenCL: use separate UV loop for building programs
Fixes #2890: uv_default_loop() can't be used there because UV loops are not thread safe.
2022-01-24 13:20:04 +01:00
xmrig
c764441337 Update CHANGELOG.md 2022-01-22 00:05:54 +07:00
xmrig
05fae12a63 Merge pull request #2882 from benthetechguy/armv7-gcc
armv7 compilation fix
2022-01-21 23:52:59 +07:00
XMRig
8059ce67f9 Add missing DNS options to config example. 2022-01-21 20:17:00 +07:00
benthetechguy
10111fd7f9 armv7 compilation fix
Compilation fails for armv7 on gcc 11, and updating the version in that line fixes it.
2022-01-20 20:47:26 -05:00
xmrig
2d25bec2df Merge pull request #2873 from SChernykh/dev
Fixed GhostRider benchmark on single-core systems
2022-01-18 10:13:16 +07:00
SChernykh
cab244d468 Fixed GhostRider benchmark on single-core systems
Fixes #2871
2022-01-17 19:59:21 +01:00
xmrig
4001488888 Merge pull request #2856 from SChernykh/dev
Fix for short responses from some Raptoreum pools
2022-01-05 10:22:39 +07:00
SChernykh
9bec1521b8 Fix for short responses from some Raptoreum pools 2022-01-04 23:54:59 +01:00
xmrig
7bde3ed5f7 Merge pull request #2848 from Spudz76/dev-addClientReconnect
Add support for client.reconnect method
2021-12-30 20:44:22 +07:00
Tony Butler
2e738509bb Add support for client.reconnect method 2021-12-30 06:26:52 -07:00
xmrig
f5447088cb Merge pull request #2837 from SChernykh/dev
RandomX: don't restart mining threads when the seed changes
2021-12-26 18:03:48 +07:00
SChernykh
7f2f50a8d9 RandomX: don't restart mining threads when the seed changes
It helps to not loose huge pages when the seed changes (every 2048 blocks, ~2.8 days).
2021-12-25 13:39:15 +01:00
xmrig
5747ccfafc Merge pull request #2827 from SChernykh/dev
GhostRider: set correct priority for helper threads
2021-12-20 18:07:23 +07:00
SChernykh
93081eb1f6 GhostRidere: set correct priority for helper threads
Fixes #2825
2021-12-20 12:05:17 +01:00
xmrig
4bf65c8669 Update README.md 2021-12-19 22:26:50 +07:00
xmrig
1a6fc3a665 Merge pull request #2815 from SChernykh/dev
Fixed cn-heavy in 32-bit builds
2021-12-16 10:44:16 +07:00
SChernykh
8dede14ac8 Fixed cn-heavy in 32-bit builds 2021-12-15 21:17:25 +00:00
xmrig
20687a397e Merge pull request #2782 from SChernykh/dev
Updated GhostRider documentation
2021-12-03 22:16:33 +07:00
SChernykh
454f97fa0f Updated GhostRider documentation
Added examples for SSL port command line that don't use #1 pool.
2021-12-03 12:30:09 +01:00
xmrig
8149fc7dcb Merge pull request #2778 from SChernykh/dev
Fixed "READY threads X/X" display after algo switching
2021-12-03 15:02:58 +07:00
SChernykh
a39ab89236 Fixed "READY threads X/X" display after algo switching 2021-12-03 07:44:23 +01:00
XMRig
5b8501fb57 v6.16.3-dev 2021-12-02 22:10:57 +07:00
XMRig
039be2ab75 Merge branch 'master' into dev 2021-12-02 22:10:23 +07:00
XMRig
718c7e0fc1 v6.16.2 2021-12-02 20:55:27 +07:00
XMRig
ef7951b91d Merge branch 'dev' 2021-12-02 20:54:50 +07:00
xmrig
214b1f021b Update CHANGELOG.md 2021-12-02 20:52:53 +07:00
XMRig
81b18c0741 #2771 Fixed environment variables support in EthStratumClient. 2021-12-02 19:36:51 +07:00
xmrig
8e83f72456 Merge pull request #2772 from SChernykh/dev
Compilation fixes
2021-12-02 19:36:09 +07:00
SChernykh
c2ae625032 Compilationn fixes 2021-12-02 13:34:24 +01:00
xmrig
60566dc84c Merge pull request #2769 from SChernykh/compiler_fix
Performance fixes
2021-12-02 10:00:29 +07:00
SChernykh
4ea8fe694d GhostRider benchmark: added 20 more possible rounds 2021-12-01 20:26:41 +01:00
SChernykh
669d1ab008 Updated changelog and GhostRider readme 2021-12-01 18:14:01 +01:00
SChernykh
e87d5111a2 Compiler fix 2021-12-01 17:08:40 +01:00
xmrig
56158779de Merge pull request #2761 from SChernykh/dev
Refactored Chrono::highResolutionMSecs()
2021-11-30 19:13:24 +07:00
SChernykh
efb322df66 Refactored Chrono::highResolutionMSecs()
Improved precision
2021-11-30 08:11:09 +01:00
xmrig
e673d541c1 Merge pull request #2751 from SChernykh/dev
VAES crash fixes
2021-11-30 09:49:37 +07:00
SChernykh
a98db529fb Explicitly use QueryPerformanceCounter() on Windows 2021-11-29 21:58:24 +01:00
SChernykh
1a9eaaad8f VAES crash fixes 2021-11-29 21:05:51 +01:00
XMRig
be5fbca9b6 v6.16.2-dev 2021-11-29 21:35:42 +07:00
XMRig
2feb264375 Merge branch 'master' into dev 2021-11-29 21:35:02 +07:00
XMRig
00990f2649 v6.16.1 2021-11-29 20:43:17 +07:00
XMRig
d78713be48 Merge branch 'dev' 2021-11-29 20:42:32 +07:00
XMRig
77367abe13 Fixed Clang build. 2021-11-29 16:01:16 +07:00
xmrig
cd046f6fd0 Merge pull request #2747 from SChernykh/dev
Disable VAES in 32-bit builds
2021-11-29 15:50:17 +07:00
SChernykh
63b7ec2887 Check compiler support for VAES 2021-11-29 09:48:15 +01:00
xmrig
a1e8f1c3e5 Merge pull request #2746 from Spudz76/dev-fixVAESCompile
Fix compile for VAES support with GCC<10
2021-11-29 15:38:35 +07:00
SChernykh
6db480a1ab Disable VAES in 32-bit builds 2021-11-29 09:32:00 +01:00
Tony Butler
a7acd9de6d Fix compile for VAES support with GCC<10 2021-11-28 22:11:42 -07:00
XMRig
a64f4d1870 v6.16.1-dev 2021-11-29 09:29:24 +07:00
XMRig
9bfe59b630 Merge branch 'master' into dev 2021-11-29 09:28:43 +07:00
xmrig
1a4bf16521 Merge pull request #2740 from SChernykh/dev
Added VAES support for Cryptonight variants
2021-11-29 09:26:45 +07:00
SChernykh
a4d5d0a75a Added VAES support for Cryptonight variants 2021-11-28 20:49:54 +01:00
xmrig
c40f1f9f66 Merge pull request #2738 from SChernykh/dev
More GhostRider fixes
2021-11-28 18:19:08 +07:00
SChernykh
15e5052dd0 More GhostRider fixes
- Fixed "difficulty is not a number" when diff is high on some pools
- Fixed GhostRider compilation when WITH_KAWPOW=OFF
2021-11-28 12:11:08 +01:00
xmrig
f9f7963453 Merge pull request #2734 from Spudz76/dev-nitpickWhitespace
Slash and burn EOL whitespace everywhere
2021-11-28 10:51:45 +07:00
Tony Butler
02240eff8c Slash and burn EOL whitespace everywhere 2021-11-27 17:59:40 -07:00
xmrig
d64c963e5e Merge pull request #2729 from SChernykh/dev
GhostRider hotfixes
2021-11-27 18:31:19 +07:00
SChernykh
c6292ce9ee GhostRider hotfixes
- Added average hashrate display
- Fixed the number of threads shown at startup
- Fixed `--threads` or `-t` command line option (but `--cpu-max-threads-hint` is recommended to use)
2021-11-27 12:27:26 +01:00
XMRig
cd652e2644 v6.16.0 2021-11-26 18:57:07 +07:00
XMRig
6f5ef0fe0f Merge branch 'dev' 2021-11-26 18:51:53 +07:00
xmrig
01fa968763 Update CHANGELOG.md 2021-11-26 18:50:34 +07:00
xmrig
8e6f3ad99e Merge pull request #2719 from SChernykh/dev
Added GhostRider release notes
2021-11-25 19:21:50 +07:00
SChernykh
b1f2479ec1 Added GhostRider release notes 2021-11-25 13:19:01 +01:00
XMRig
ecceba8ecd Add GhostRider support for AutoClient. 2021-11-25 17:44:36 +07:00
xmrig
cb5f4a9c17 Merge pull request #2716 from Spudz76/dev-initGR
Only initGhostRider() when job is in the family
2021-11-25 09:09:16 +07:00
Tony Butler
3a8ebfdcb6 Only initGhostRider() when job is in the family 2021-11-24 13:04:03 -07:00
xmrig
0dcafeb571 Merge pull request #2715 from SChernykh/dev
Benchmark support for GhostRider (offline only)
2021-11-24 22:05:44 +07:00
SChernykh
a1d7ee4c6b Benchmark support for GhostRider (offline only)
Command line:
```
./xmrig --bench=250K -a gr --rotation 15
```
Where `rotation` is an integer between 0 and 19 (inclusive).
2021-11-24 15:54:09 +01:00
XMRig
03e70ba2ed v6.16.0-dev 2021-11-24 19:49:21 +07:00
xmrig
19ef8c5d65 Merge pull request #2714 from SChernykh/gh3
GhostRider: fixed invalid hashes on ARMv8
2021-11-24 19:40:48 +07:00
SChernykh
63baa9e263 GhostRider: fixed invalid hashes on ARMv8 2021-11-24 13:39:55 +01:00
xmrig
1248bd5859 Merge pull request #2713 from SChernykh/gh3
Optimized quad hash for Ryzens
2021-11-24 18:21:01 +07:00
SChernykh
5c951ddb8a Optimized quad hash for Ryzens 2021-11-24 08:16:41 +01:00
xmrig
4ab0ad928d Merge pull request #2712 from SChernykh/gh3
GhostRider algorithm (Raptoreum) support
2021-11-24 09:49:34 +07:00
SChernykh
e67eb47796 Faster quad hash for GhostRider algos (Ryzen CPUs) 2021-11-23 22:14:46 +01:00
SChernykh
a6656a8c49 Fixed broken difficulty adjustment on some Raptoreum pools 2021-11-23 18:02:58 +01:00
SChernykh
a903d0a5bd Fixed compilation error 2021-11-23 08:52:30 +01:00
SChernykh
ceaebfd877 GhostRider algorithm (Raptoreum) support 2021-11-23 08:14:01 +01:00
xmrig
5156ff11a8 Merge pull request #2684 from SChernykh/fix-183
MSR mod: fix for error 183
2021-11-11 17:50:08 +07:00
xmrig
e0143a92a8 Merge pull request #2682 from SChernykh/dev
Fix: use cn-heavy optimization only for Vermeer CPUs
2021-11-11 17:49:51 +07:00
SChernykh
f682d9a2e9 MSR mod: fix for error 183
When WinRing0 driver starts, but some other version already created "\\.\WinRing0_1_2_0", it returns error 183 ERROR_ALREADY_EXISTS - "Cannot create a file when that file already exists."
2021-11-11 10:26:38 +01:00
SChernykh
3bece0ff40 Fix: use cn-heavy optimization only for Vermeer CPUs
Fixes #2680
2021-11-11 07:57:05 +01:00
XMRig
e6c456a970 v6.15.4-dev 2021-11-02 18:26:44 +07:00
XMRig
923d1d712f Merge branch 'master' into dev 2021-11-02 18:26:12 +07:00
XMRig
ae8459bd35 v6.15.3 2021-11-01 19:59:05 +07:00
XMRig
3a7be07c62 Merge branch 'dev' 2021-11-01 19:58:30 +07:00
xmrig
e1cc0000c6 Update CHANGELOG.md 2021-11-01 12:27:10 +07:00
xmrig
1210e8e95c Merge pull request #2644 from Spudz76/dev-fixMemleaks
Patch a couple minor leaks
2021-10-25 20:33:10 +07:00
xmrig
a45fbd9cae Merge pull request #2646 from SChernykh/dev
Fix MSVC compilation error
2021-10-25 20:31:12 +07:00
Tony Butler
f6d45f7990 Fix various memory leaks 2021-10-25 04:06:49 -06:00
SChernykh
b9464f993b Fix MSVC compilation error 2021-10-25 10:26:44 +02:00
xmrig
f8f73b0cd7 Merge pull request #2641 from SChernykh/dev
AstroBWT: fixed rare incorrect hashes
2021-10-20 07:24:15 +07:00
SChernykh
df6ab2edd8 AstroBWT: fixed rare incorrect hashes 2021-10-19 19:08:56 +02:00
xmrig
8bf7600154 Merge pull request #2639 from SChernykh/dev
AstroBWT even bigger speedup (up to +35%)
2021-10-19 22:50:07 +07:00
SChernykh
a30501956f AstroBWT even bigger speedup 2021-10-19 17:37:45 +02:00
xmrig
c287a40a20 Merge pull request #2636 from SChernykh/dev
AstroBWT speedup (up to +7%)
2021-10-19 07:58:24 +07:00
SChernykh
04f50c24e2 AstroBWT speedup 2021-10-18 18:05:51 +02:00
xmrig
7627b23212 Merge pull request #2614 from Spudz76/dev-fixAppleOpenCL
OpenCL fixes for non-AMD platforms
2021-10-13 06:20:53 +07:00
XMRig
e90e7febfb Merge branch 'StriderDM-merge_mining_tag_fix' into dev 2021-10-13 05:43:27 +07:00
XMRig
733b85a132 Code cleanup. 2021-10-13 05:43:05 +07:00
XMRig
35ba786e63 Merge branch 'merge_mining_tag_fix' of https://github.com/StriderDM/xmrig into StriderDM-merge_mining_tag_fix 2021-10-13 05:33:34 +07:00
David Main
446810a837 fix: expand validation of tx_extra for merge mining tag 2021-10-12 11:17:37 +02:00
Tony Butler
c6a68c3e51 Cap max threads to 4096 with nVidia OpenCL 2021-10-11 04:17:01 -06:00
Tony Butler
ca8bef3ade Adjust API version logic 2021-10-11 04:17:01 -06:00
Tony Butler
d735caa334 Adjust definitions and replace literal 0x4038 2021-10-11 04:17:01 -06:00
Tony Butler
eb54cc0e0f Revert amd_bitalign/amd_bfe polyfills 2021-10-11 04:17:01 -06:00
Tony Butler
84c67c37cd Apply "no-static-without-amd" fixes 2021-10-11 04:17:01 -06:00
Tony Butler
b44f38a362 Attempt repair of cn/r output-array access problem 2021-10-11 04:17:01 -06:00
Tony Butler
8ed4088d0a Second try at fixing cn/r atomic_inc() call 2021-10-11 04:17:01 -06:00
Tony Butler
cdcea2a4f9 Attempt fix for cn/r on Apple-AMD 2021-10-11 04:17:01 -06:00
Tony Butler
f0d80326ec Add Ellesmere correctly (still just a Polaris alias) 2021-10-11 04:17:01 -06:00
Tony Butler
cb8fc26cbe Add every Apple AMD GPU type 2021-10-11 04:17:01 -06:00
Tony Butler
5ec5b5ed00 Possibly fix problem with clGetProgramInfo crash 2021-10-11 04:17:01 -06:00
Tony Butler
67e29c1af1 Readjust OclDevice logic and add OCL_VENDOR_APPLE 2021-10-11 04:17:01 -06:00
xmrig
4bd94a79a4 Merge pull request #2623 from Spudz76/dev-fixWithoutKawpow
Fix #2583 compiling without kawpow (string ref is nonexistent then)
2021-10-11 16:41:44 +07:00
Tony Butler
80e597d951 Fix #2583 compiling without kawpow (string ref is nonexistent then) 2021-10-11 03:31:28 -06:00
XMRig
2e269f5b8c v6.15.3-dev 2021-10-06 02:01:29 +07:00
XMRig
57b8e35903 Merge branch 'master' into dev 2021-10-06 02:00:49 +07:00
XMRig
53be5765e6 v6.15.2 2021-10-05 23:28:29 +07:00
XMRig
68741c925b Merge branch 'dev' 2021-10-05 23:28:06 +07:00
xmrig
9ce207e667 Update CHANGELOG.md 2021-10-05 22:24:58 +07:00
XMRig
07e0966517 Added "--versions" alias. 2021-10-05 21:49:03 +07:00
XMRig
a9d4c2a923 Removed uv_os_gethostname call for all OS. 2021-09-28 23:56:33 +07:00
xmrig
dc02e1feaa Merge pull request #2606 from SChernykh/dev
Fix: AstroBWT auto-config ignored max-threads-hint
2021-09-26 18:51:47 +07:00
SChernykh
7daff331dc Fix: AstroBWT auto-config ignored max-threads-hint 2021-09-26 12:22:58 +02:00
XMRig
058a2fb0f4 v6.15.2-dev 2021-09-22 19:13:07 +07:00
XMRig
4fff3b946e Merge branch 'master' into dev 2021-09-22 19:12:38 +07:00
XMRig
f7aa5e781b v6.15.1 2021-09-22 13:08:00 +07:00
XMRig
298c5cccfa Merge branch 'dev' 2021-09-22 13:05:36 +07:00
xmrig
2985571620 Update CHANGELOG.md 2021-09-21 18:59:47 +07:00
xmrig
279d29cd7f Merge pull request #2594 from SChernykh/dev
Added Windows taskbar icon colors
2021-09-20 23:07:00 +07:00
SChernykh
387320ad6d Added Windows taskbar icon colors
- Red when there's no connection to any pool
- Yellow when mining is paused
- No color during normal mining
2021-09-20 18:03:22 +02:00
XMRig
76cd83edb2 Merge branch 'Spudz76-dev-fixAsteriskProfiling' into dev 2021-09-20 20:56:11 +07:00
XMRig
7f4d667351 Remove unnecessary string. 2021-09-20 20:53:36 +07:00
Tony Butler
8027716264 Fix --threads generates "*" profile without "kawpow":false to negate it. 2021-09-20 06:49:17 -06:00
xmrig
a459dd7741 Merge pull request #2591 from Spudz76/dev-fixCompileNoRX
Fix compile warning/crash when WITH_RANDOMX=OFF
2021-09-20 10:50:00 +07:00
Tony Butler
ef6011ac12 Fix compile warning when WITH_RANDOMX=OFF 2021-09-19 18:12:46 -06:00
xmrig
6d66051d92 Merge pull request #2586 from SChernykh/dev
Fixed Windows 7 compatibility
2021-09-17 17:11:09 +07:00
SChernykh
b2cc2ef0d7 Fixed Windows 7 compatibility
Fixes #2585
2021-09-17 12:05:37 +02:00
xmrig
9805320517 Merge pull request #2582 from Spudz76/dev-fixupRXnaming
Fixup RandomX naming consistency
2021-09-17 08:03:03 +07:00
Tony Butler
582d17bb84 Fixup RandomX naming consistency 2021-09-16 08:24:37 -06:00
XMRig
9e5f5b35a6 v6.15.1-dev 2021-08-31 18:57:08 +07:00
XMRig
9a9c69ff50 Merge branch 'master' into dev 2021-08-31 18:56:31 +07:00
XMRig
5c1f3f395c v6.15.0 2021-08-31 14:42:43 +07:00
XMRig
23cefffe43 Merge branch 'dev' 2021-08-31 14:41:47 +07:00
XMRig
d048d5a639 Fixed class/struct inconsistency. 2021-08-31 03:32:36 +07:00
xmrig
9a6f773dea Update CHANGELOG.md 2021-08-29 20:19:41 +07:00
XMRig
cd7c7902a9 Fixed clang build. 2021-08-29 18:52:11 +07:00
xmrig
fd3dad920d Merge pull request #2565 from SChernykh/dev
AstroBWT: add AVX2 Salsa20 implementation
2021-08-29 15:42:00 +07:00
SChernykh
3dc192f63e AstroBWT: add AVX2 Salsa20 implementation
+4.5% speedup on Ryzen 5 5600X
2021-08-29 10:35:43 +02:00
XMRig
123c7ab140 Added support for new CUDA plugin API. 2021-08-29 14:22:19 +07:00
XMRig
838996a0fc v6.15.0-dev 2021-08-28 19:53:28 +07:00
XMRig
6e4fea34a4 #2555 Update deps. 2021-08-28 13:10:48 +07:00
XMRig
b52c289931 Increase RANDOMX_PROGRAM_MAX_SIZE 2021-08-28 12:32:57 +07:00
XMRig
4dbb5b89da Update hwloc for MSVC. 2021-08-28 12:16:41 +07:00
XMRig
84d0212e79 Merge branch 'pr2563' into dev 2021-08-28 11:54:11 +07:00
XMRig
35acb3f00b Merge branch 'GraftRandomX' of https://github.com/Stardock2018/xmrig into pr2563 2021-08-28 11:50:17 +07:00
Chris
7f2771b466 Fixed Algorithm id
Algorithm id should be 0x72151267, second and third byte encode L3 and L2 size.
0x72 = 'r'
0x15 = 1 << 0x15 (L3 size)
0x12 = 1 << 0x12 (L2 size)
0x67 = 'g'
2021-08-27 10:31:36 -06:00
Chris
5fdf5516ff Added Graft RandonX 2021-08-27 08:19:54 -06:00
XMRig
234de96784 Update rapidjson. 2021-08-27 18:51:59 +07:00
XMRig
df4532d9a1 Cleanup ARM code. 2021-08-27 12:36:08 +07:00
XMRig
c27f535768 Fixed build on Linux. 2021-08-25 18:52:54 +07:00
XMRig
c7ac314110 Code cleanup based on Clang-Tidy. 2021-08-25 18:45:15 +07:00
XMRig
3215403815 Add missing files. 2021-08-23 18:43:14 +07:00
XMRig
bea2a6cf5b Update BlockTemplate class. 2021-08-23 18:32:58 +07:00
xmrig
a28f411339 Merge pull request #2548 from xmrig/feature-auto-coin
Added automatic coin detection for daemon mining
2021-08-19 15:35:37 +07:00
XMRig
460d9c75c5 Add global wallet address parser for DaemonClient. 2021-08-18 13:36:50 +07:00
XMRig
d1033abbe5 Update Coin, BlobReader and WalletAddress. 2021-08-17 08:17:21 +07:00
XMRig
9eac9dd30a v6.14.2-dev 2021-08-15 02:12:33 +07:00
XMRig
8d7b6adf98 Merge branch 'master' into dev 2021-08-15 02:11:29 +07:00
XMRig
230ff87634 v6.14.1 2021-08-15 00:42:47 +07:00
XMRig
19adf2630a Merge branch 'dev' 2021-08-15 00:42:12 +07:00
xmrig
3de4b16117 Update CHANGELOG.md 2021-08-15 00:37:23 +07:00
XMRig
602e3a7587 Fix algorithms order. 2021-08-14 05:48:37 +07:00
XMRig
4f6ffb67c1 Cleanup. 2021-08-14 04:58:01 +07:00
xmrig
a0194ddd18 Merge pull request #2537 from SChernykh/dev
Fixed Termux build
2021-08-13 21:14:35 +07:00
SChernykh
30f7e876a2 Update CnHash.cpp 2021-08-13 16:03:15 +02:00
SChernykh
5958490c23 Fixed Termux build 2021-08-13 12:02:03 +02:00
XMRig
f92ad4423d Fix Job::getNumTransactions. 2021-08-12 22:30:47 +07:00
XMRig
e0749a82c2 Fix cn-pico name. 2021-08-12 17:52:52 +07:00
xmrig
440aa003af Merge pull request #2532 from xmrig/feature-stable-algo-id
Refactoring: Stable (persistent) algorithms IDs.
2021-08-12 02:03:39 +07:00
XMRig
9580f5395f Removed shortName. 2021-08-11 22:26:34 +07:00
XMRig
e9ae4deb91 Removed duplicate strings. 2021-08-11 22:07:43 +07:00
XMRig
aee0762424 Fix typo. 2021-08-11 16:27:36 +07:00
XMRig
e6332eff2b Implemented stable algorithm ids. 2021-08-11 03:46:34 +07:00
XMRig
d0a632f557 Optimize CnHash storage. 2021-08-10 14:54:35 +07:00
XMRig
f4cdc527b0 #2527 Fix narrowing conversion. 2021-08-10 01:40:36 +07:00
XMRig
661dc515ab namespace cleanup. 2021-08-09 23:51:07 +07:00
XMRig
6d9bafe068 v6.14.1-dev 2021-08-09 17:20:15 +07:00
XMRig
202c8aaee8 Merge branch 'master' into dev 2021-08-09 17:19:48 +07:00
XMRig
410084384e v6.14.0 2021-08-09 16:09:15 +07:00
XMRig
43e98c509a Merge branch 'dev' 2021-08-09 16:08:20 +07:00
XMRig
08d79ddcdc v6.14.0-dev 2021-08-08 19:36:54 +07:00
xmrig
0fdf063760 Merge pull request #2512 from SChernykh/dev
Show the number of transactions in pool job
2021-08-08 00:52:06 +07:00
SChernykh
929205536c Show the number of transactions in pool job
Useful to check if pool/proxy is working properly and can also be used to compare different pools.
2021-08-07 19:38:31 +02:00
XMRig
d24581c963 #2492 Add missing --huge-pages-jit command line option. 2021-07-24 12:27:48 +07:00
xmrig
2eb2e90631 Merge pull request #2484 from SChernykh/zmq
ZeroMQ support for solo mining
2021-07-17 17:14:42 +07:00
SChernykh
0842e6b9d2 ZeroMQ support for solo mining
Gets new blocks from daemon immediately without polling, saving ~0.5 seconds on average when daemon gets new block from the network. Also saves some CPU cycles because it doesn't need to poll daemon every second.

Testing: add "daemon-zmq-port": 28083 to xmrig's pool config in config.json and run ./monerod --testnet --zmq-pub tcp://127.0.0.1:28083
2021-07-15 11:13:14 +02:00
XMRig
93805cd167 #2476 Fixed crash in DMI memory reader. 2021-07-06 23:07:31 +07:00
xmrig
755fe28bc3 Merge pull request #2472 from SChernykh/dev
Updates from xmrig-proxy
2021-07-05 19:13:14 +07:00
SChernykh
59d780169f Merge branch 'dev' of https://github.com/SChernykh/xmrig into dev 2021-07-05 13:57:16 +02:00
SChernykh
a30ede04f3 Updates from xmrig-proxy 2021-07-05 13:56:37 +02:00
XMRig
3f2dfa4279 Sync with proxy. 2021-07-05 02:31:29 +07:00
XMRig
7177b42903 v6.13.2-dev 2021-07-03 16:00:30 +07:00
XMRig
21638c2f58 Merge branch 'master' into dev 2021-07-03 16:00:05 +07:00
XMRig
02b2b87bb6 v6.13.1 2021-07-03 15:29:49 +07:00
XMRig
c8a9dba8fd Merge branch 'dev' 2021-07-03 15:29:14 +07:00
xmrig
9a77d39a3f Update CHANGELOG.md 2021-07-03 15:16:47 +07:00
xmrig
28a1d0fe1e Merge pull request #2468 from SChernykh/dev
Fix: don't send miner signature during regular mining
2021-07-02 00:37:04 +07:00
XMRig
0243789c04 v6.13.1-dev 2021-07-02 00:36:32 +07:00
XMRig
45dd58f808 Merge branch 'master' into dev 2021-07-02 00:35:52 +07:00
SChernykh
1b4abe1e98 Fix: don't send miner signature during regular mining 2021-07-01 19:31:55 +02:00
XMRig
9f778742a6 v6.13.0 2021-07-01 20:03:52 +07:00
XMRig
015f8aeed4 Merge branch 'dev' 2021-07-01 20:02:38 +07:00
xmrig
9e6311a7e0 Update CHANGELOG.md 2021-07-01 13:54:09 +07:00
XMRig
0af9d2e75b v6.13.0-dev 2021-06-28 19:02:48 +07:00
xmrig
6e2a84a46c Merge pull request #2445 from SChernykh/miner_signature
Support for solo mining with miner signatures (Wownero)
2021-06-28 18:11:13 +07:00
SChernykh
6bb8913066 Correct handling of block submit responses for Dero 2021-06-24 18:06:07 +02:00
SChernykh
cf104ebdc5 Update signing algorithm 2021-06-21 23:49:13 +02:00
XMRig
ecba750442 Add token support for online benchmark. 2021-06-20 09:28:39 +07:00
SChernykh
3967badc55 Added profiling 2021-06-19 16:19:16 +02:00
SChernykh
3f3f9b0661 Fixed GCC warnings 2021-06-19 14:54:03 +02:00
SChernykh
e3fc78a66c Fix Wownero hardfork version 2021-06-18 13:52:24 +02:00
SChernykh
e6d833c227 Proxy miner signature support 2021-06-17 22:48:08 +02:00
SChernykh
ebe299902c Proxy miner signature support (WIP) 2021-06-17 16:58:18 +02:00
SChernykh
bc63b63a2a More sanity checks 2021-06-17 13:18:34 +02:00
SChernykh
e739e7d704 More error handling in DaemonClient::parseJob 2021-06-17 10:39:22 +02:00
SChernykh
1bae083587 Fixed CalculateMerkleTreeHash 2021-06-17 10:26:17 +02:00
SChernykh
88959bd703 BlockTemplate: miner tx and root hash updating 2021-06-16 23:44:05 +02:00
SChernykh
93e689d601 Fix buffer size in generateMinerSignature 2021-06-16 18:20:11 +02:00
SChernykh
a136790bee Added support for solo mining with miner signatures (Wownero) 2021-06-16 18:07:36 +02:00
SChernykh
29f2dd4b9e Cleanup 2021-06-16 11:47:17 +02:00
SChernykh
3003c067d3 Fixed random32_unbiased 2021-06-16 00:19:49 +02:00
SChernykh
89bc6418b1 Secret key derivation 2021-06-16 00:10:34 +02:00
SChernykh
8458b4ee39 Added signature functions 2021-06-15 15:51:29 +02:00
SChernykh
7bfb801ce2 Cryptonote tools WIP 2021-06-15 00:28:32 +02:00
xmrig
4567499905 Merge pull request #2433 from candrews/patch-2
Fix shellcheck warnings in randomx_boost.sh
2021-06-09 23:41:58 +07:00
Craig Andrews
9b63955b09 Fix shellcheck warnings in randomx_boost.sh
Checked using www.shellcheck.net

Specific issues addessed:
* https://github.com/koalaman/shellcheck/wiki/SC2002
* Use POSIX instead of bash for wider compatibility
* Fail on error
2021-06-08 21:56:02 -04:00
XMRig
0414511de0 v6.12.3-dev 2021-05-31 13:51:41 +07:00
XMRig
b61dad128c Merge branch 'master' into dev 2021-05-31 13:49:35 +07:00
XMRig
80ae339343 v6.12.2 2021-05-31 12:58:30 +07:00
XMRig
4d87555398 Merge branch 'dev' 2021-05-31 12:57:55 +07:00
xmrig
bef82c5de6 Update CHANGELOG.md 2021-05-30 21:28:28 +07:00
xmrig
b069ad5dd1 Merge pull request #2358 from zzjzxq33/patch-1
Update openssl version to 1.1.1k
2021-05-30 17:53:53 +07:00
xmrig
f6a0646271 Merge pull request #2401 from SChernykh/dev
RandomX: fix broken light mode mining
2021-05-22 18:54:29 +07:00
SChernykh
b5f1a1feae RandomX: fix broken light mode mining
It broke after #2395
2021-05-22 13:49:22 +02:00
XMRig
1ce059da1c Add "argon2/ninja" algorithm alias. 2021-05-22 15:10:50 +07:00
xmrig
2929451ee1 Merge pull request #2398 from SChernykh/dev
RandomX ARMv8: optimized dataset read
2021-05-21 09:58:54 +07:00
SChernykh
94fecb5e92 RandomX ARMv8: optimized dataset read
Break dependency from readReg2 and readReg3. It should run faster on superscalar and out-of-order CPUs i.e. Apple M1.
2021-05-20 21:24:28 +02:00
xmrig
3bfa5ea038 Merge pull request #2395 from SChernykh/dev
RandomX: rewrote dataset read code
2021-05-20 18:58:48 +07:00
SChernykh
ff82ca57f2 RandomX: rewrote dataset read code
Unified code for AMD and Intel
1% faster on Intel
0.15% faster on AMD Ryzen
2021-05-20 12:45:42 +02:00
xmrig
7f7b1fb073 Merge pull request #2393 from SChernykh/dev
RandomX: added BMI2 version for scratchpad prefetch
2021-05-19 22:54:58 +07:00
SChernykh
d443dd86f1 RandomX: added BMI2 version for scratchpad prefetch
Saves 1 instruction and 1 byte in the main loop.
2021-05-19 17:52:16 +02:00
xmrig
3ac8f6b23a Merge pull request #2386 from SChernykh/dev
Enabled IMUL_RCP optimization for light mode mining
2021-05-17 16:36:23 +07:00
SChernykh
9b1f020a8b Enabled IMUL_RCP optimization for light mode mining
Better fix for #2377
2021-05-17 11:26:40 +02:00
XMRig
8bf88a4e74 Merge branch 'Spudz76-dev-fixCLKawPowPlatformHandling' into dev 2021-05-16 10:10:33 +07:00
XMRig
08a2c143f5 Regenerate OpenCL headers. 2021-05-16 10:09:29 +07:00
Tony Butler
4eb9a1aad5 Fix CL code for KawPow where it assumes everything is AMD 2021-05-15 20:34:57 -06:00
xmrig
c8c40586a1 Merge pull request #2378 from SChernykh/dev
Fixed broken light mode mining on x86
2021-05-16 07:03:57 +07:00
SChernykh
29cb416107 Fixed broken light mode mining on x86 2021-05-15 21:41:39 +02:00
xmrig
465169ff12 Merge pull request #2375 from Spudz76/dev-fixMacOSCudaLoader
Fixup MacOS CUDA backend default loader name
2021-05-14 18:48:09 +07:00
Tony Butler
df2bcd8192 Fixup MacOS CUDA backend default loader name 2021-05-14 05:28:31 -06:00
zzjzxq33
d89bb56964 Update openssl version to 1.1.1k 2021-05-09 11:11:46 +08:00
XMRig
87a0864e3b ...and --cpu-affinity. 2021-05-08 04:36:09 +07:00
XMRig
ecf5579f36 #2351 Fixed help output for --cpu-priority option. 2021-05-08 04:34:22 +07:00
xmrig
d5523d819f Merge pull request #2341 from SChernykh/dev
Update sse2neon.h
2021-05-03 23:17:12 +07:00
SChernykh
dbda2e9ccd Update sse2neon.h 2021-05-03 18:08:59 +02:00
xmrig
8babd7bc0a Merge pull request #2340 from SChernykh/dev
Fix AES detection on FreeBSD on ARM
2021-05-03 19:06:49 +07:00
SChernykh
27ced139a6 Fix AES detection on FreeBSD on ARM 2021-05-03 09:57:43 +02:00
xmrig
b46849e813 Merge pull request #2322 from SChernykh/dev
Update randomx_boost.sh
2021-04-28 19:12:37 +07:00
SChernykh
a96a6108ff Update randomx_boost.sh
- Support builtin MSR, see #2283
- Added detection of AMD EPYC CPUs
2021-04-28 14:10:30 +02:00
xmrig
c50c78b700 Merge pull request #2312 from SChernykh/dev
Add  missing allow_writes=on to randomx_boost.sh
2021-04-25 20:46:07 +07:00
SChernykh
cd7ab2c79f Add missing allow_writes=on to randomx_boost.sh 2021-04-25 15:31:30 +02:00
XMRig
695fbc013b #2280 Disable GPU backends in benchmark mode. 2021-04-25 15:28:45 +07:00
XMRig
a403c53543 Merge branch 'jsonboss-patch-1' into dev 2021-04-24 23:22:56 +07:00
XMRig
e26fbc96e9 Removed unnecessary system call. 2021-04-24 23:22:10 +07:00
XMRig
259c165e60 Merge branch 'patch-1' of https://github.com/jsonboss/xmrig into jsonboss-patch-1 2021-04-24 22:14:59 +07:00
XMRig
7897bf02dc v6.12.2-dev 2021-04-24 01:53:07 +07:00
XMRig
05f62c5ccc Merge branch 'master' into dev 2021-04-24 01:52:37 +07:00
XMRig
d82e100e30 v6.12.1 2021-04-23 19:43:12 +07:00
XMRig
5f869a414c Merge branch 'dev' 2021-04-23 19:42:29 +07:00
xmrig
7fd6be7d83 Update CHANGELOG.md 2021-04-23 18:54:42 +07:00
xmrig
ae6c536e98 Merge pull request #2296 from SChernykh/dev
Fixed Zen3 asm for cn/upx2
2021-04-21 19:52:52 +07:00
XMRig
c66c593123 v6.12.1-dev 2021-04-21 19:51:03 +07:00
XMRig
b3788b2ba3 Merge branch 'master' into dev 2021-04-21 19:49:54 +07:00
SChernykh
b7adb34c37 Fixed Zen3 asm for cn/upx2
- Invalid rounding mode was used which caused rejected shares sometimes
- Also optimized CN implode/explode functions a bit.
2021-04-21 13:22:25 +02:00
XMRig
ace8409a56 v6.12.0 2021-04-20 20:55:58 +07:00
XMRig
e2c757d9dd Merge branch 'dev' 2021-04-20 20:55:35 +07:00
xmrig
da35de993f Update CHANGELOG.md 2021-04-19 23:20:10 +07:00
xmrig
854b7618ef Merge pull request #2289 from SChernykh/dev
RandomX: optimized IMUL_RCP instruction
2021-04-19 22:54:02 +07:00
SChernykh
3477f9fbc1 RandomX: optimized IMUL_RCP instruction
+0.4% on AMD Zen2
+0.3% on AMD Zen3
+0.1% on Intel SandyBridge
+0.3% on rx/wow on Intel SandyBridge
2021-04-19 17:43:58 +02:00
xmrig
5799744f2f Update CHANGELOG.md 2021-04-19 20:56:45 +07:00
xmrig
61d165a314 Merge pull request #2287 from SChernykh/dev
Fixed rounding mode after running cn/upx
2021-04-19 18:06:16 +07:00
SChernykh
69186f2470 Optimized cn/upx for Zen3
0.9% faster
2021-04-19 12:29:44 +02:00
SChernykh
730d4a6cee Fix dvision by zero check in percent() 2021-04-19 12:05:07 +02:00
SChernykh
54bc91d5e3 Fixed rounding mode after running cn/upx 2021-04-19 12:02:57 +02:00
jsonboss
2012ffb231 support builtin msr 2021-04-19 10:38:27 +08:00
XMRig
5f9e0ebc6c v6.12.0-dev 2021-04-18 20:12:03 +07:00
xmrig
f314c69a70 Merge pull request #2278 from SChernykh/dev
Optimized cn/upx2
2021-04-17 23:41:26 +07:00
SChernykh
16fe462cad Optimized cn/upx2 for Ryzen CPUs 2021-04-17 18:18:26 +02:00
xmrig
e6e2987ddf Merge pull request #2276 from SChernykh/dev
Added support for Uplexa (cn/upx2 algorithm)
2021-04-17 20:10:54 +07:00
SChernykh
ed456b02cf Update CnHash.cpp 2021-04-17 15:06:31 +02:00
SChernykh
da7f5826cb Added support for Uplexa (cn/upx2 algorithm) 2021-04-17 14:53:42 +02:00
XMRig
6cb398bb42 Merge branch 'dev' of github.com:xmrig/xmrig into dev 2021-04-14 23:44:42 +07:00
XMRig
748be760e8 Added support for --user command line option for the benchmark. 2021-04-14 23:43:31 +07:00
xmrig
4a4118bb8e Merge pull request #2261 from SChernykh/dev
Show total hashrate if compiled without OpenCL
2021-04-13 19:06:42 +07:00
SChernykh
77f1bf0861 Show total hashrate if compiled without OpenCL 2021-04-13 14:02:29 +02:00
XMRig
6bb29b3e7b v6.11.3-dev 2021-04-11 21:13:39 +07:00
XMRig
f720772338 Merge branch 'master' into dev 2021-04-11 21:13:08 +07:00
XMRig
e53e48b88c v6.11.2 2021-04-11 17:24:46 +07:00
XMRig
ecf36ee891 Merge branch 'dev' 2021-04-11 17:24:23 +07:00
xmrig
23ef949dd3 Update CHANGELOG.md 2021-04-11 11:45:07 +07:00
XMRig
92e708c6e7 Update llhttp to v5.1.0 2021-04-10 21:23:32 +07:00
XMRig
30cfcc27db #2207 Fixed regression in HTTP parser. 2021-04-10 21:02:59 +07:00
XMRig
3c6077fb02 v6.11.2-dev 2021-04-08 00:33:01 +07:00
XMRig
63883b4fa7 Merge branch 'master' into dev 2021-04-08 00:32:21 +07:00
XMRig
0f83b5e06c v6.11.1 2021-04-07 10:34:37 +07:00
XMRig
637a333197 Merge branch 'dev' 2021-04-07 10:33:48 +07:00
xmrig
3171b06048 Update CHANGELOG.md 2021-04-07 10:32:17 +07:00
xmrig
2a66a0fa2f Merge pull request #2239 from SChernykh/dev
Fixed broken "coin" setting functionality
2021-04-07 10:30:28 +07:00
SChernykh
c080d5b962 Fixed broken "coin" setting functionality 2021-04-06 23:02:10 +02:00
XMRig
0133107f14 v6.11.0 2021-04-06 21:11:44 +07:00
XMRig
253e349ef9 Merge branch 'dev' 2021-04-06 21:11:13 +07:00
xmrig
5126cc1414 Update CHANGELOG.md 2021-04-06 15:48:18 +07:00
XMRig
ea1245026d #2234 Use const_cast. 2021-04-06 12:07:06 +07:00
xmrig
2158adb711 Merge pull request #2234 from esrrhs/dev
fix build error on gcc 4.8.5
2021-04-06 12:00:36 +07:00
xmrig
8554bb4d9c Merge pull request #2235 from SChernykh/dev
Fixed cn-heavy for GCC-8
2021-04-04 18:09:09 +07:00
SChernykh
1741354498 Fixed cn-heavy for GCC-8 2021-04-04 10:18:27 +02:00
esrrhs
866e97efcf fix build error on gcc 9.3.0
FileLogWriter.h:34:41: error: array used as initializer
2021-04-04 12:42:14 +08:00
xmrig
277352d072 Merge pull request #2233 from SChernykh/dev
Fixed compilation for ARM
2021-04-03 23:03:05 +07:00
SChernykh
8cae605e1f Update randomx.cmake 2021-04-03 17:59:28 +02:00
SChernykh
59c85eaf6a Fixed compilation for ARM 2021-04-03 17:50:52 +02:00
xmrig
864233c110 Merge pull request #2228 from esrrhs/dev
remove useless v4_random_math_init if algo is not cn/r
2021-04-02 15:49:53 +07:00
xmrig
e9b32b3009 Merge pull request #2229 from SChernykh/dev
Don't use RandomX JIT if WITH_ASM=OFF
2021-04-02 15:47:51 +07:00
SChernykh
ec608bbd05 Don't use RandomX JIT if WITH_ASM=OFF
Because RandomX JIT use asm code
2021-04-02 10:05:46 +02:00
esrrhs
ec2793bcc9 remove useless v4_random_math_init if algo is not cn/r 2021-04-02 14:59:09 +08:00
xmrig
eb40f07552 Merge pull request #2225 from gentoo-monero/fix-2224
Add missing include
2021-04-01 17:27:53 +07:00
Matthew Smith
28f268aeba Add missing include
memory header ends up not being included when built without OpenCL
support.

Closes: https://github.com/xmrig/xmrig/issues/2224
2021-04-01 11:01:55 +01:00
XMRig
bad5458d40 Merge branch 'pr2217' into dev 2021-03-29 18:17:33 +07:00
XMRig
b72e21fc3c Merge branch 'master' of https://github.com/esrrhs/xmrig into pr2217 2021-03-29 18:16:45 +07:00
esrrhs
d578a3828f setBlob should run after setAlgorithm 2021-03-29 12:11:03 +08:00
xmrig
6c417eb9af Merge pull request #2216 from SChernykh/dev
Optimize cn-heavy in GCC builds
2021-03-28 21:13:45 +07:00
SChernykh
dc70893e6b Optimize cn-heavy in GCC builds
+0.7% in GCC builds, but GCC is still slower than MSVC on cn-heavy.
2021-03-28 16:12:09 +02:00
xmrig
c5c958743e Merge pull request #2214 from SChernykh/cn-heavy-opt
Optimized cn-heavy
2021-03-28 09:56:22 +07:00
xmrig
89f2fa6818 Merge pull request #2213 from SChernykh/dev
Fixed use-after-free bug when exiting
2021-03-28 09:55:50 +07:00
SChernykh
bcfd9edaa5 Optimized cn-heavy
- Remove unnecessary type conversion when doing `idx0 = d ^ q;`
- Saves 1 CPU cycle in the main loop
- 0.2% speedup on Ryzen 5 5600X, results on other CPUs may vary
2021-03-27 22:21:01 +01:00
SChernykh
e0f774d6dd Fixed use-after-free bug when exiting 2021-03-27 21:53:40 +01:00
XMRig
955cc366d1 v6.11.0-dev 2021-03-20 13:42:46 +07:00
xmrig
bc4f6249be Merge pull request #2196 from xmrig/feature-dns2
Improved DNS subsystem
2021-03-20 12:50:53 +07:00
XMRig
0d45600b0e Added command line options --dns-ipv6 and --dns-ttl. 2021-03-20 11:12:09 +07:00
XMRig
2c8f7f692c Added DNS config. 2021-03-20 00:09:59 +07:00
XMRig
3e41bdc552 New DNS implementation. 2021-03-16 22:24:37 +07:00
XMRig
5b189696d7 Added DnsRecords class. 2021-03-14 09:44:56 +07:00
XMRig
c6bcea3811 Improved DnsRecord class. 2021-03-13 20:30:52 +07:00
xmrig
900dd13c45 Merge pull request #2177 from SChernykh/dev
Fix `vld1q_u8_x4` compilation error with GCC 10.2
2021-03-13 08:30:44 +07:00
SChernykh
2876f17f65 Fix vld1q_u8_x4 compilation error with GCC 10.2 2021-03-12 16:26:02 +01:00
xmrig
b2563ca8a6 Merge pull request #2172 from bisand/patch-1
Added reference to limits.h in AdlLib_linux.cpp
2021-03-11 18:07:23 +07:00
André Biseth
7c0d60ac68 Added reference to limits.h in AdlLib_linux.cpp
Suggested solution to bug https://github.com/xmrig/xmrig/issues/2171
2021-03-11 11:50:05 +01:00
xmrig
813a1885cb Merge pull request #2169 from SChernykh/dev
Fix wrong type in Handle::deleteLater()
2021-03-11 06:26:27 +07:00
SChernykh
54bcf05b1d Fix wrong type in Handle::deleteLater()
Bug found by Address Sanitizer
2021-03-10 14:55:06 +01:00
XMRig
bbea8810a7 v6.10.1-dev 2021-03-08 06:04:59 +07:00
XMRig
b6514957f1 Merge branch 'master' into dev 2021-03-08 06:04:32 +07:00
XMRig
69590f9777 v6.10.0 2021-03-08 04:05:27 +07:00
xmrig
576ff120e5 Merge pull request #2128 from ianmaddox/patch-1
Minor verbiage tweak
2021-03-08 04:02:02 +07:00
xmrig
2d52118c1b Merge pull request #2161 from coolhaircut/patch-1
Added Userspace MSR permissions clarification in CPU.md
2021-03-08 04:01:15 +07:00
xmrig
28ad59d828 Merge pull request #2129 from felixonmars/patch-1
Correct a typo in doc/CPU.md
2021-03-08 04:00:38 +07:00
XMRig
e0c630f34f Merge branch 'dev' 2021-03-08 03:59:09 +07:00
XMRig
b8f9a326aa 6.10.0-dev 2021-03-07 01:44:38 +07:00
Cool Dude (with a cool haircut)
542617b6db Update CPU.md 2021-03-05 22:54:03 +00:00
XMRig
f5db50c9d7 Sync with the proxy. 2021-03-06 05:32:54 +07:00
XMRig
856c8e6bcd Fixed build without TLS support. 2021-03-06 02:07:10 +07:00
XMRig
b3dbf6e23f http-parser replaced to llhttp. 2021-03-06 01:46:49 +07:00
xmrig
a11c57226b Merge pull request #2158 from SChernykh/dev
Fix GCC compilation
2021-03-04 16:48:05 +07:00
SChernykh
94d2cac775 Fix GCC compilation 2021-03-04 10:45:39 +01:00
XMRig
548a7d46e1 Add note about CPU affinity. 2021-03-04 16:19:06 +07:00
xmrig
bebc163e25 Merge pull request #2157 from SChernykh/dev
Fix crash in cn-heavy on Zen3 with manual thread count
2021-03-04 16:03:54 +07:00
SChernykh
70cddc06ba Fix crash in cn-heavy on Zen3 with manual thread count 2021-03-04 10:02:35 +01:00
XMRig
1f9cdc0564 Update hwloc for MSVC. 2021-03-04 03:23:26 +07:00
XMRig
a5a7ee716d Update build scripts. 2021-03-03 19:38:54 +07:00
xmrig
d2f24d94b9 Merge pull request #2150 from TheGreatMcPain/dev
Update sse2neon.h to the latest master. Fixes build on armv7.
2021-03-02 19:41:11 +07:00
TheGreatMcPain
ba3299b61b Update sse2neon.h to the latest master. Fixes build on armv7.
A few days after this header was introduced. Upstream updated it with
armv7 versions of `_mm_aesenc_si128` which allows xmrig to build
on armv7.
2021-03-02 01:33:25 -06:00
xmrig
ca5dfe7c12 Merge pull request #2147 from SChernykh/dev
Fixed many "new job" messages when solo mining
2021-03-01 23:49:03 +07:00
SChernykh
91ad6fcf3d Fixed many "new job" messages when solo mining
Fix for https://github.com/xmrig/xmrig/issues/2127
2021-03-01 17:46:05 +01:00
XMRig
0b7dfaabe0 Code cleanup. 2021-03-01 19:04:03 +07:00
XMRig
6f8ffb7660 Fixed possible out of order write to log file. 2021-03-01 18:54:20 +07:00
XMRig
4a8e7510e1 #2123 Ignore regex exception. 2021-02-27 15:29:14 +07:00
Felix Yan
32876dd01d Correct a typo in doc/CPU.md 2021-02-24 04:36:27 +08:00
Ian Maddox
37df513b32 Minor verbiage tweak
Fixing mixed phrasing in error message
2021-02-23 11:34:10 -08:00
xmrig
31a5d05dc1 Merge pull request #2122 from SChernykh/dev
Fixed pause logic when both pause on battery and user activity are en…
2021-02-21 22:36:32 +07:00
SChernykh
d478d737c4 Fixed pause logic when both pause on battery and user activity are enabled 2021-02-21 16:33:57 +01:00
XMRig
e20daff4eb v6.9.1-dev 2021-02-21 22:28:15 +07:00
XMRig
1ccdcb1645 Merge branch 'master' into dev 2021-02-21 22:27:36 +07:00
XMRig
072881e1a1 v6.9.0 2021-02-21 21:23:48 +07:00
XMRig
0c4a3cfc30 Merge branch 'dev' 2021-02-21 21:23:15 +07:00
xmrig
cffd0f50a4 Update CPU.md 2021-02-21 20:22:06 +07:00
XMRig
4b1857114e v6.9.0-dev 2021-02-20 14:28:20 +07:00
XMRig
b49fb27e84 Added idle time detection for macOS. 2021-02-20 13:18:31 +07:00
XMRig
ee341118ce #2104 Added user configurable idle time. 2021-02-19 23:35:30 +07:00
XMRig
f599807bbb Simplified code, fixed broken pause. 2021-02-19 16:26:31 +07:00
xmrig
a2ad626012 Merge pull request #2117 from SChernykh/dev
Fixed crash when GPU mining cn-heavy on Zen3 system
2021-02-18 21:08:44 +07:00
SChernykh
e8a99809b6 Fixed crash when GPU mining cn-heavy on Zen3 system 2021-02-18 14:49:37 +01:00
XMRig
0fe20fe88c Merge remote-tracking branch 'remotes/origin/pr2112' into dev 2021-02-18 15:35:59 +07:00
XMRig
d1d1517b4f Fixed macOS build. 2021-02-18 15:22:39 +07:00
XMRig
5980675876 Code and copyright cleanup. 2021-02-18 12:56:39 +07:00
Hansie Odendaal
3b87cd97ce Allow result submission to origin daemon with self-select
With `self-select` mode enabled, the `submit-to-origin` config option
will let the `SelfSelectClient` submit the solution to both
the daemon where it got the template from as well as to
the connected pool, for miners that want to do pool minining
with Monero and solo mining with an altcoin (merged mining variant).

Thank you and special credit to @StriderDM (https://github.com/StriderDM)!
2021-02-17 18:05:13 +02:00
xmrig
d2f01cfa86 Merge pull request #2104 from SChernykh/dev
Added `pause-on-active` option
2021-02-15 11:04:14 +07:00
SChernykh
82830e359a Added pause-on-active option
Windows only for now. When set to true, pauses mining when user touches mouse or keyboard.
2021-02-14 15:32:18 +01:00
XMRig
8e3fec5768 v6.8.3 2021-02-12 22:51:26 +07:00
XMRig
4fd23a1bf4 Merge branch 'master' into dev 2021-02-12 22:50:52 +07:00
XMRig
8bfaddd3fc v6.8.2 2021-02-12 18:47:16 +07:00
XMRig
dabafaaadb Merge branch 'dev' 2021-02-12 18:46:41 +07:00
xmrig
5cda714254 Update CHANGELOG.md 2021-02-12 18:35:43 +07:00
xmrig
91151ce4a1 Merge pull request #2089 from SChernykh/dev
Optimized cn-heavy for Zen3
2021-02-08 16:24:16 +07:00
SChernykh
dc1443f3b8 Cryptonight: add prefetching to interleaved mode 2021-02-07 23:29:54 +01:00
SChernykh
8af8df25aa Optimized cn-heavy for Zen3
- Uses scratchpad interleaving to access only the closest L3 slice from each CPU core.
- Also activates MSR mod for cn-heavy because CPU prefetchers get confused with interleaving
- 7-8% speedup on Zen3
2021-02-07 22:05:11 +01:00
XMRig
b1e14dc1d3 Always disable kawpow for CPU backend. 2021-02-07 18:49:54 +07:00
XMRig
f460d76f8d Add missing option to config example. 2021-02-06 16:17:53 +07:00
xmrig
1c63e9efba Merge pull request #2080 from SChernykh/dev 2021-02-04 04:29:59 +07:00
SChernykh
21abbe4e84 Fix compile error in Termux 2021-02-03 19:05:05 +01:00
XMRig
3080f47cd6 v6.8.2-dev 2021-02-03 18:01:14 +07:00
XMRig
f4ebdaa8e5 Merge branch 'master' into dev 2021-02-03 18:00:42 +07:00
XMRig
1bcfd0cdea v6.8.1 2021-02-03 07:00:39 +07:00
XMRig
9396ecf93d Merge branch 'dev' 2021-02-03 06:57:11 +07:00
xmrig
a4af964696 Update CHANGELOG.md 2021-02-03 06:04:30 +07:00
XMRig
2c8d8ee2ab Fixed macOS build and compile warning. 2021-02-02 13:53:45 +07:00
xmrig
631a8ca802 Merge pull request #2077 from SChernykh/dev
Fix for illegal instruction crash on ARM
2021-02-02 04:57:36 +07:00
SChernykh
346892e170 Update jit_compiler_a64.cpp 2021-02-01 22:52:02 +01:00
SChernykh
db03573804 ARM JIT: added missing cache flush 2021-02-01 22:42:35 +01:00
SChernykh
e74573f81f Fixed code allocation for ARM 2021-02-01 22:36:11 +01:00
xmrig
0e70974d7d Merge pull request #2076 from xmrig/feature-flexible-hugepages
Added support for flexible huge page sizes on Linux.
2021-02-02 04:07:41 +07:00
xmrig
3a3ee91324 Merge pull request #2075 from SChernykh/dev
Fixed crashes on ARM
2021-02-02 03:06:58 +07:00
SChernykh
4108428872 Fixed crashes on ARM 2021-02-01 17:07:45 +01:00
XMRig
4c3425a958 Added "--hugepage-size" command line option. 2021-02-01 05:06:24 +07:00
XMRig
09624c4f9b Added support for flexible huge page sizes on Linux. 2021-01-31 23:38:57 +07:00
XMRig
8faef28e7d Detect Apple M1 on Linux. 2021-01-31 05:41:32 +07:00
XMRig
62450f4ed8 Update ARM CPUs names. 2021-01-31 03:53:22 +07:00
XMRig
2c52a5a352 #2066 Fixed AMD GPUs health data readings. 2021-01-30 02:42:59 +07:00
XMRig
7d52bd7454 Extend normalization rules. 2021-01-29 18:22:24 +07:00
XMRig
f68b105bd9 Normalize DMI memory slot name. 2021-01-29 04:23:50 +07:00
XMRig
9ca1a6129b #2066 Quick fix for AMD GPUs health data. 2021-01-29 01:23:35 +07:00
xmrig
7a3df1c0bb Merge pull request #2067 from SChernykh/dev
Fix compilation error when RandomX and Argon2 are disabled
2021-01-28 20:44:03 +07:00
SChernykh
22a1b8d82d Fix compilation error when RandomX and Argon2 are disabled 2021-01-28 14:38:28 +01:00
xmrig
0a462fbef5 Merge pull request #2064 from SChernykh/dev
Added documentation for config.json CPU options
2021-01-28 19:41:15 +07:00
SChernykh
f302b4b0ef Added documentation for config.json CPU options 2021-01-28 13:37:27 +01:00
XMRig
65fe26dc6c Don't print empty memory slots if the total count above 8. 2021-01-28 00:00:00 +07:00
XMRig
e6d4921e21 v6.8.1-dev 2021-01-26 16:40:10 +07:00
XMRig
f82d67e76e Merge branch 'master' into dev 2021-01-26 16:38:37 +07:00
XMRig
4e671a945d v6.8.0 2021-01-26 15:26:16 +07:00
XMRig
e38d277143 Merge branch 'dev' 2021-01-26 15:25:20 +07:00
XMRig
8eb9b4d37a Update default config example. 2021-01-26 15:15:08 +07:00
xmrig
2d45cc64c1 Update CHANGELOG.md 2021-01-26 15:08:05 +07:00
XMRig
b9081e992b Code cleanup 2021-01-25 22:00:42 +07:00
XMRig
1424b2975f Fixed DMI memory speed. 2021-01-24 15:56:02 +07:00
XMRig
0fa5db8fa3 Code cleanup. 2021-01-24 15:02:22 +07:00
xmrig
5999dccd57 Merge pull request #2058 from SChernykh/dev
RandomX JIT x86: remove unnecessary instructions
2021-01-24 13:59:56 +07:00
SChernykh
78922a0772 RandomX JIT x86: remove unnecessary instructions
Adopted from https://github.com/tevador/RandomX/pull/201
2021-01-23 22:28:50 +01:00
XMRig
bc3914883a Merge branch 'alvv-z-patch-1' into dev 2021-01-24 02:30:22 +07:00
XMRig
86dae9e149 Merge branch 'patch-1' of https://github.com/alvv-z/xmrig into alvv-z-patch-1 2021-01-24 02:30:05 +07:00
xmrig
05b2260393 Merge pull request #2057 from xmrig/feature-msr2
Improved MSR subsystem code quality
2021-01-24 02:28:54 +07:00
XMRig
672f6df6c1 Fixed Cache QoS restore on exit where it not supported. 2021-01-24 02:23:27 +07:00
XMRig
9dae559b73 Added RxMsr class. 2021-01-23 23:23:39 +07:00
XMRig
b9d813c403 Move Ryzen related fixes to RxFix class. 2021-01-23 00:27:56 +07:00
XMRig
c48e2e6af8 Added new class Msr. 2021-01-22 23:50:25 +07:00
xmrig
76fba819fe Merge pull request #2055 from GoDzM4TT3O/patch-1
Add missing "cstdio" library
2021-01-22 22:19:41 +07:00
GoDzM4TT3O
6bab624885 Add missing "cstdio" library
Compilation fails if the above library is missing. This fixes a compilation error.
2021-01-22 14:18:28 +01:00
XMRig
3730bcd434 Merge branch 'master' into feature-msr2 2021-01-22 16:55:57 +07:00
XMRig
3b7d30a91d v6.8.0-dev 2021-01-22 00:27:38 +07:00
XMRig
c8588903e3 Enable DMI reader by default. 2021-01-22 00:12:34 +07:00
xmrig
0b4fec15dd Merge pull request #2052 from xmrig/feature-dmi
Added DMI/SMBIOS reader
2021-01-22 00:09:10 +07:00
XMRig
ef8cc28f3f Added DMI data to online benchmark. 2021-01-21 23:22:01 +07:00
XMRig
8471f7fad3 Added "GET /2/dmi" API endpoint. 2021-01-20 22:54:02 +07:00
alvv-z
b99dc440af Spelling Check
agaiin -> again
2021-01-20 12:36:47 +01:00
XMRig
9a02007900 Added config option "dmi" and command line option "--no-dmi". 2021-01-20 16:02:48 +07:00
XMRig
efc5e5d811 Fix summary. 2021-01-20 00:45:36 +07:00
XMRig
dea5be0a57 Added basic system reader. 2021-01-20 00:43:01 +07:00
XMRig
24c290963a Added DMI reader for macOS. 2021-01-19 14:16:03 +07:00
XMRig
9dffcdaddd Enable FreeBSD support. 2021-01-19 01:45:17 +07:00
XMRig
3df47052ed Added legacy DMI readers for Linux. 2021-01-19 01:23:09 +07:00
XMRig
3b8d081c8c Add support for older DMI formats on Linux. 2021-01-18 22:56:57 +07:00
XMRig
05e6f66169 Added basic Linux support. 2021-01-18 16:53:42 +07:00
XMRig
11e0d3de3a Added DMI reader (Windows only). 2021-01-18 11:23:29 +07:00
XMRig
ea367da064 #2043 Fix compile warning. 2021-01-17 17:48:35 +07:00
xmrig
a999a56775 Merge pull request #2041 from coldiron/typo-fixes
fixed grammar in a couple of awkward error messages
2021-01-16 10:15:29 +07:00
Richard Mitsuk Lavitt
590252bd5e fixed grammar in a couple of awkward error messages 2021-01-15 14:33:38 -06:00
XMRig
cc2de4f768 v6.7.3-dev 2021-01-15 20:11:28 +07:00
XMRig
aeea0e0a6c Merge branch 'master' into dev 2021-01-15 20:09:26 +07:00
XMRig
82d698a1e5 v6.7.2 2021-01-15 19:31:41 +07:00
XMRig
95b2b5e028 Merge branch 'dev' 2021-01-15 19:31:09 +07:00
xmrig
eae84d47e7 Update CHANGELOG.md 2021-01-15 19:30:22 +07:00
XMRig
45d12314f4 Sync changes. 2021-01-15 19:18:52 +07:00
xmrig
fa11cb623d Merge pull request #2039 from SChernykh/dev
Fixed solo mining
2021-01-15 18:49:04 +07:00
SChernykh
7da04c6a2c Always use cvt_bin2hex 2021-01-15 12:46:27 +01:00
SChernykh
5c449913af Fixed solo mining
It was broken since 6.7.0
2021-01-15 11:18:36 +01:00
XMRig
af019fed8e v6.7.2-dev 2021-01-11 18:29:56 +07:00
XMRig
8872630c46 Merge branch 'master' into dev 2021-01-11 18:29:06 +07:00
XMRig
d3ec21cbf5 v6.7.1 2021-01-11 16:13:29 +07:00
XMRig
395dd4086b Merge branch 'dev' 2021-01-11 16:12:14 +07:00
XMRig
a7f9808621 Fixed HOSTNAME environment variable. 2021-01-11 11:42:32 +07:00
xmrig
88862b617f Update CHANGELOG.md 2021-01-10 07:53:44 +07:00
xmrig
39bfa0c420 Merge pull request #2028 from SChernykh/dev
RandomX x86 JIT: remove redundant CFROUND
2021-01-08 04:58:25 +07:00
SChernykh
f62f4e6108 RandomX x86 JIT: remove redundant CFROUND 2021-01-07 16:20:00 +01:00
xmrig
9f128d1182 Merge pull request #2009 from SChernykh/dev
AstroBWT OpenCL fixes
2020-12-27 22:56:58 +07:00
SChernykh
2f2b33c82b AstroBWT OpenCL fixes
- Rewrote main BWT kernel to work properly on Navi
- Fixed nonce iterations in OclWorker
- Fixed memory allocation for AstroBWT
2020-12-27 16:44:35 +01:00
xmrig
56280cb1d5 Merge pull request #2007 from Frago9876543210/dev
Added scripts/{build, deps} into .gitignore
2020-12-26 00:13:19 +07:00
Frago9876543210
07127c6e87 Added scripts/{build, deps} into .gitignore 2020-12-25 20:05:18 +03:00
xmrig
3dabc77a09 Merge pull request #1998 from SChernykh/dev
Show hashrate in the benchmark finished message
2020-12-23 21:04:11 +07:00
SChernykh
66349e3d23 Show hashrate in the benchmark finished message 2020-12-23 14:31:38 +01:00
XMRig
85a78ce537 #1995 Fixed log initialization. 2020-12-22 21:41:39 +07:00
XMRig
0d9f17670e v6.7.1-dev 2020-12-21 20:59:00 +07:00
XMRig
deb561a410 Merge branch 'master' into dev 2020-12-21 20:57:49 +07:00
XMRig
9d256a1e9b v6.7.0 2020-12-21 17:55:17 +07:00
XMRig
3c985eef25 Merge branch 'dev' 2020-12-21 17:54:18 +07:00
xmrig
6224887967 Update CHANGELOG.md 2020-12-21 17:26:29 +07:00
xmrig
09361bf3a5 Update CHANGELOG.md 2020-12-21 11:30:12 +07:00
xmrig
8a1311f015 Merge pull request #1989 from SChernykh/dev
Fixed broken Dero solo mining
2020-12-21 09:01:10 +07:00
SChernykh
cde7cddcaa Fixed broken Dero solo mining 2020-12-20 22:17:08 +01:00
xmrig
aa53ba073d Merge pull request #1987 from SChernykh/dev
Another dataset AVX2 init speedup (+3.8% faster on Zen3)
2020-12-20 01:57:12 +07:00
SChernykh
ac46d6f8de Fix GCC warning 2020-12-19 19:50:52 +01:00
SChernykh
5efd00abec Another dataset AVX2 init speedup (+3.8% faster on Zen3) 2020-12-19 19:46:31 +01:00
xmrig
e79e3370f8 Merge pull request #1986 from SChernykh/dev
Dataset initialization with AVX2 (faster startup)
2020-12-20 00:16:20 +07:00
SChernykh
633aaccd9c Added config option for AVX2 dataset init
-1 = Auto detect
0 = Always disabled
1 = Enabled if AVX2 is supported
2020-12-19 16:18:49 +01:00
SChernykh
410313d933 Auto-detect the fastest code for dataset init 2020-12-19 13:59:28 +01:00
SChernykh
7aba194d3b Fixed Windows scripts
Change back to script's folder when started as administrator
2020-12-18 16:51:28 +01:00
SChernykh
515a85e66c Dataset initialization with AVX2 (WIP) 2020-12-18 14:53:54 +01:00
XMRig
6b21a51a2f Huge pages not supported by macOS ARM. 2020-12-16 01:59:20 +07:00
XMRig
a934ba3079 Fixed Xcode generator. 2020-12-15 22:47:22 +07:00
XMRig
633a92bff0 Merge branch 'gcc11' of https://github.com/voidanix/xmrig into dev 2020-12-15 17:32:24 +07:00
XMRig
5a846ebd58 Merge branch '64bit-is-not-x64' of https://github.com/rivoreo/xmrig into dev 2020-12-15 17:28:36 +07:00
voidanix
e4c2ccba9d Fix build on GCC 11 2020-12-15 09:39:26 +01:00
WHR
15168950e5 Don't use team 'x64' for '64-bit' 2020-12-15 14:56:06 +08:00
XMRig
6b331b6945 Reduce JIT memory for ARM. 2020-12-15 02:52:38 +07:00
xmrig
4c7d20c8e6 Merge pull request #1977 from SChernykh/dev
Fix: secure JIT and huge pages are incompatible on Windows
2020-12-15 00:41:55 +07:00
SChernykh
414588d701 Fix alignment for Linux 2020-12-14 18:32:25 +01:00
SChernykh
f89f6a8abf Fix: secure JIT and huge pages are incompatible on Windows 2020-12-14 18:22:58 +01:00
XMRig
ca3695a754 Update hwloc for MSVC to 2.4.0. 2020-12-14 02:55:50 +07:00
XMRig
7c682ec91a Update build scripts. 2020-12-13 22:56:00 +07:00
XMRig
cc5c2c41be Hardcode L2 cache size for Apple M1. 2020-12-13 20:09:29 +07:00
XMRig
643142dc30 Update user agent for macOS and fix compile warnings 2020-12-13 13:57:12 +07:00
XMRig
a36fb7e728 More correct CPU affinity support for macOS. 2020-12-13 01:20:31 +07:00
XMRig
87fafcf91b Fixed JIT on macOS. 2020-12-12 22:40:48 +07:00
XMRig
2966b80ba1 Fixed macOS build. 2020-12-12 22:15:15 +07:00
XMRig
179f09081f Alternative secure JIT for macOS. 2020-12-12 21:32:36 +07:00
XMRig
775867fc3e Fixed secure JIT on Linux and code cleanup. 2020-12-12 19:18:47 +07:00
XMRig
497863441a Remove duplicated code. 2020-12-12 12:39:11 +07:00
XMRig
ec62ded279 Added generic secure JIT support for RandomX. 2020-12-11 23:17:54 +07:00
xmrig
f9c0933f05 Merge pull request #1970 from SChernykh/dev
More static analysis fixes
2020-12-08 22:34:55 +07:00
SChernykh
0da3390d09 More static analysis fixes 2020-12-08 16:05:58 +01:00
xmrig
9a025fdb75 Merge pull request #1969 from SChernykh/dev
Fixed errors found by static analysis
2020-12-08 18:24:41 +07:00
SChernykh
cafd868773 Fixed errors found by static analysis 2020-12-08 12:16:59 +01:00
xmrig
1c9e959cc4 Merge pull request #1968 from SChernykh/dev
Added virtual machine detection
2020-12-06 23:45:53 +07:00
SChernykh
41a9bddd59 Added virtual machine detection 2020-12-06 17:34:01 +01:00
xmrig
7a09f5fe47 Merge pull request #1966 from xmrig/remove-libcpuid
Removed libcpuid support
2020-12-06 21:59:12 +07:00
XMRig
ab45794b7c Removed libcpuid support. 2020-12-06 21:51:24 +07:00
xmrig
1d5592f303 Merge pull request #1964 from xmrig/update-base
Cleanup and refactoring
2020-12-06 00:13:05 +07:00
XMRig
2bf8887cab v6.7.0-dev 2020-12-06 00:08:34 +07:00
XMRig
acf7ec8355 Restore Hashrate class interface. 2020-12-05 11:09:25 +07:00
XMRig
bd82b3c852 Added GpuWorker class. 2020-12-04 22:25:28 +07:00
XMRig
daf08fcf9a Cleanup 2020-12-04 19:52:53 +07:00
XMRig
c8ee6f7db8 Move Profiler and more cleanup. 2020-12-04 09:23:40 +07:00
XMRig
662a957106 Fixed Linux build. 2020-12-03 19:55:49 +07:00
XMRig
3055e03b7e Cleanup 2020-12-03 19:45:16 +07:00
XMRig
11da7a3155 Update Json. 2020-12-03 15:39:33 +07:00
XMRig
0a27c6d6af Update Signals and Console. 2020-12-03 12:06:18 +07:00
XMRig
86795aa5b7 Update HTTP 2020-12-03 10:48:57 +07:00
XMRig
63bd45c397 Added Cvt class. 2020-12-02 16:31:45 +07:00
XMRig
469b1f08de Update net 2020-12-02 11:32:11 +07:00
XMRig
121c515a07 Update log. 2020-12-01 23:28:07 +07:00
XMRig
2715bc20d9 v6.6.3-dev 2020-12-01 21:28:31 +07:00
XMRig
c156cdfe7a Merge branch 'master' into dev 2020-12-01 21:27:56 +07:00
XMRig
a9965c5580 v6.6.2 2020-12-01 20:51:37 +07:00
XMRig
dca6d3f1ff Merge branch 'dev' 2020-12-01 20:49:59 +07:00
xmrig
91979dc4dd Update CHANGELOG.md 2020-12-01 20:12:27 +07:00
xmrig
87195ed237 Merge pull request #1960 from SChernykh/dev
Fix RandomX init when switching to other algo and back
2020-11-30 09:20:14 +07:00
SChernykh
d557fe7f39 Fix RandomX init when switching to other algo and back 2020-11-29 22:02:48 +01:00
xmrig
13ee9d09a8 Merge pull request #1959 from SChernykh/dev
Optimized JIT compiler
2020-11-29 20:08:40 +07:00
SChernykh
f16d1837f8 Optimized JIT compiler
More branch-free code
2020-11-29 14:05:50 +01:00
XMRig
096b09bf4d Update base 2020-11-29 18:45:52 +07:00
xmrig
bbcf8e2be3 Merge pull request #1958 from SChernykh/dev
Example mining scripts to help new miners
2020-11-27 14:51:53 +07:00
SChernykh
fb9d2b9e7c Example mining scripts to help new miners 2020-11-26 19:06:46 +01:00
XMRig
58711aa666 v6.6.2-dev 2020-11-25 21:12:45 +07:00
XMRig
c7236d2cf0 Merge branch 'master' into dev 2020-11-25 21:06:58 +07:00
XMRig
25da0cba57 v6.6.1 2020-11-25 17:46:39 +07:00
XMRig
fb721edc20 Merge branch 'dev' 2020-11-25 17:46:00 +07:00
xmrig
d2a4fa367a Update CHANGELOG.md 2020-11-25 16:44:06 +07:00
XMRig
8686e08336 Fixed, benchmark validation on NUMA hardware produced incorrect results in some conditions. 2020-11-25 09:35:11 +07:00
XMRig
09b68f3cdb Added BenchStatePrivate class. 2020-11-24 17:59:40 +07:00
XMRig
05a2054057 v6.6.1-dev 2020-11-24 10:58:12 +07:00
XMRig
4e59f90495 Merge branch 'master' into dev 2020-11-24 10:57:35 +07:00
739 changed files with 135725 additions and 30886 deletions

2
.gitignore vendored
View File

@@ -1,4 +1,6 @@
/build
scripts/build
scripts/deps
/CMakeLists.txt.user
/.idea
/src/backend/opencl/cl/cn/cryptonight_gen.cl

View File

@@ -1,3 +1,248 @@
# v6.19.3
- [#3245](https://github.com/xmrig/xmrig/issues/3245) Improved algorithm negotiation for donation rounds by sending extra information about current mining job.
- [#3254](https://github.com/xmrig/xmrig/pull/3254) Tweaked auto-tuning for Intel CPUs.
- [#3271](https://github.com/xmrig/xmrig/pull/3271) RandomX: optimized program generation.
- [#3273](https://github.com/xmrig/xmrig/pull/3273) RandomX: fixed undefined behavior.
- [#3275](https://github.com/xmrig/xmrig/pull/3275) RandomX: fixed `jccErratum` list.
- [#3280](https://github.com/xmrig/xmrig/pull/3280) Updated example scripts.
# v6.19.2
- [#3230](https://github.com/xmrig/xmrig/pull/3230) Fixed parsing of `TX_EXTRA_MERGE_MINING_TAG`.
- [#3232](https://github.com/xmrig/xmrig/pull/3232) Added new `X-Hash-Difficulty` HTTP header.
- [#3240](https://github.com/xmrig/xmrig/pull/3240) Improved .cmd files when run by shortcuts on another drive.
- [#3241](https://github.com/xmrig/xmrig/pull/3241) Added view tag calculation (fixes Wownero solo mining issue).
# v6.19.1
- Resolved deprecated methods warnings with OpenSSL 3.0.
- [#3213](https://github.com/xmrig/xmrig/pull/3213) Fixed build with 32-bit clang 15.
- [#3218](https://github.com/xmrig/xmrig/pull/3218) Fixed: `--randomx-wrmsr=-1` worked only on Intel.
- [#3228](https://github.com/xmrig/xmrig/pull/3228) Fixed build with gcc 13.
# v6.19.0
- [#3144](https://github.com/xmrig/xmrig/pull/3144) Update to latest `sse2neon.h`.
- [#3161](https://github.com/xmrig/xmrig/pull/3161) MSVC build: enabled parallel compilation.
- [#3163](https://github.com/xmrig/xmrig/pull/3163) Improved Zen 3 MSR mod.
- [#3176](https://github.com/xmrig/xmrig/pull/3176) Update cmake required version to 3.1.
- [#3182](https://github.com/xmrig/xmrig/pull/3182) DragonflyBSD compilation fixes.
- [#3196](https://github.com/xmrig/xmrig/pull/3196) Show IP address for failed connections.
- [#3185](https://github.com/xmrig/xmrig/issues/3185) Fixed macOS DMI reader.
- [#3198](https://github.com/xmrig/xmrig/pull/3198) Fixed broken RandomX light mode mining.
- [#3202](https://github.com/xmrig/xmrig/pull/3202) Solo mining: added job timeout (default is 15 seconds).
# v6.18.1
- [#3129](https://github.com/xmrig/xmrig/pull/3129) Fix: protectRX flushed CPU cache only on MacOS/iOS.
- [#3126](https://github.com/xmrig/xmrig/pull/3126) Don't reset when pool sends the same job blob.
- [#3120](https://github.com/xmrig/xmrig/pull/3120) RandomX: optimized `CFROUND` elimination.
- [#3109](https://github.com/xmrig/xmrig/pull/3109) RandomX: added Blake2 AVX2 version.
- [#3082](https://github.com/xmrig/xmrig/pull/3082) Fixed GCC 12 warnings.
- [#3075](https://github.com/xmrig/xmrig/pull/3075) Recognize `armv7ve` as valid ARMv7 target.
- [#3132](https://github.com/xmrig/xmrig/pull/3132) RandomX: added MSR mod for Zen 4.
- [#3134](https://github.com/xmrig/xmrig/pull/3134) Added Zen4 to `randomx_boost.sh`.
# v6.18.0
- [#3067](https://github.com/xmrig/xmrig/pull/3067) Monero v15 network upgrade support and more house keeping.
- Removed deprecated AstroBWTv1 and v2.
- Fixed debug GhostRider build.
- Monero v15 network upgrade support.
- Fixed ZMQ debug log.
- Improved daemon ZMQ mining stability.
- [#3054](https://github.com/xmrig/xmrig/pull/3054) Fixes for 32-bit ARM.
- [#3042](https://github.com/xmrig/xmrig/pull/3042) Fixed being unable to resume from `pause-on-battery`.
- [#3031](https://github.com/xmrig/xmrig/pull/3031) Fixed `--cpu-priority` not working sometimes.
- [#3020](https://github.com/xmrig/xmrig/pull/3020) Removed old AstroBWT algorithm.
# v6.17.0
- [#2954](https://github.com/xmrig/xmrig/pull/2954) **Dero HE fork support (`astrobwt/v2` algorithm).**
- [#2961](https://github.com/xmrig/xmrig/pull/2961) Dero HE (`astrobwt/v2`) CUDA config generator.
- [#2969](https://github.com/xmrig/xmrig/pull/2969) Dero HE (`astrobwt/v2`) OpenCL support.
- Fixed displayed DMI memory information for empty slots.
- [#2932](https://github.com/xmrig/xmrig/pull/2932) Fixed GhostRider with hwloc disabled.
# v6.16.4
- [#2904](https://github.com/xmrig/xmrig/pull/2904) Fixed unaligned memory accesses.
- [#2908](https://github.com/xmrig/xmrig/pull/2908) Added MSVC/2022 to `version.h`.
- [#2910](https://github.com/xmrig/xmrig/issues/2910) Fixed donation for GhostRider/RTM.
# v6.16.3
- [#2778](https://github.com/xmrig/xmrig/pull/2778) Fixed `READY threads X/X` display after algorithm switching.
- [#2782](https://github.com/xmrig/xmrig/pull/2782) Updated GhostRider documentation.
- [#2815](https://github.com/xmrig/xmrig/pull/2815) Fixed `cn-heavy` in 32-bit builds.
- [#2827](https://github.com/xmrig/xmrig/pull/2827) GhostRider: set correct priority for helper threads.
- [#2837](https://github.com/xmrig/xmrig/pull/2837) RandomX: don't restart mining threads when the seed changes.
- [#2848](https://github.com/xmrig/xmrig/pull/2848) GhostRider: added support for `client.reconnect` method.
- [#2856](https://github.com/xmrig/xmrig/pull/2856) Fix for short responses from some Raptoreum pools.
- [#2873](https://github.com/xmrig/xmrig/pull/2873) Fixed GhostRider benchmark on single-core systems.
- [#2882](https://github.com/xmrig/xmrig/pull/2882) Fixed ARMv7 compilation.
- [#2893](https://github.com/xmrig/xmrig/pull/2893) KawPow OpenCL: use separate UV loop for building programs.
# v6.16.2
- [#2751](https://github.com/xmrig/xmrig/pull/2751) Fixed crash on CPUs supporting VAES and running GCC-compiled xmrig.
- [#2761](https://github.com/xmrig/xmrig/pull/2761) Fixed broken auto-tuning in GCC Windows build.
- [#2771](https://github.com/xmrig/xmrig/issues/2771) Fixed environment variables support for GhostRider and KawPow.
- [#2769](https://github.com/xmrig/xmrig/pull/2769) Performance fixes:
- Fixed several performance bottlenecks introduced in v6.16.1.
- Fixed overall GCC-compiled build performance, it's the same speed as MSVC build now.
- **Linux builds are up to 10% faster now compared to v6.16.0 GCC build.**
- **Windows builds are up to 5% faster now compared to v6.16.0 MSVC build.**
# v6.16.1
- [#2729](https://github.com/xmrig/xmrig/pull/2729) GhostRider fixes:
- Added average hashrate display.
- Fixed the number of threads shown at startup.
- Fixed `--threads` or `-t` command line option (but `--cpu-max-threads-hint` is recommended to use).
- [#2738](https://github.com/xmrig/xmrig/pull/2738) GhostRider fixes:
- Fixed "difficulty is not a number" error when diff is high on some pools.
- Fixed GhostRider compilation when `WITH_KAWPOW=OFF`.
- [#2740](https://github.com/xmrig/xmrig/pull/2740) Added VAES support for Cryptonight variants **+4% speedup on Zen3**.
- VAES instructions are available on Intel Ice Lake/AMD Zen3 and newer CPUs.
- +4% speedup on Ryzen 5 5600X.
# v6.16.0
- [#2712](https://github.com/xmrig/xmrig/pull/2712) **GhostRider algorithm (Raptoreum) support**: read the [RELEASE NOTES](src/crypto/ghostrider/README.md) for quick start guide and performance comparisons.
- [#2682](https://github.com/xmrig/xmrig/pull/2682) Fixed: use cn-heavy optimization only for Vermeer CPUs.
- [#2684](https://github.com/xmrig/xmrig/pull/2684) MSR mod: fix for error 183.
# v6.15.3
- [#2614](https://github.com/xmrig/xmrig/pull/2614) OpenCL fixes for non-AMD platforms.
- [#2623](https://github.com/xmrig/xmrig/pull/2623) Fixed compiling without kawpow.
- [#2636](https://github.com/xmrig/xmrig/pull/2636) [#2639](https://github.com/xmrig/xmrig/pull/2639) AstroBWT speedup (up to +35%).
- [#2646](https://github.com/xmrig/xmrig/pull/2646) Fixed MSVC compilation error.
# v6.15.2
- [#2606](https://github.com/xmrig/xmrig/pull/2606) Fixed: AstroBWT auto-config ignored `max-threads-hint`.
- Fixed possible crash on Windows (regression in v6.15.1).
# v6.15.1
- [#2586](https://github.com/xmrig/xmrig/pull/2586) Fixed Windows 7 compatibility.
- [#2594](https://github.com/xmrig/xmrig/pull/2594) Added Windows taskbar icon colors.
# v6.15.0
- [#2548](https://github.com/xmrig/xmrig/pull/2548) Added automatic coin detection for daemon mining.
- [#2563](https://github.com/xmrig/xmrig/pull/2563) Added new algorithm RandomX Graft (`rx/graft`).
- [#2565](https://github.com/xmrig/xmrig/pull/2565) AstroBWT: added AVX2 Salsa20 implementation.
- Added support for new CUDA plugin API (previous API still supported).
# v6.14.1
- [#2532](https://github.com/xmrig/xmrig/pull/2532) Refactoring: stable (persistent) algorithms IDs.
- [#2537](https://github.com/xmrig/xmrig/pull/2537) Fixed Termux build.
# v6.14.0
- [#2484](https://github.com/xmrig/xmrig/pull/2484) Added ZeroMQ support for solo mining.
- [#2476](https://github.com/xmrig/xmrig/issues/2476) Fixed crash in DMI memory reader.
- [#2492](https://github.com/xmrig/xmrig/issues/2492) Added missing `--huge-pages-jit` command line option.
- [#2512](https://github.com/xmrig/xmrig/pull/2512) Added show the number of transactions in pool job.
# v6.13.1
- [#2468](https://github.com/xmrig/xmrig/pull/2468) Fixed regression in previous version: don't send miner signature during regular mining.
# v6.13.0
- [#2445](https://github.com/xmrig/xmrig/pull/2445) Added support for solo mining with miner signatures for the upcoming Wownero fork.
# v6.12.2
- [#2280](https://github.com/xmrig/xmrig/issues/2280) GPU backends are now disabled in benchmark mode.
- [#2322](https://github.com/xmrig/xmrig/pull/2322) Improved MSR compatibility with recent Linux kernels and updated `randomx_boost.sh`.
- [#2340](https://github.com/xmrig/xmrig/pull/2340) Fixed AES detection on FreeBSD on ARM.
- [#2341](https://github.com/xmrig/xmrig/pull/2341) `sse2neon` updated to the latest version.
- [#2351](https://github.com/xmrig/xmrig/issues/2351) Fixed help output for `--cpu-priority` and `--cpu-affinity` option.
- [#2375](https://github.com/xmrig/xmrig/pull/2375) Fixed macOS CUDA backend default loader name.
- [#2378](https://github.com/xmrig/xmrig/pull/2378) Fixed broken light mode mining on x86.
- [#2379](https://github.com/xmrig/xmrig/pull/2379) Fixed CL code for KawPow where it assumes everything is AMD.
- [#2386](https://github.com/xmrig/xmrig/pull/2386) RandomX: enabled `IMUL_RCP` optimization for light mode mining.
- [#2393](https://github.com/xmrig/xmrig/pull/2393) RandomX: added BMI2 version for scratchpad prefetch.
- [#2395](https://github.com/xmrig/xmrig/pull/2395) RandomX: rewrote dataset read code.
- [#2398](https://github.com/xmrig/xmrig/pull/2398) RandomX: optimized ARMv8 dataset read.
- Added `argon2/ninja` alias for `argon2/wrkz` algorithm.
# v6.12.1
- [#2296](https://github.com/xmrig/xmrig/pull/2296) Fixed Zen3 assembly code for `cn/upx2` algorithm.
# v6.12.0
- [#2276](https://github.com/xmrig/xmrig/pull/2276) Added support for Uplexa (`cn/upx2` algorithm).
- [#2261](https://github.com/xmrig/xmrig/pull/2261) Show total hashrate if compiled without OpenCL.
- [#2289](https://github.com/xmrig/xmrig/pull/2289) RandomX: optimized `IMUL_RCP` instruction.
- Added support for `--user` command line option for online benchmark.
# v6.11.2
- [#2207](https://github.com/xmrig/xmrig/issues/2207) Fixed regression in HTTP parser and llhttp updated to v5.1.0.
# v6.11.1
- [#2239](https://github.com/xmrig/xmrig/pull/2239) Fixed broken `coin` setting functionality.
# v6.11.0
- [#2196](https://github.com/xmrig/xmrig/pull/2196) Improved DNS subsystem and added new DNS specific options.
- [#2172](https://github.com/xmrig/xmrig/pull/2172) Fixed build on Alpine 3.13.
- [#2177](https://github.com/xmrig/xmrig/pull/2177) Fixed ARM specific compilation error with GCC 10.2.
- [#2214](https://github.com/xmrig/xmrig/pull/2214) [#2216](https://github.com/xmrig/xmrig/pull/2216) [#2235](https://github.com/xmrig/xmrig/pull/2235) Optimized `cn-heavy` algorithm.
- [#2217](https://github.com/xmrig/xmrig/pull/2217) Fixed mining job creation sequence.
- [#2225](https://github.com/xmrig/xmrig/pull/2225) Fixed build without OpenCL support on some systems.
- [#2229](https://github.com/xmrig/xmrig/pull/2229) Don't use RandomX JIT if `WITH_ASM=OFF`.
- [#2228](https://github.com/xmrig/xmrig/pull/2228) Removed useless code for cryptonight algorithms.
- [#2234](https://github.com/xmrig/xmrig/pull/2234) Fixed build error on gcc 4.8.
# v6.10.0
- [#2122](https://github.com/xmrig/xmrig/pull/2122) Fixed pause logic when both pause on battery and user activity are enabled.
- [#2123](https://github.com/xmrig/xmrig/issues/2123) Fixed compatibility with gcc 4.8.
- [#2147](https://github.com/xmrig/xmrig/pull/2147) Fixed many `new job` messages when solo mining.
- [#2150](https://github.com/xmrig/xmrig/pull/2150) Updated `sse2neon.h` to the latest master, fixes build on ARMv7.
- [#2157](https://github.com/xmrig/xmrig/pull/2157) Fixed crash in `cn-heavy` on Zen3 with manual thread count.
- Fixed possible out of order write to log file.
- [http-parser](https://github.com/nodejs/http-parser) replaced to [llhttp](https://github.com/nodejs/llhttp).
- For official builds: libuv, hwloc and OpenSSL updated to latest versions.
# v6.9.0
- [#2104](https://github.com/xmrig/xmrig/pull/2104) Added [pause-on-active](https://xmrig.com/docs/miner/config/misc#pause-on-active) config option and `--pause-on-active=N` command line option.
- [#2112](https://github.com/xmrig/xmrig/pull/2112) Added support for [Tari merge mining](https://github.com/tari-project/tari/blob/development/README.md#tari-merge-mining).
- [#2117](https://github.com/xmrig/xmrig/pull/2117) Fixed crash when GPU mining `cn-heavy` on Zen3 system.
# v6.8.2
- [#2080](https://github.com/xmrig/xmrig/pull/2080) Fixed compile error in Termux.
- [#2089](https://github.com/xmrig/xmrig/pull/2089) Optimized CryptoNight-Heavy for Zen3, 7-8% speedup.
# v6.8.1
- [#2064](https://github.com/xmrig/xmrig/pull/2064) Added documentation for config.json CPU options.
- [#2066](https://github.com/xmrig/xmrig/issues/2066) Fixed AMD GPUs health data readings on Linux.
- [#2067](https://github.com/xmrig/xmrig/pull/2067) Fixed compilation error when RandomX and Argon2 are disabled.
- [#2076](https://github.com/xmrig/xmrig/pull/2076) Added support for flexible huge page sizes on Linux.
- [#2077](https://github.com/xmrig/xmrig/pull/2077) Fixed `illegal instruction` crash on ARM.
# v6.8.0
- [#2052](https://github.com/xmrig/xmrig/pull/2052) Added DMI/SMBIOS reader.
- Added information about memory modules on the miner startup and for online benchmark.
- Added new HTTP API endpoint: `GET /2/dmi`.
- Added new command line option `--no-dmi` or config option `"dmi"`.
- Added new CMake option `-DWITH_DMI=OFF`.
- [#2057](https://github.com/xmrig/xmrig/pull/2057) Improved MSR subsystem code quality.
- [#2058](https://github.com/xmrig/xmrig/pull/2058) RandomX JIT x86: removed unnecessary instructions.
# v6.7.2
- [#2039](https://github.com/xmrig/xmrig/pull/2039) Fixed solo mining.
# v6.7.1
- [#1995](https://github.com/xmrig/xmrig/issues/1995) Fixed log initialization.
- [#1998](https://github.com/xmrig/xmrig/pull/1998) Added hashrate in the benchmark finished message.
- [#2009](https://github.com/xmrig/xmrig/pull/2009) AstroBWT OpenCL fixes.
- [#2028](https://github.com/xmrig/xmrig/pull/2028) RandomX x86 JIT: removed redundant `CFROUND`.
# v6.7.0
- **[#1991](https://github.com/xmrig/xmrig/issues/1991) Added Apple M1 processor support.**
- **[#1986](https://github.com/xmrig/xmrig/pull/1986) Up to 20-30% faster RandomX dataset initialization with AVX2 on some CPUs.**
- [#1964](https://github.com/xmrig/xmrig/pull/1964) Cleanup and refactoring.
- [#1966](https://github.com/xmrig/xmrig/pull/1966) Removed libcpuid support.
- [#1968](https://github.com/xmrig/xmrig/pull/1968) Added virtual machine detection.
- [#1969](https://github.com/xmrig/xmrig/pull/1969) [#1970](https://github.com/xmrig/xmrig/pull/1970) Fixed errors found by static analysis.
- [#1977](https://github.com/xmrig/xmrig/pull/1977) Fixed: secure JIT and huge pages are incompatible on Windows.
- [#1979](https://github.com/xmrig/xmrig/pull/1979) Term `x64` replaced to `64-bit`.
- [#1980](https://github.com/xmrig/xmrig/pull/1980) Fixed build on gcc 11.
- [#1989](https://github.com/xmrig/xmrig/pull/1989) Fixed broken Dero solo mining.
# v6.6.2
- [#1958](https://github.com/xmrig/xmrig/pull/1958) Added example mining scripts to help new miners.
- [#1959](https://github.com/xmrig/xmrig/pull/1959) Optimized JIT compiler.
- [#1960](https://github.com/xmrig/xmrig/pull/1960) Fixed RandomX init when switching to other algo and back.
# v6.6.1
- Fixed, benchmark validation on NUMA hardware produced incorrect results in some conditions.
# v6.6.0
- Online benchmark protocol upgraded to v2, validation not compatible with previous versions.
- Single thread benchmark now is cheat-resistant, not possible speedup it with multiple threads.

View File

@@ -1,15 +1,15 @@
cmake_minimum_required(VERSION 2.8)
cmake_minimum_required(VERSION 3.1)
project(xmrig)
option(WITH_LIBCPUID "Enable libcpuid support" ON)
option(WITH_HWLOC "Enable hwloc support" ON)
option(WITH_CN_LITE "Enable CryptoNight-Lite algorithms family" ON)
option(WITH_CN_HEAVY "Enable CryptoNight-Heavy algorithms family" ON)
option(WITH_CN_PICO "Enable CryptoNight-Pico algorithm" ON)
option(WITH_CN_FEMTO "Enable CryptoNight-UPX2 algorithm" ON)
option(WITH_RANDOMX "Enable RandomX algorithms family" ON)
option(WITH_ARGON2 "Enable Argon2 algorithms family" ON)
option(WITH_ASTROBWT "Enable AstroBWT algorithms family" ON)
option(WITH_KAWPOW "Enable KawPow algorithms family" ON)
option(WITH_GHOSTRIDER "Enable GhostRider algorithm" ON)
option(WITH_HTTP "Enable HTTP protocol support (client/server)" ON)
option(WITH_DEBUG_LOG "Enable debug log output" OFF)
option(WITH_TLS "Enable OpenSSL support" ON)
@@ -18,6 +18,8 @@ option(WITH_MSR "Enable MSR mod & 1st-gen Ryzen fix" ON)
option(WITH_ENV_VARS "Enable environment variables support in config file" ON)
option(WITH_EMBEDDED_CONFIG "Enable internal embedded JSON config" OFF)
option(WITH_OPENCL "Enable OpenCL backend" ON)
set(WITH_OPENCL_VERSION 200 CACHE STRING "Target OpenCL version")
set_property(CACHE WITH_OPENCL_VERSION PROPERTY STRINGS 120 200 210 220)
option(WITH_CUDA "Enable CUDA backend" ON)
option(WITH_NVML "Enable NVML (NVIDIA Management Library) support (only if CUDA backend enabled)" ON)
option(WITH_ADL "Enable ADL (AMD Display Library) or sysfs support (only if OpenCL backend enabled)" ON)
@@ -25,10 +27,16 @@ option(WITH_STRICT_CACHE "Enable strict checks for OpenCL cache" ON)
option(WITH_INTERLEAVE_DEBUG_LOG "Enable debug log for threads interleave" OFF)
option(WITH_PROFILING "Enable profiling for developers" OFF)
option(WITH_SSE4_1 "Enable SSE 4.1 for Blake2" ON)
option(WITH_AVX2 "Enable AVX2 for Blake2" ON)
option(WITH_VAES "Enable VAES instructions for Cryptonight" ON)
option(WITH_BENCHMARK "Enable builtin RandomX benchmark and stress test" ON)
option(WITH_SECURE_JIT "Enable secure access to JIT memory" OFF)
option(WITH_DMI "Enable DMI/SMBIOS reader" ON)
option(WITH_BUNDLED_FMT "Force use of bundled fmt library" ON)
option(BUILD_STATIC "Build static binary" OFF)
option(ARM_TARGET "Force use specific ARM target 8 or 7" 0)
option(ARM_V8 "Force ARMv8 (64 bit) architecture, use with caution if automatic detection fails, but you sure it may work" OFF)
option(ARM_V7 "Force ARMv7 (32 bit) architecture, use with caution if automatic detection fails, but you sure it may work" OFF)
option(HWLOC_DEBUG "Enable hwloc debug helpers and log" OFF)
@@ -54,6 +62,7 @@ set(HEADERS
src/core/config/usage.h
src/core/Controller.h
src/core/Miner.h
src/core/Taskbar.h
src/net/interfaces/IJobResultListener.h
src/net/JobResult.h
src/net/JobResults.h
@@ -102,6 +111,7 @@ set(SOURCES
src/core/config/ConfigTransform.cpp
src/core/Controller.cpp
src/core/Miner.cpp
src/core/Taskbar.cpp
src/net/JobResults.cpp
src/net/Network.cpp
src/net/strategies/DonateStrategy.cpp
@@ -122,6 +132,19 @@ set(SOURCES_CRYPTO
src/crypto/common/VirtualMemory.cpp
)
if (CMAKE_C_COMPILER_ID MATCHES GNU)
set_source_files_properties(src/crypto/cn/CnHash.cpp PROPERTIES COMPILE_FLAGS "-Ofast -fno-tree-vectorize")
endif()
if (WITH_VAES)
add_definitions(-DXMRIG_VAES)
set(HEADERS_CRYPTO "${HEADERS_CRYPTO}" src/crypto/cn/CryptoNight_x86_vaes.h)
set(SOURCES_CRYPTO "${SOURCES_CRYPTO}" src/crypto/cn/CryptoNight_x86_vaes.cpp)
if (CMAKE_C_COMPILER_ID MATCHES GNU OR CMAKE_C_COMPILER_ID MATCHES Clang)
set_source_files_properties(src/crypto/cn/CryptoNight_x86_vaes.cpp PROPERTIES COMPILE_FLAGS "-Ofast -fno-tree-vectorize -mavx2 -mvaes")
endif()
endif()
if (WITH_HWLOC)
list(APPEND HEADERS_CRYPTO
src/crypto/common/NUMAMemoryPool.h
@@ -146,8 +169,10 @@ elseif (XMRIG_OS_APPLE)
src/App_unix.cpp
src/crypto/common/VirtualMemory_unix.cpp
)
find_library(IOKIT_LIBRARY IOKit)
set(EXTRA_LIBS ${IOKIT_LIBRARY})
find_library(CORESERVICES_LIBRARY CoreServices)
set(EXTRA_LIBS ${IOKIT_LIBRARY} ${CORESERVICES_LIBRARY})
else()
list(APPEND SOURCES_OS
src/App_unix.cpp
@@ -168,16 +193,17 @@ else()
endif()
endif()
add_definitions(-DXMRIG_MINER_PROJECT)
add_definitions(-D__STDC_FORMAT_MACROS -DUNICODE)
add_definitions(-DXMRIG_MINER_PROJECT -DXMRIG_JSON_SINGLE_LINE_ARRAY)
add_definitions(-D__STDC_FORMAT_MACROS -DUNICODE -D_FILE_OFFSET_BITS=64)
find_package(UV REQUIRED)
include(cmake/flags.cmake)
include(cmake/fmt.cmake)
include(cmake/randomx.cmake)
include(cmake/argon2.cmake)
include(cmake/astrobwt.cmake)
include(cmake/kawpow.cmake)
include(cmake/ghostrider.cmake)
include(cmake/OpenSSL.cmake)
include(cmake/asm.cmake)
@@ -193,27 +219,37 @@ if (WITH_CN_PICO)
add_definitions(/DXMRIG_ALGO_CN_PICO)
endif()
if (WITH_CN_FEMTO)
add_definitions(/DXMRIG_ALGO_CN_FEMTO)
endif()
if (WITH_EMBEDDED_CONFIG)
add_definitions(/DXMRIG_FEATURE_EMBEDDED_CONFIG)
endif()
include(src/hw/api/api.cmake)
include(src/hw/dmi/dmi.cmake)
include_directories(src)
include_directories(src/3rdparty)
include_directories(src/3rdparty/CL)
include_directories(${UV_INCLUDE_DIR})
if (WITH_DEBUG_LOG)
add_definitions(/DAPP_DEBUG)
endif()
add_executable(${CMAKE_PROJECT_NAME} ${HEADERS} ${SOURCES} ${SOURCES_OS} ${SOURCES_CPUID} ${HEADERS_CRYPTO} ${SOURCES_CRYPTO} ${SOURCES_SYSLOG} ${TLS_SOURCES} ${XMRIG_ASM_SOURCES})
target_link_libraries(${CMAKE_PROJECT_NAME} ${XMRIG_ASM_LIBRARY} ${OPENSSL_LIBRARIES} ${UV_LIBRARIES} ${EXTRA_LIBS} ${CPUID_LIB} ${ARGON2_LIBRARY} ${ETHASH_LIBRARY})
add_executable(${CMAKE_PROJECT_NAME} ${HEADERS} ${SOURCES} ${SOURCES_OS} ${HEADERS_CRYPTO} ${SOURCES_CRYPTO} ${SOURCES_SYSLOG} ${TLS_SOURCES} ${XMRIG_ASM_SOURCES})
target_link_libraries(${CMAKE_PROJECT_NAME} ${XMRIG_ASM_LIBRARY} ${OPENSSL_LIBRARIES} ${UV_LIBRARIES} ${EXTRA_LIBS} ${CPUID_LIB} ${ARGON2_LIBRARY} ${ETHASH_LIBRARY} ${GHOSTRIDER_LIBRARY} ${FMT_LIBRARY})
if (WIN32)
add_custom_command(TARGET ${CMAKE_PROJECT_NAME} POST_BUILD COMMAND ${CMAKE_COMMAND} -E copy_if_different "${CMAKE_SOURCE_DIR}/bin/WinRing0/WinRing0x64.sys" $<TARGET_FILE_DIR:${CMAKE_PROJECT_NAME}>)
add_custom_command(TARGET ${CMAKE_PROJECT_NAME} POST_BUILD COMMAND ${CMAKE_COMMAND} -E copy_if_different "${CMAKE_SOURCE_DIR}/scripts/benchmark_1M.cmd" $<TARGET_FILE_DIR:${CMAKE_PROJECT_NAME}>)
add_custom_command(TARGET ${CMAKE_PROJECT_NAME} POST_BUILD COMMAND ${CMAKE_COMMAND} -E copy_if_different "${CMAKE_SOURCE_DIR}/scripts/benchmark_10M.cmd" $<TARGET_FILE_DIR:${CMAKE_PROJECT_NAME}>)
add_custom_command(TARGET ${CMAKE_PROJECT_NAME} POST_BUILD COMMAND ${CMAKE_COMMAND} -E copy_if_different "${CMAKE_SOURCE_DIR}/scripts/pool_mine_example.cmd" $<TARGET_FILE_DIR:${CMAKE_PROJECT_NAME}>)
add_custom_command(TARGET ${CMAKE_PROJECT_NAME} POST_BUILD COMMAND ${CMAKE_COMMAND} -E copy_if_different "${CMAKE_SOURCE_DIR}/scripts/solo_mine_example.cmd" $<TARGET_FILE_DIR:${CMAKE_PROJECT_NAME}>)
add_custom_command(TARGET ${CMAKE_PROJECT_NAME} POST_BUILD COMMAND ${CMAKE_COMMAND} -E copy_if_different "${CMAKE_SOURCE_DIR}/scripts/rtm_ghostrider_example.cmd" $<TARGET_FILE_DIR:${CMAKE_PROJECT_NAME}>)
endif()
if (CMAKE_CXX_COMPILER_ID MATCHES Clang AND CMAKE_BUILD_TYPE STREQUAL Release)
if (CMAKE_CXX_COMPILER_ID MATCHES Clang AND CMAKE_BUILD_TYPE STREQUAL Release AND NOT CMAKE_GENERATOR STREQUAL Xcode)
add_custom_command(TARGET ${PROJECT_NAME} POST_BUILD COMMAND ${CMAKE_STRIP} ${CMAKE_PROJECT_NAME})
endif()

View File

@@ -7,10 +7,10 @@
[![GitHub stars](https://img.shields.io/github/stars/xmrig/xmrig.svg)](https://github.com/xmrig/xmrig/stargazers)
[![GitHub forks](https://img.shields.io/github/forks/xmrig/xmrig.svg)](https://github.com/xmrig/xmrig/network)
XMRig is a high performance, open source, cross platform RandomX, KawPow, CryptoNight and AstroBWT unified CPU/GPU miner and [RandomX benchmark](https://xmrig.com/benchmark). Official binaries are available for Windows, Linux, macOS and FreeBSD.
XMRig is a high performance, open source, cross platform RandomX, KawPow, CryptoNight and [GhostRider](https://github.com/xmrig/xmrig/tree/master/src/crypto/ghostrider#readme) unified CPU/GPU miner and [RandomX benchmark](https://xmrig.com/benchmark). Official binaries are available for Windows, Linux, macOS and FreeBSD.
## Mining backends
- **CPU** (x64/ARMv8)
- **CPU** (x86/x64/ARMv7/ARMv8)
- **OpenCL** for AMD GPUs.
- **CUDA** for NVIDIA GPUs via external [CUDA plugin](https://github.com/xmrig/xmrig-cuda).
@@ -19,7 +19,7 @@ XMRig is a high performance, open source, cross platform RandomX, KawPow, Crypto
* **[Build from source](https://xmrig.com/docs/miner/build)**
## Usage
The preferred way to configure the miner is the [JSON config file](src/config.json) as it is more flexible and human friendly. The [command line interface](https://xmrig.com/docs/miner/command-line-options) does not cover all features, such as mining profiles for different algorithms. Important options can be changed during runtime without miner restart by editing the config file or executing API calls.
The preferred way to configure the miner is the [JSON config file](https://xmrig.com/docs/miner/config) as it is more flexible and human friendly. The [command line interface](https://xmrig.com/docs/miner/command-line-options) does not cover all features, such as mining profiles for different algorithms. Important options can be changed during runtime without miner restart by editing the config file or executing [API](https://xmrig.com/docs/miner/api) calls.
* **[Wizard](https://xmrig.com/wizard)** helps you create initial configuration for the miner.
* **[Workers](http://workers.xmrig.info)** helps manage your miners via HTTP API.

View File

@@ -1,45 +0,0 @@
if (WITH_ASTROBWT)
add_definitions(/DXMRIG_ALGO_ASTROBWT)
list(APPEND HEADERS_CRYPTO
src/crypto/astrobwt/AstroBWT.h
)
list(APPEND SOURCES_CRYPTO
src/crypto/astrobwt/AstroBWT.cpp
)
if (XMRIG_ARM)
list(APPEND HEADERS_CRYPTO
src/crypto/astrobwt/salsa20_ref/ecrypt-config.h
src/crypto/astrobwt/salsa20_ref/ecrypt-machine.h
src/crypto/astrobwt/salsa20_ref/ecrypt-portable.h
src/crypto/astrobwt/salsa20_ref/ecrypt-sync.h
)
list(APPEND SOURCES_CRYPTO
src/crypto/astrobwt/salsa20_ref/salsa20.c
)
else()
if (CMAKE_SIZEOF_VOID_P EQUAL 8)
add_definitions(/DASTROBWT_AVX2)
if (CMAKE_C_COMPILER_ID MATCHES MSVC)
enable_language(ASM_MASM)
list(APPEND SOURCES_CRYPTO src/crypto/astrobwt/sha3_256_avx2.asm)
else()
enable_language(ASM)
list(APPEND SOURCES_CRYPTO src/crypto/astrobwt/sha3_256_avx2.S)
endif()
endif()
list(APPEND HEADERS_CRYPTO
src/crypto/astrobwt/Salsa20.hpp
)
list(APPEND SOURCES_CRYPTO
src/crypto/astrobwt/Salsa20.cpp
)
endif()
else()
remove_definitions(/DXMRIG_ALGO_ASTROBWT)
endif()

View File

@@ -1,48 +1,70 @@
if (CMAKE_SIZEOF_VOID_P EQUAL 8)
set(XMRIG_64_BIT ON)
add_definitions(-DXMRIG_64_BIT)
else()
set(XMRIG_64_BIT OFF)
endif()
if (NOT CMAKE_SYSTEM_PROCESSOR)
message(WARNING "CMAKE_SYSTEM_PROCESSOR not defined")
endif()
if (CMAKE_SYSTEM_PROCESSOR MATCHES "^(x86_64|AMD64)$" AND CMAKE_SIZEOF_VOID_P EQUAL 8)
add_definitions(/DRAPIDJSON_SSE2)
include(CheckCXXCompilerFlag)
if (CMAKE_CXX_COMPILER_ID MATCHES MSVC)
set(VAES_SUPPORTED ON)
else()
CHECK_CXX_COMPILER_FLAG("-mavx2 -mvaes" VAES_SUPPORTED)
endif()
if (NOT VAES_SUPPORTED)
set(WITH_VAES OFF)
endif()
if (XMRIG_64_BIT AND CMAKE_SYSTEM_PROCESSOR MATCHES "^(x86_64|AMD64)$")
add_definitions(-DRAPIDJSON_SSE2)
else()
set(WITH_SSE4_1 OFF)
set(WITH_AVX2 OFF)
set(WITH_VAES OFF)
endif()
if (ARM_V8)
set(ARM_TARGET 8)
elseif (ARM_V7)
set(ARM_TARGET 7)
endif()
if (NOT ARM_TARGET)
if (CMAKE_SYSTEM_PROCESSOR MATCHES "^(aarch64|arm64|armv8-a)$")
set(ARM_TARGET 8)
elseif (CMAKE_SYSTEM_PROCESSOR MATCHES "^(armv7|armv7f|armv7s|armv7k|armv7-a|armv7l)$")
elseif (CMAKE_SYSTEM_PROCESSOR MATCHES "^(armv7|armv7f|armv7s|armv7k|armv7-a|armv7l|armv7ve)$")
set(ARM_TARGET 7)
endif()
endif()
if (ARM_TARGET AND ARM_TARGET GREATER 6)
set(XMRIG_ARM ON)
set(WITH_LIBCPUID OFF)
add_definitions(/DXMRIG_ARM)
set(XMRIG_ARM ON)
add_definitions(-DXMRIG_ARM=${ARM_TARGET})
message(STATUS "Use ARM_TARGET=${ARM_TARGET} (${CMAKE_SYSTEM_PROCESSOR})")
include(CheckCXXCompilerFlag)
if (ARM_TARGET EQUAL 8)
set(XMRIG_ARMv8 ON)
add_definitions(/DXMRIG_ARMv8)
CHECK_CXX_COMPILER_FLAG(-march=armv8-a+crypto XMRIG_ARM_CRYPTO)
if (XMRIG_ARM_CRYPTO)
add_definitions(/DXMRIG_ARM_CRYPTO)
add_definitions(-DXMRIG_ARM_CRYPTO)
set(ARM8_CXX_FLAGS "-march=armv8-a+crypto")
else()
set(ARM8_CXX_FLAGS "-march=armv8-a")
endif()
elseif (ARM_TARGET EQUAL 7)
set(XMRIG_ARMv7 ON)
add_definitions(/DXMRIG_ARMv7)
endif()
endif()
if (WITH_SSE4_1)
add_definitions(/DXMRIG_FEATURE_SSE4_1)
add_definitions(-DXMRIG_FEATURE_SSE4_1)
endif()
if (WITH_AVX2)
add_definitions(-DXMRIG_FEATURE_AVX2)
endif()

View File

@@ -10,7 +10,7 @@ if ("${CMAKE_BUILD_TYPE}" STREQUAL "")
endif()
if (CMAKE_BUILD_TYPE STREQUAL "Release")
add_definitions(/DNDEBUG)
add_definitions(-DNDEBUG)
endif()
include(CheckSymbolExists)
@@ -22,17 +22,17 @@ if (CMAKE_CXX_COMPILER_ID MATCHES GNU)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wall -fexceptions -fno-rtti -Wno-strict-aliasing -Wno-class-memaccess")
set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -Ofast -s")
if (XMRIG_ARMv8)
if (ARM_TARGET EQUAL 8)
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${ARM8_CXX_FLAGS}")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${ARM8_CXX_FLAGS} -flax-vector-conversions")
elseif (XMRIG_ARMv7)
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -mfpu=neon")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mfpu=neon -flax-vector-conversions")
elseif (ARM_TARGET EQUAL 7)
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -march=armv7-a -mfpu=neon")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=armv7-a -mfpu=neon -flax-vector-conversions")
else()
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -maes")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -maes")
add_definitions(/DHAVE_ROTR)
add_definitions(-DHAVE_ROTR)
endif()
if (WIN32)
@@ -49,28 +49,16 @@ if (CMAKE_CXX_COMPILER_ID MATCHES GNU)
set(CMAKE_EXE_LINKER_FLAGS "${CMAKE_EXE_LINKER_FLAGS} -static")
endif()
add_definitions(/D_GNU_SOURCE)
if (${CMAKE_VERSION} VERSION_LESS "3.1.0")
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -std=c99")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -std=c++11")
endif()
#set(CMAKE_C_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -gdwarf-2")
add_definitions(/DHAVE_BUILTIN_CLEAR_CACHE)
add_definitions(-D_GNU_SOURCE -DHAVE_BUILTIN_CLEAR_CACHE)
elseif (CMAKE_CXX_COMPILER_ID MATCHES MSVC)
set(CMAKE_C_FLAGS_RELEASE "/MT /O2 /Oi /DNDEBUG /GL")
set(CMAKE_CXX_FLAGS_RELEASE "/MT /O2 /Oi /DNDEBUG /GL")
set(CMAKE_C_FLAGS_RELEASE "/MP /MT /O2 /Oi /DNDEBUG /GL")
set(CMAKE_CXX_FLAGS_RELEASE "/MP /MT /O2 /Oi /DNDEBUG /GL")
set(CMAKE_C_FLAGS_RELWITHDEBINFO "/Ob1 /Zi /DRELWITHDEBINFO")
set(CMAKE_CXX_FLAGS_RELWITHDEBINFO "/Ob1 /Zi /DRELWITHDEBINFO")
set(CMAKE_C_FLAGS_RELWITHDEBINFO "/MP /Ob1 /Zi /DRELWITHDEBINFO")
set(CMAKE_CXX_FLAGS_RELWITHDEBINFO "/MP /Ob1 /Zi /DRELWITHDEBINFO")
add_definitions(/D_CRT_SECURE_NO_WARNINGS)
add_definitions(/D_CRT_NONSTDC_NO_WARNINGS)
add_definitions(/DNOMINMAX)
add_definitions(/DHAVE_ROTR)
add_definitions(-D_CRT_SECURE_NO_WARNINGS -D_CRT_NONSTDC_NO_WARNINGS -DNOMINMAX -DHAVE_ROTR)
elseif (CMAKE_CXX_COMPILER_ID MATCHES Clang)
@@ -80,10 +68,10 @@ elseif (CMAKE_CXX_COMPILER_ID MATCHES Clang)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wall -fexceptions -fno-rtti -Wno-missing-braces")
set(CMAKE_CXX_FLAGS_RELEASE "${CMAKE_CXX_FLAGS_RELEASE} -Ofast -funroll-loops -fmerge-all-constants")
if (XMRIG_ARMv8)
if (ARM_TARGET EQUAL 8)
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${ARM8_CXX_FLAGS}")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${ARM8_CXX_FLAGS}")
elseif (XMRIG_ARMv7)
elseif (ARM_TARGET EQUAL 7)
set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -mfpu=neon -march=${CMAKE_SYSTEM_PROCESSOR}")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mfpu=neon -march=${CMAKE_SYSTEM_PROCESSOR}")
else()
@@ -92,7 +80,7 @@ elseif (CMAKE_CXX_COMPILER_ID MATCHES Clang)
check_symbol_exists("_rotr" "x86intrin.h" HAVE_ROTR)
if (HAVE_ROTR)
add_definitions(/DHAVE_ROTR)
add_definitions(-DHAVE_ROTR)
endif()
endif()
@@ -105,6 +93,6 @@ endif()
if (NOT WIN32)
check_symbol_exists("__builtin___clear_cache" "stdlib.h" HAVE_BUILTIN_CLEAR_CACHE)
if (HAVE_BUILTIN_CLEAR_CACHE)
add_definitions(/DHAVE_BUILTIN_CLEAR_CACHE)
add_definitions(-DHAVE_BUILTIN_CLEAR_CACHE)
endif()
endif()

13
cmake/fmt.cmake Normal file
View File

@@ -0,0 +1,13 @@
# SPDX-FileCopyrightText: © 2023 Jean-Pierre De Jesus DIAZ <me@jeandudey.tech>
# SPDX-License-Identifier: GPL-3.0-or-later
if(WITH_BUNDLED_FMT)
add_library(fmt INTERFACE)
target_sources(fmt INTERFACE ${CMAKE_CURRENT_SOURCE_DIR}/src/3rdparty/fmt/format.cc)
target_include_directories(fmt INTERFACE ${CMAKE_CURRENT_SOURCE_DIR}/src/3rdparty/fmt)
else()
set(FMT_LIBRARY fmt)
find_package(fmt REQUIRED)
set(FMT_LIBRARY fmt::fmt)
endif()

8
cmake/ghostrider.cmake Normal file
View File

@@ -0,0 +1,8 @@
if (WITH_GHOSTRIDER)
add_definitions(/DXMRIG_ALGO_GHOSTRIDER)
add_subdirectory(src/crypto/ghostrider)
set(GHOSTRIDER_LIBRARY ghostrider)
else()
remove_definitions(/DXMRIG_ALGO_GHOSTRIDER)
set(GHOSTRIDER_LIBRARY "")
endif()

View File

@@ -15,31 +15,38 @@ else()
set(XMRIG_OS_ANDROID ON)
elseif(CMAKE_SYSTEM_NAME MATCHES "Linux")
set(XMRIG_OS_LINUX ON)
elseif(CMAKE_SYSTEM_NAME STREQUAL FreeBSD)
elseif(CMAKE_SYSTEM_NAME STREQUAL FreeBSD OR CMAKE_SYSTEM_NAME STREQUAL DragonFly)
set(XMRIG_OS_FREEBSD ON)
endif()
endif()
if (XMRIG_OS_WIN)
add_definitions(/DWIN32)
add_definitions(/DXMRIG_OS_WIN)
add_definitions(-DWIN32 -DXMRIG_OS_WIN)
elseif(XMRIG_OS_APPLE)
add_definitions(/DXMRIG_OS_APPLE)
add_definitions(-DXMRIG_OS_APPLE)
if (XMRIG_OS_IOS)
add_definitions(/DXMRIG_OS_IOS)
add_definitions(-DXMRIG_OS_IOS)
else()
add_definitions(/DXMRIG_OS_MACOS)
add_definitions(-DXMRIG_OS_MACOS)
endif()
if (XMRIG_ARM)
set(WITH_SECURE_JIT ON)
endif()
elseif(XMRIG_OS_UNIX)
add_definitions(/DXMRIG_OS_UNIX)
add_definitions(-DXMRIG_OS_UNIX)
if (XMRIG_OS_ANDROID)
add_definitions(/DXMRIG_OS_ANDROID)
add_definitions(-DXMRIG_OS_ANDROID)
elseif (XMRIG_OS_LINUX)
add_definitions(/DXMRIG_OS_LINUX)
add_definitions(-DXMRIG_OS_LINUX)
elseif (XMRIG_OS_FREEBSD)
add_definitions(/DXMRIG_OS_FREEBSD)
add_definitions(-DXMRIG_OS_FREEBSD)
endif()
endif()
if (WITH_SECURE_JIT)
add_definitions(-DXMRIG_SECURE_JIT)
endif()

View File

@@ -42,13 +42,13 @@ if (WITH_RANDOMX)
src/crypto/rx/RxVm.cpp
)
if (CMAKE_C_COMPILER_ID MATCHES MSVC)
if (WITH_ASM AND CMAKE_C_COMPILER_ID MATCHES MSVC)
enable_language(ASM_MASM)
list(APPEND SOURCES_CRYPTO
src/crypto/randomx/jit_compiler_x86_static.asm
src/crypto/randomx/jit_compiler_x86.cpp
)
elseif (NOT XMRIG_ARM AND CMAKE_SIZEOF_VOID_P EQUAL 8)
elseif (WITH_ASM AND NOT XMRIG_ARM AND CMAKE_SIZEOF_VOID_P EQUAL 8)
list(APPEND SOURCES_CRYPTO
src/crypto/randomx/jit_compiler_x86_static.S
src/crypto/randomx/jit_compiler_x86.cpp
@@ -61,7 +61,11 @@ if (WITH_RANDOMX)
src/crypto/randomx/jit_compiler_a64.cpp
)
# cheat because cmake and ccache hate each other
set_property(SOURCE src/crypto/randomx/jit_compiler_a64_static.S PROPERTY LANGUAGE C)
if (CMAKE_GENERATOR STREQUAL Xcode)
set_property(SOURCE src/crypto/randomx/jit_compiler_a64_static.S PROPERTY LANGUAGE ASM)
else()
set_property(SOURCE src/crypto/randomx/jit_compiler_a64_static.S PROPERTY LANGUAGE C)
endif()
else()
list(APPEND SOURCES_CRYPTO
src/crypto/randomx/jit_compiler_fallback.cpp
@@ -72,7 +76,15 @@ if (WITH_RANDOMX)
list(APPEND SOURCES_CRYPTO src/crypto/randomx/blake2/blake2b_sse41.c)
if (CMAKE_C_COMPILER_ID MATCHES GNU OR CMAKE_C_COMPILER_ID MATCHES Clang)
set_source_files_properties(src/crypto/randomx/blake2/blake2b_sse41.c PROPERTIES COMPILE_FLAGS -msse4.1)
set_source_files_properties(src/crypto/randomx/blake2/blake2b_sse41.c PROPERTIES COMPILE_FLAGS "-Ofast -msse4.1")
endif()
endif()
if (WITH_AVX2)
list(APPEND SOURCES_CRYPTO src/crypto/randomx/blake2/avx2/blake2b_avx2.c)
if (CMAKE_C_COMPILER_ID MATCHES GNU OR CMAKE_C_COMPILER_ID MATCHES Clang)
set_source_files_properties(src/crypto/randomx/blake2/avx2/blake2b_avx2.c PROPERTIES COMPILE_FLAGS "-Ofast -mavx2")
endif()
endif()
@@ -96,18 +108,41 @@ if (WITH_RANDOMX)
message("-- WITH_MSR=ON")
if (XMRIG_OS_WIN)
list(APPEND SOURCES_CRYPTO src/crypto/rx/Rx_win.cpp)
list(APPEND SOURCES_CRYPTO
src/crypto/rx/RxFix_win.cpp
src/hw/msr/Msr_win.cpp
)
elseif (XMRIG_OS_LINUX)
list(APPEND SOURCES_CRYPTO src/crypto/rx/Rx_linux.cpp)
list(APPEND SOURCES_CRYPTO
src/crypto/rx/RxFix_linux.cpp
src/hw/msr/Msr_linux.cpp
)
endif()
list(APPEND HEADERS_CRYPTO src/crypto/rx/msr/MsrItem.h)
list(APPEND SOURCES_CRYPTO src/crypto/rx/msr/MsrItem.cpp)
list(APPEND HEADERS_CRYPTO
src/crypto/rx/RxFix.h
src/crypto/rx/RxMsr.h
src/hw/msr/Msr.h
src/hw/msr/MsrItem.h
)
list(APPEND SOURCES_CRYPTO
src/crypto/rx/RxMsr.cpp
src/hw/msr/Msr.cpp
src/hw/msr/MsrItem.cpp
)
else()
remove_definitions(/DXMRIG_FEATURE_MSR)
remove_definitions(/DXMRIG_FIX_RYZEN)
message("-- WITH_MSR=OFF")
endif()
if (WITH_PROFILING)
add_definitions(/DXMRIG_FEATURE_PROFILING)
list(APPEND HEADERS_CRYPTO src/crypto/rx/Profiler.h)
list(APPEND SOURCES_CRYPTO src/crypto/rx/Profiler.cpp)
endif()
else()
remove_definitions(/DXMRIG_ALGO_RANDOMX)
endif()

View File

@@ -1,3 +1,5 @@
**:warning: Recent version of this page https://xmrig.com/docs/miner/config/cpu.**
# CPU backend
All CPU related settings contains in one `cpu` object in config file, CPU backend allow specify multiple profiles and allow switch between them without restrictions by pool request or config change. Default auto-configuration create reasonable minimum of profiles which cover all supported algorithms.
@@ -75,6 +77,35 @@ Each number represent one thread and means CPU affinity, this is default format
```
Internal format, but can be user defined.
## RandomX options
#### `init`
Thread count to initialize RandomX dataset. Auto-detect (`-1`) or any number greater than 0 to use that many threads.
#### `init-avx2`
Use AVX2 for dataset initialization. Faster on some CPUs. Auto-detect (`-1`), disabled (`0`), always enabled on CPUs that support AVX2 (`1`).
#### `mode`
RandomX mining mode: `auto`, `fast` (2 GB memory), `light` (256 MB memory).
#### `1gb-pages`
Use 1GB hugepages for RandomX dataset (Linux only). Enabled (`true`) or disabled (`false`). It gives 1-3% speedup.
#### `wrmsr`
[MSR mod](https://xmrig.com/docs/miner/randomx-optimization-guide/msr). Enabled (`true`) or disabled (`false`). It gives up to 15% speedup depending on your system. _(**Note**: Userspace MSR writes are no longer enabled by default; the flag `msr.allow_writes=on` must be set for Linux Kernels 5.9 and after.)_
#### `rdmsr`
Restore MSR register values to their original values on exit. Used together with `wrmsr`. Enabled (`true`) or disabled (`false`).
#### `cache_qos`
[Cache QoS](https://xmrig.com/docs/miner/randomx-optimization-guide/qos). Enabled (`true`) or disabled (`false`). It's useful when you can't or don't want to mine on all CPU cores to make mining hashrate more stable.
#### `numa`
NUMA support (better hashrate on multi-CPU servers and Ryzen Threadripper 1xxx/2xxx). Enabled (`true`) or disabled (`false`).
#### `scratchpad_prefetch_mode`
Which instruction to use in RandomX loop to prefetch data from scratchpad. `1` is default and fastest in most cases. Can be off (`0`), `prefetcht0` instruction (`1`), `prefetchnta` instruction (`2`, a bit faster on Coffee Lake and a few other CPUs), `mov` instruction (`3`).
## Shared options
#### `enabled`
@@ -83,23 +114,32 @@ Enable (`true`) or disable (`false`) CPU backend, by default `true`.
#### `huge-pages`
Enable (`true`) or disable (`false`) huge pages support, by default `true`.
#### `huge-pages-jit`
Enable (`true`) or disable (`false`) huge pages support for RandomX JIT code, by default `false`. It gives a very small boost on Ryzen CPUs, but hashrate is unstable between launches. Use with caution.
#### `hw-aes`
Force enable (`true`) or disable (`false`) hardware AES support. Default value `null` means miner autodetect this feature. Usually don't need change this option, this option useful for some rare cases when miner can't detect hardware AES, but it available. If you force enable this option, but your hardware not support it, miner will crash.
#### `priority`
Mining threads priority, value from `1` (lowest priority) to `5` (highest possible priority). Default value `null` means miner don't change threads priority at all.
Mining threads priority, value from `1` (lowest priority) to `5` (highest possible priority). Default value `null` means miner don't change threads priority at all. Setting priority higher than 2 can make your PC unresponsive.
#### `memory-pool` (since v4.3.0)
Use continuous, persistent memory block for mining threads, useful for preserve huge pages allocation while algorithm switching. Possible values `false` (feature disabled, by default) or `true` or specific count of 2 MB huge pages. It helps to avoid loosing huge pages for scratchpads when RandomX dataset is updated and mining threads restart after a 2-3 days of mining.
#### `yield` (since v5.1.1)
Prefer system better system response/stability `true` (default value) or maximum hashrate `false`.
#### `asm`
Enable/configure or disable ASM optimizations. Possible values: `true`, `false`, `"intel"`, `"ryzen"`, `"bulldozer"`.
#### `argon2-impl` (since v3.1.0)
Allow override automatically detected Argon2 implementation, this option added mostly for debug purposes, default value `null` means autodetect. Other possible values: `"x86_64"`, `"SSE2"`, `"SSSE3"`, `"XOP"`, `"AVX2"`, `"AVX-512F"`. Manual selection has no safe guards, if you CPU not support required instuctions, miner will crash.
Allow override automatically detected Argon2 implementation, this option added mostly for debug purposes, default value `null` means autodetect. This is used in RandomX dataset initialization and also in some other mining algorithms. Other possible values: `"x86_64"`, `"SSE2"`, `"SSSE3"`, `"XOP"`, `"AVX2"`, `"AVX-512F"`. Manual selection has no safe guards - if your CPU doesn't support required instuctions, miner will crash.
#### `astrobwt-max-size`
AstroBWT algorithm: skip hashes with large stage 2 size, default: `550`, min: `400`, max: `1200`. Optimal value depends on your CPU/GPU
#### `astrobwt-avx2`
AstroBWT algorithm: use AVX2 code. It's faster on some CPUs and slower on other
#### `max-threads-hint` (since v4.2.0)
Maximum CPU threads count (in percentage) hint for autoconfig. [CPU_MAX_USAGE.md](CPU_MAX_USAGE.md)
#### `memory-pool` (since v4.3.0)
Use continuous, persistent memory block for mining threads, useful for preserve huge pages allocation while algorithm swithing. Possible values `false` (feature disabled, by default) or `true` or specific count of 2 MB huge pages.
#### `yield` (since v5.1.1)
Prefer system better system response/stability `true` (default value) or maximum hashrate `false`.

View File

@@ -1,5 +0,0 @@
6bb1a2e3a0fbca5195be6022f2a9fbff8a353c37c7542e7ab89420cb45b64505 xmrig-5.0.1-gcc-win32.zip
24dba9ec281acfb2ea2c401ebd0e4e2d1f1ee5fd557da5ff3c7049020c1f78b6 xmrig-5.0.1-gcc-win64.zip
86d65c6693ec9e35cd7547329580638b85c9eb0cf8383892a1c15199de5b556f xmrig-5.0.1-msvc-cuda10_1-win64.zip
0fbfe518b1c4b6993b0f66ff01302626375b15620ccf8f64d6fb97845068ffca xmrig-5.0.1-msvc-win64.zip
aa34890738a3494de2fa0e44db346937fea7339852f5f10b5d4655f95e2d8f1f xmrig-5.0.1-xenial-x64.tar.gz

View File

@@ -1,11 +0,0 @@
-----BEGIN PGP SIGNATURE-----
iQEzBAABCgAdFiEEmsTOqOZuNaXHzdwbRGpTY4vpRAkFAl3VcsoACgkQRGpTY4vp
RAm9vQgA1MyTUU2jley2TCYLUzQy2Fffc8fbXYv64r44jbWOjC/6qo2iIlRgPhIc
oVyPKr5TYS3QjDzCEm8IvozS0YudS6soESbPzqDonboK8pd0K4bsML9TQY2feV7A
NL5vln0rfVHp1wxLLrQpfBqAgvJUXEyaHece6gFQN79JOGhEo2bHL2NyrOl+FViS
b2BaMtXq410Fh+XT6ShnOaG/2EuO8ZqSGdCO6A/2LHQw1UY+mZiCvue6P6B06HmB
WD/urOv38V389v+V+Sp4UlEW6VpBOOjvtChoVWtLt+tKzydrnt2EmoWWWg475pka
4G6whHuMWS8CTt5/PDhJpvVXNQTIOw==
=C764
-----END PGP SIGNATURE-----

View File

@@ -1,3 +1,4 @@
@echo off
cd /d "%~dp0"
xmrig.exe --bench=10M --submit
pause

View File

@@ -1,3 +1,4 @@
@echo off
cd /d "%~dp0"
xmrig.exe --bench=1M --submit
pause

View File

@@ -1,6 +1,10 @@
#!/bin/bash -e
HWLOC_VERSION="2.2.0"
HWLOC_VERSION_MAJOR="2"
HWLOC_VERSION_MINOR="9"
HWLOC_VERSION_PATCH="0"
HWLOC_VERSION="${HWLOC_VERSION_MAJOR}.${HWLOC_VERSION_MINOR}.${HWLOC_VERSION_PATCH}"
mkdir -p deps
mkdir -p deps/include
@@ -8,7 +12,7 @@ mkdir -p deps/lib
mkdir -p build && cd build
wget https://download.open-mpi.org/release/hwloc/v2.2/hwloc-${HWLOC_VERSION}.tar.gz -O hwloc-${HWLOC_VERSION}.tar.gz
wget https://download.open-mpi.org/release/hwloc/v${HWLOC_VERSION_MAJOR}.${HWLOC_VERSION_MINOR}/hwloc-${HWLOC_VERSION}.tar.gz -O hwloc-${HWLOC_VERSION}.tar.gz
tar -xzf hwloc-${HWLOC_VERSION}.tar.gz
cd hwloc-${HWLOC_VERSION}
@@ -16,4 +20,4 @@ cd hwloc-${HWLOC_VERSION}
make -j$(nproc || sysctl -n hw.ncpu || sysctl -n hw.logicalcpu)
cp -fr include ../../deps
cp hwloc/.libs/libhwloc.a ../../deps/lib
cd ..
cd ..

View File

@@ -1,6 +1,6 @@
#!/bin/bash -e
LIBRESSL_VERSION="3.0.2"
LIBRESSL_VERSION="3.5.2"
mkdir -p deps
mkdir -p deps/include
@@ -17,4 +17,4 @@ make -j$(nproc || sysctl -n hw.ncpu || sysctl -n hw.logicalcpu)
cp -fr include ../../deps
cp crypto/.libs/libcrypto.a ../../deps/lib
cp ssl/.libs/libssl.a ../../deps/lib
cd ..
cd ..

View File

@@ -1,6 +1,6 @@
#!/bin/bash -e
OPENSSL_VERSION="1.1.1h"
OPENSSL_VERSION="1.1.1s"
mkdir -p deps
mkdir -p deps/include
@@ -17,4 +17,4 @@ make -j$(nproc || sysctl -n hw.ncpu || sysctl -n hw.logicalcpu)
cp -fr include ../../deps
cp libcrypto.a ../../deps/lib
cp libssl.a ../../deps/lib
cd ..
cd ..

20
scripts/build.openssl3.sh Executable file
View File

@@ -0,0 +1,20 @@
#!/bin/bash -e
OPENSSL_VERSION="3.0.7"
mkdir -p deps
mkdir -p deps/include
mkdir -p deps/lib
mkdir -p build && cd build
wget https://www.openssl.org/source/openssl-${OPENSSL_VERSION}.tar.gz -O openssl-${OPENSSL_VERSION}.tar.gz
tar -xzf openssl-${OPENSSL_VERSION}.tar.gz
cd openssl-${OPENSSL_VERSION}
./config -no-shared -no-asm -no-zlib -no-comp -no-dgram -no-filenames -no-cms
make -j$(nproc || sysctl -n hw.ncpu || sysctl -n hw.logicalcpu)
cp -fr include ../../deps
cp libcrypto.a ../../deps/lib
cp libssl.a ../../deps/lib
cd ..

View File

@@ -1,6 +1,6 @@
#!/bin/bash -e
UV_VERSION="1.40.0"
UV_VERSION="1.44.2"
mkdir -p deps
mkdir -p deps/include
@@ -17,4 +17,4 @@ sh autogen.sh
make -j$(nproc || sysctl -n hw.ncpu || sysctl -n hw.logicalcpu)
cp -fr include ../../deps
cp .libs/libuv.a ../../deps/lib
cd ..
cd ..

View File

@@ -51,6 +51,7 @@ function rx()
'randomx_constants_wow.h',
'randomx_constants_arqma.h',
'randomx_constants_keva.h',
'randomx_constants_graft.h',
'aes.cl',
'blake2b.cl',
'randomx_vm.cl',
@@ -66,15 +67,6 @@ function rx()
}
function astrobwt()
{
const astrobwt = opencl_minify(addIncludes('astrobwt.cl', [ 'BWT.cl', 'salsa20.cl', 'sha3.cl' ]));
// fs.writeFileSync('astrobwt_gen.cl', astrobwt);
fs.writeFileSync('astrobwt_cl.h', text2h(astrobwt, 'xmrig', 'astrobwt_cl'));
}
function kawpow()
{
const kawpow = opencl_minify(addIncludes('kawpow.cl', [ 'defs.h' ]));
@@ -96,11 +88,6 @@ process.chdir(path.resolve('src/backend/opencl/cl/rx'));
rx();
process.chdir(cwd);
process.chdir(path.resolve('src/backend/opencl/cl/astrobwt'));
astrobwt();
process.chdir(cwd);
process.chdir(path.resolve('src/backend/opencl/cl/kawpow'));

View File

@@ -0,0 +1,20 @@
:: Example batch file for mining Monero at a pool
::
:: Format:
:: xmrig.exe -o <pool address>:<pool port> -u <pool username/wallet> -p <pool password>
::
:: Fields:
:: pool address The host name of the pool stratum or its IP address, for example pool.hashvault.pro
:: pool port The port of the pool's stratum to connect to, for example 3333. Check your pool's getting started page.
:: pool username/wallet For most pools, this is the wallet address you want to mine to. Some pools require a username
:: pool password For most pools this can be just 'x'. For pools using usernames, you may need to provide a password as configured on the pool.
::
:: List of Monero mining pools:
:: https://miningpoolstats.stream/monero
::
:: Choose pools outside of top 5 to help Monero network be more decentralized!
:: Smaller pools also often have smaller fees/payout limits.
cd /d "%~dp0"
xmrig.exe -o xmrpool.eu:3333 -u 48edfHu7V9Z84YzzMa6fUueoELZ9ZRXq9VetWzYGzKt52XU5xvqgzYnDK9URnRoJMk1j8nLwEVsaSWJ4fhdUyZijBGUicoD -p x
pause

View File

@@ -1,28 +1,44 @@
#!/bin/bash
#!/bin/sh -e
modprobe msr
MSR_FILE=/sys/module/msr/parameters/allow_writes
if cat /proc/cpuinfo | grep "AMD Ryzen" > /dev/null;
if test -e "$MSR_FILE"; then
echo on > $MSR_FILE
else
modprobe msr allow_writes=on
fi
if grep -E 'AMD Ryzen|AMD EPYC' /proc/cpuinfo > /dev/null;
then
if cat /proc/cpuinfo | grep "cpu family[[:space:]]:[[:space:]]25" > /dev/null;
if grep "cpu family[[:space:]]\{1,\}:[[:space:]]25" /proc/cpuinfo > /dev/null;
then
echo "Detected Ryzen (Zen3)"
wrmsr -a 0xc0011020 0x4480000000000
wrmsr -a 0xc0011021 0x1c000200000040
wrmsr -a 0xc0011022 0xc000000401500000
wrmsr -a 0xc001102b 0x2000cc14
echo "MSR register values for Ryzen (Zen3) applied"
if grep "model[[:space:]]\{1,\}:[[:space:]]97" /proc/cpuinfo > /dev/null;
then
echo "Detected Zen4 CPU"
wrmsr -a 0xc0011020 0x4400000000000
wrmsr -a 0xc0011021 0x4000000000040
wrmsr -a 0xc0011022 0x8680000401570000
wrmsr -a 0xc001102b 0x2040cc10
echo "MSR register values for Zen4 applied"
else
echo "Detected Zen3 CPU"
wrmsr -a 0xc0011020 0x4480000000000
wrmsr -a 0xc0011021 0x1c000200000040
wrmsr -a 0xc0011022 0xc000000401570000
wrmsr -a 0xc001102b 0x2000cc10
echo "MSR register values for Zen3 applied"
fi
else
echo "Detected Ryzen (Zen1/Zen2)"
echo "Detected Zen1/Zen2 CPU"
wrmsr -a 0xc0011020 0
wrmsr -a 0xc0011021 0x40
wrmsr -a 0xc0011022 0x1510000
wrmsr -a 0xc001102b 0x2000cc16
echo "MSR register values for Ryzen (Zen1/Zen2) applied"
echo "MSR register values for Zen1/Zen2 applied"
fi
elif cat /proc/cpuinfo | grep "Intel" > /dev/null;
elif grep "Intel" /proc/cpuinfo > /dev/null;
then
echo "Detected Intel"
echo "Detected Intel CPU"
wrmsr -a 0x1a4 0xf
echo "MSR register values for Intel applied"
else

View File

@@ -0,0 +1,23 @@
:: Example batch file for mining Raptoreum at a pool
::
:: Format:
:: xmrig.exe -a gr -o <pool address>:<pool port> -u <pool username/wallet> -p <pool password>
::
:: Fields:
:: pool address The host name of the pool stratum or its IP address, for example raptoreumemporium.com
:: pool port The port of the pool's stratum to connect to, for example 3333. Check your pool's getting started page.
:: pool username/wallet For most pools, this is the wallet address you want to mine to. Some pools require a username
:: pool password For most pools this can be just 'x'. For pools using usernames, you may need to provide a password as configured on the pool.
::
:: List of Raptoreum mining pools:
:: https://miningpoolstats.stream/raptoreum
::
:: Choose pools outside of top 5 to help Raptoreum network be more decentralized!
:: Smaller pools also often have smaller fees/payout limits.
cd /d "%~dp0"
:: Use this command line to connect to non-SSL port
xmrig.exe -a gr -o raptoreumemporium.com:3008 -u WALLET_ADDRESS -p x
:: Or use this command line to connect to an SSL port
:: xmrig.exe -a gr -o rtm.suprnova.cc:4273 --tls -u WALLET_ADDRESS -p x
pause

View File

@@ -0,0 +1,16 @@
:: Example batch file for mining Monero solo
::
:: Format:
:: xmrig.exe -o <node address>:<node port> -a rx/0 -u <wallet address> --daemon
::
:: Fields:
:: node address The host name of your monerod node or its IP address. It can also be a public node with RPC enabled, for example node.xmr.to
:: node port The RPC port of your monerod node to connect to, usually 18081.
:: wallet address Check your Monero CLI or GUI wallet to see your wallet's address.
::
:: Mining solo is the best way to help Monero network be more decentralized!
:: But you will only get a payout when you find a block which can take more than a year for a single low-end PC.
cd /d "%~dp0"
xmrig.exe -o YOUR_NODE_IP:18081 -a rx/0 -u 48edfHu7V9Z84YzzMa6fUueoELZ9ZRXq9VetWzYGzKt52XU5xvqgzYnDK9URnRoJMk1j8nLwEVsaSWJ4fhdUyZijBGUicoD --daemon
pause

View File

@@ -44,7 +44,7 @@ extern "C" {
typedef cl_uint cl_dx9_media_adapter_type_khr;
typedef cl_uint cl_dx9_media_adapter_set_khr;
#if defined(_WIN32)
#include <d3d9.h>
typedef struct _cl_dx9_surface_info_khr
@@ -105,7 +105,7 @@ typedef CL_API_ENTRY cl_mem (CL_API_CALL *clCreateFromDX9MediaSurfaceKHR_fn)(
cl_mem_flags flags,
cl_dx9_media_adapter_type_khr adapter_type,
void * surface_info,
cl_uint plane,
cl_uint plane,
cl_int * errcode_ret) CL_API_SUFFIX__VERSION_1_2;
typedef CL_API_ENTRY cl_int (CL_API_CALL *clEnqueueAcquireDX9MediaSurfacesKHR_fn)(

View File

@@ -35,7 +35,7 @@ extern "C" {
#include <CL/cl_gl.h>
/*
/*
* cl_khr_gl_event extension
*/
#define CL_COMMAND_GL_FENCE_SYNC_OBJECT_KHR 0x200D

View File

@@ -1471,7 +1471,7 @@ typedef enum _ADLProfilePropertyType
#define ADL_HDR_FREESYNC_HDR 0x0004 ///< FreeSync HDR supported
/// @}
/// \defgroup define_FreesyncFlags ADLDDCInfo2 Freesync HDR flags
/// \defgroup define_FreesyncFlags ADLDDCInfo2 Freesync HDR flags
/// @{
/// defines for iFreesyncFlags in ADLDDCInfo2
#define ADL_HDR_FREESYNC_BACKLIGHT_SUPPORT 0x0001 ///< Global backlight control supported
@@ -1738,7 +1738,7 @@ enum ADLODNDPMMaskType
ADL_ODN_DPM_MASK = 1 << 2,
};
//ODN features Bits for ADLODNCapabilitiesX2
//ODN features Bits for ADLODNCapabilitiesX2
enum ADLODNFeatureControl
{
ADL_ODN_SCLK_DPM = 1 << 0,
@@ -1764,7 +1764,7 @@ enum ADLODNFeatureControl
//If any new feature is added, PPLIB only needs to add ext feature ID and Item ID(Seeting ID). These IDs should match the drive defined in CWDDEPM.h
enum ADLODNExtFeatureControl
{
{
ADL_ODN_EXT_FEATURE_MEMORY_TIMING_TUNE = 1 << 0,
ADL_ODN_EXT_FEATURE_FAN_ZERO_RPM_CONTROL = 1 << 1,
ADL_ODN_EXT_FEATURE_AUTO_UV_ENGINE = 1 << 2, //Auto under voltage
@@ -1794,7 +1794,7 @@ enum ADLODNExtSettingId
ADL_ODN_PARAMETER_FAN_CURVE_SPEED_5,
ADL_ODN_POWERGAUGE,
ODN_COUNT
} ;
//OD8 Capability features bits
@@ -1811,7 +1811,7 @@ enum ADLOD8FeatureControl
ADL_OD8_MEMORY_TIMING_TUNE = 1 << 8,
ADL_OD8_FAN_ZERO_RPM_CONTROL = 1 << 9 ,
ADL_OD8_AUTO_UV_ENGINE = 1 << 10, //Auto under voltage
ADL_OD8_AUTO_OC_ENGINE = 1 << 11, //Auto overclock engine
ADL_OD8_AUTO_OC_ENGINE = 1 << 11, //Auto overclock engine
ADL_OD8_AUTO_OC_MEMORY = 1 << 12, //Auto overclock memory
ADL_OD8_FAN_CURVE = 1 << 13, //Fan curve
ADL_OD8_WS_AUTO_FAN_ACOUSTIC_LIMIT = 1 << 14, //Workstation Manual Fan controller
@@ -1888,7 +1888,7 @@ typedef enum _ADLSensorType
PMLOG_TEMPERATURE_VRSOC = 24,
PMLOG_TEMPERATURE_VRMVDD0 = 25,
PMLOG_TEMPERATURE_VRMVDD1 = 26,
PMLOG_TEMPERATURE_HOTSPOT = 27,
PMLOG_TEMPERATURE_HOTSPOT = 27,
PMLOG_TEMPERATURE_GFX = 28,
PMLOG_TEMPERATURE_SOC = 29,
PMLOG_GFX_POWER = 30,

View File

@@ -37,7 +37,7 @@
#define __stdcall
#endif /* (LINUX) */
/// Memory Allocation Call back
/// Memory Allocation Call back
typedef void* ( __stdcall *ADL_MAIN_MALLOC_CALLBACK )( int );

View File

@@ -1753,7 +1753,7 @@ typedef struct ADLPXConfigCaps
///\brief Enum containing PX or HG type
///
/// This enum is used to get PX or hG type
///
///
/// \nosubgrouping
//////////////////////////////////////////////////////////////////////////////////////////
enum ADLPxType

View File

@@ -1,4 +1,4 @@
cmake_minimum_required(VERSION 2.8)
cmake_minimum_required(VERSION 3.1)
project(argon2 C)
set(CMAKE_C_STANDARD 99)

2
src/3rdparty/cl.h vendored
View File

@@ -29,7 +29,7 @@
#if defined(__APPLE__)
# include <OpenCL/cl.h>
#else
# include "3rdparty/CL/cl.h"
# include <CL/cl.h>
#endif

25
src/3rdparty/epee/LICENSE.txt vendored Normal file
View File

@@ -0,0 +1,25 @@
Copyright (c) 2006-2013, Andrey N. Sabelnikov, www.sabelnikov.net
All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
* Redistributions of source code must retain the above copyright
notice, this list of conditions and the following disclaimer.
* Redistributions in binary form must reproduce the above copyright
notice, this list of conditions and the following disclaimer in the
documentation and/or other materials provided with the distribution.
* Neither the name of the Andrey N. Sabelnikov nor the
names of its contributors may be used to endorse or promote products
derived from this software without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL Andrey N. Sabelnikov BE LIABLE FOR ANY
DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

1
src/3rdparty/epee/README.md vendored Normal file
View File

@@ -0,0 +1 @@
epee - is a small library of helpers, wrappers, tools and and so on, used to make my life easier.

176
src/3rdparty/epee/span.h vendored Normal file
View File

@@ -0,0 +1,176 @@
// Copyright (c) 2017-2020, The Monero Project
//
// All rights reserved.
//
// Redistribution and use in source and binary forms, with or without modification, are
// permitted provided that the following conditions are met:
//
// 1. Redistributions of source code must retain the above copyright notice, this list of
// conditions and the following disclaimer.
//
// 2. Redistributions in binary form must reproduce the above copyright notice, this list
// of conditions and the following disclaimer in the documentation and/or other
// materials provided with the distribution.
//
// 3. Neither the name of the copyright holder nor the names of its contributors may be
// used to endorse or promote products derived from this software without specific
// prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY
// EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
// MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL
// THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
// SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
// PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
// INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT,
// STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF
// THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#pragma once
#include <algorithm>
#include <cstdint>
#include <memory>
#include <string>
#include <type_traits>
namespace epee
{
/*!
\brief Non-owning sequence of data. Does not deep copy
Inspired by `gsl::span` and/or `boost::iterator_range`. This class is
intended to be used as a parameter type for functions that need to take a
writable or read-only sequence of data. Most common cases are `span<char>`
and `span<std::uint8_t>`. Using as a class member is only recommended if
clearly documented as not doing a deep-copy. C-arrays are easily convertible
to this type.
\note Conversion from C string literal to `span<const char>` will include
the NULL-terminator.
\note Never allows derived-to-base pointer conversion; an array of derived
types is not an array of base types.
*/
template<typename T>
class span
{
template<typename U>
static constexpr bool safe_conversion() noexcept
{
// Allow exact matches or `T*` -> `const T*`.
using with_const = typename std::add_const<U>::type;
return std::is_same<T, U>() ||
(std::is_const<T>() && std::is_same<T, with_const>());
}
public:
using value_type = T;
using size_type = std::size_t;
using difference_type = std::ptrdiff_t;
using pointer = T*;
using const_pointer = const T*;
using reference = T&;
using const_reference = const T&;
using iterator = pointer;
using const_iterator = const_pointer;
constexpr span() noexcept : ptr(nullptr), len(0) {}
constexpr span(std::nullptr_t) noexcept : span() {}
//! Prevent derived-to-base conversions; invalid in this context.
template<typename U, typename = typename std::enable_if<safe_conversion<U>()>::type>
constexpr span(U* const src_ptr, const std::size_t count) noexcept
: ptr(src_ptr), len(count) {}
//! Conversion from C-array. Prevents common bugs with sizeof + arrays.
template<std::size_t N>
constexpr span(T (&src)[N]) noexcept : span(src, N) {}
constexpr span(const span&) noexcept = default;
span& operator=(const span&) noexcept = default;
/*! Try to remove `amount` elements from beginning of span.
\return Number of elements removed. */
std::size_t remove_prefix(std::size_t amount) noexcept
{
amount = std::min(len, amount);
ptr += amount;
len -= amount;
return amount;
}
constexpr iterator begin() const noexcept { return ptr; }
constexpr const_iterator cbegin() const noexcept { return ptr; }
constexpr iterator end() const noexcept { return begin() + size(); }
constexpr const_iterator cend() const noexcept { return cbegin() + size(); }
constexpr bool empty() const noexcept { return size() == 0; }
constexpr pointer data() const noexcept { return ptr; }
constexpr std::size_t size() const noexcept { return len; }
constexpr std::size_t size_bytes() const noexcept { return size() * sizeof(value_type); }
T &operator[](size_t idx) noexcept { return ptr[idx]; }
const T &operator[](size_t idx) const noexcept { return ptr[idx]; }
private:
T* ptr;
std::size_t len;
};
//! \return `span<const T::value_type>` from a STL compatible `src`.
template<typename T>
constexpr span<const typename T::value_type> to_span(const T& src)
{
// compiler provides diagnostic if size() is not size_t.
return {src.data(), src.size()};
}
//! \return `span<T::value_type>` from a STL compatible `src`.
template<typename T>
constexpr span<typename T::value_type> to_mut_span(T& src)
{
// compiler provides diagnostic if size() is not size_t.
return {src.data(), src.size()};
}
template<typename T>
constexpr bool has_padding() noexcept
{
return !std::is_standard_layout<T>() || alignof(T) != 1;
}
//! \return Cast data from `src` as `span<const std::uint8_t>`.
template<typename T>
span<const std::uint8_t> to_byte_span(const span<const T> src) noexcept
{
static_assert(!has_padding<T>(), "source type may have padding");
return {reinterpret_cast<const std::uint8_t*>(src.data()), src.size_bytes()};
}
//! \return `span<const std::uint8_t>` which represents the bytes at `&src`.
template<typename T>
span<const std::uint8_t> as_byte_span(const T& src) noexcept
{
static_assert(!std::is_empty<T>(), "empty types will not work -> sizeof == 1");
static_assert(!has_padding<T>(), "source type may have padding");
return {reinterpret_cast<const std::uint8_t*>(std::addressof(src)), sizeof(T)};
}
//! \return `span<std::uint8_t>` which represents the bytes at `&src`.
template<typename T>
span<std::uint8_t> as_mut_byte_span(T& src) noexcept
{
static_assert(!std::is_empty<T>(), "empty types will not work -> sizeof == 1");
static_assert(!has_padding<T>(), "source type may have padding");
return {reinterpret_cast<std::uint8_t*>(std::addressof(src)), sizeof(T)};
}
//! make a span from a std::string
template<typename T>
span<const T> strspan(const std::string &s) noexcept
{
static_assert(std::is_same<T, char>() || std::is_same<T, unsigned char>() || std::is_same<T, int8_t>() || std::is_same<T, uint8_t>(), "Unexpected type");
return {reinterpret_cast<const T*>(s.data()), s.size()};
}
}

View File

@@ -81,7 +81,7 @@ Examples
.. code:: c++
#include <fmt/core.h>
int main() {
fmt::print("Hello, world!\n");
}
@@ -293,11 +293,11 @@ Projects using this library
An open-source library for mathematical programming
* `Aseprite <https://github.com/aseprite/aseprite>`_:
Animated sprite editor & pixel art tool
Animated sprite editor & pixel art tool
* `AvioBook <https://www.aviobook.aero/en>`_: A comprehensive aircraft
operations suite
* `Celestia <https://celestia.space/>`_: Real-time 3D visualization of space
* `Ceph <https://ceph.com/>`_: A scalable distributed storage system
@@ -351,7 +351,7 @@ Projects using this library
* `quasardb <https://www.quasardb.net/>`_: A distributed, high-performance,
associative database
* `Quill <https://github.com/odygrd/quill>`_: Asynchronous low-latency logging library
* `QKW <https://github.com/ravijanjam/qkw>`_: Generalizing aliasing to simplify

View File

@@ -1754,7 +1754,7 @@ inline bool divisible_by_power_of_2(uint64_t x, int exp) FMT_NOEXCEPT {
#ifdef FMT_BUILTIN_CTZLL
return FMT_BUILTIN_CTZLL(x) >= exp;
#else
return exp < num_bits<uint64_t>()) && x == ((x >> exp) << exp);
return (exp < num_bits<uint64_t>()) && x == ((x >> exp) << exp);
#endif
}

View File

@@ -5,7 +5,7 @@
//
// For the license information refer to format.h.
#include "3rdparty/fmt/format-inl.h"
#include "fmt/format-inl.h"
FMT_BEGIN_NAMESPACE
namespace detail {

View File

@@ -3,9 +3,9 @@
* DISCLAIMER
* This file is part of the mingw-w64 runtime package.
*
* The mingw-w64 runtime package and its code is distributed in the hope that it
* will be useful but WITHOUT ANY WARRANTY. ALL WARRANTIES, EXPRESSED OR
* IMPLIED ARE HEREBY DISCLAIMED. This includes but is not limited to
* The mingw-w64 runtime package and its code is distributed in the hope that it
* will be useful but WITHOUT ANY WARRANTY. ALL WARRANTIES, EXPRESSED OR
* IMPLIED ARE HEREBY DISCLAIMED. This includes but is not limited to
* warranties of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
*/
/*
@@ -109,11 +109,7 @@ char *optarg; /* argument associated with option */
extern char __declspec(dllimport) *__progname;
#endif
#ifdef __CYGWIN__
static char EMSG[] = "";
#else
#define EMSG ""
#endif
static int getopt_internal(int, char * const *, const char *,
const struct option *, int *, int);

View File

@@ -1,68 +0,0 @@
# Authors ordered by first contribution.
Ryan Dahl <ry@tinyclouds.org>
Jeremy Hinegardner <jeremy@hinegardner.org>
Sergey Shepelev <temotor@gmail.com>
Joe Damato <ice799@gmail.com>
tomika <tomika_nospam@freemail.hu>
Phoenix Sol <phoenix@burninglabs.com>
Cliff Frey <cliff@meraki.com>
Ewen Cheslack-Postava <ewencp@cs.stanford.edu>
Santiago Gala <sgala@apache.org>
Tim Becker <tim.becker@syngenio.de>
Jeff Terrace <jterrace@gmail.com>
Ben Noordhuis <info@bnoordhuis.nl>
Nathan Rajlich <nathan@tootallnate.net>
Mark Nottingham <mnot@mnot.net>
Aman Gupta <aman@tmm1.net>
Tim Becker <tim.becker@kuriositaet.de>
Sean Cunningham <sean.cunningham@mandiant.com>
Peter Griess <pg@std.in>
Salman Haq <salman.haq@asti-usa.com>
Cliff Frey <clifffrey@gmail.com>
Jon Kolb <jon@b0g.us>
Fouad Mardini <f.mardini@gmail.com>
Paul Querna <pquerna@apache.org>
Felix Geisendörfer <felix@debuggable.com>
koichik <koichik@improvement.jp>
Andre Caron <andre.l.caron@gmail.com>
Ivo Raisr <ivosh@ivosh.net>
James McLaughlin <jamie@lacewing-project.org>
David Gwynne <loki@animata.net>
Thomas LE ROUX <thomas@november-eleven.fr>
Randy Rizun <rrizun@ortivawireless.com>
Andre Louis Caron <andre.louis.caron@usherbrooke.ca>
Simon Zimmermann <simonz05@gmail.com>
Erik Dubbelboer <erik@dubbelboer.com>
Martell Malone <martellmalone@gmail.com>
Bertrand Paquet <bpaquet@octo.com>
BogDan Vatra <bogdan@kde.org>
Peter Faiman <peter@thepicard.org>
Corey Richardson <corey@octayn.net>
Tóth Tamás <tomika_nospam@freemail.hu>
Cam Swords <cam.swords@gmail.com>
Chris Dickinson <christopher.s.dickinson@gmail.com>
Uli Köhler <ukoehler@btronik.de>
Charlie Somerville <charlie@charliesomerville.com>
Patrik Stutz <patrik.stutz@gmail.com>
Fedor Indutny <fedor.indutny@gmail.com>
runner <runner.mei@gmail.com>
Alexis Campailla <alexis@janeasystems.com>
David Wragg <david@wragg.org>
Vinnie Falco <vinnie.falco@gmail.com>
Alex Butum <alexbutum@linux.com>
Rex Feng <rexfeng@gmail.com>
Alex Kocharin <alex@kocharin.ru>
Mark Koopman <markmontymark@yahoo.com>
Helge Heß <me@helgehess.eu>
Alexis La Goutte <alexis.lagoutte@gmail.com>
George Miroshnykov <george.miroshnykov@gmail.com>
Maciej Małecki <me@mmalecki.com>
Marc O'Morain <github.com@marcomorain.com>
Jeff Pinner <jpinner@twitter.com>
Timothy J Fontaine <tjfontaine@gmail.com>
Akagi201 <akagi201@gmail.com>
Romain Giraud <giraud.romain@gmail.com>
Jay Satiro <raysatiro@yahoo.com>
Arne Steen <Arne.Steen@gmx.de>
Kjell Schubert <kjell.schubert@gmail.com>
Olivier Mengué <dolmen@cpan.org>

View File

@@ -1,19 +0,0 @@
Copyright Joyent, Inc. and other Node contributors.
Permission is hereby granted, free of charge, to any person obtaining a copy
of this software and associated documentation files (the "Software"), to
deal in the Software without restriction, including without limitation the
rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
sell copies of the Software, and to permit persons to whom the Software is
furnished to do so, subject to the following conditions:
The above copyright notice and this permission notice shall be included in
all copies or substantial portions of the Software.
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
IN THE SOFTWARE.

View File

@@ -1,246 +0,0 @@
HTTP Parser
===========
[![Build Status](https://api.travis-ci.org/nodejs/http-parser.svg?branch=master)](https://travis-ci.org/nodejs/http-parser)
This is a parser for HTTP messages written in C. It parses both requests and
responses. The parser is designed to be used in performance HTTP
applications. It does not make any syscalls nor allocations, it does not
buffer data, it can be interrupted at anytime. Depending on your
architecture, it only requires about 40 bytes of data per message
stream (in a web server that is per connection).
Features:
* No dependencies
* Handles persistent streams (keep-alive).
* Decodes chunked encoding.
* Upgrade support
* Defends against buffer overflow attacks.
The parser extracts the following information from HTTP messages:
* Header fields and values
* Content-Length
* Request method
* Response status code
* Transfer-Encoding
* HTTP version
* Request URL
* Message body
Usage
-----
One `http_parser` object is used per TCP connection. Initialize the struct
using `http_parser_init()` and set the callbacks. That might look something
like this for a request parser:
```c
http_parser_settings settings;
settings.on_url = my_url_callback;
settings.on_header_field = my_header_field_callback;
/* ... */
http_parser *parser = malloc(sizeof(http_parser));
http_parser_init(parser, HTTP_REQUEST);
parser->data = my_socket;
```
When data is received on the socket execute the parser and check for errors.
```c
size_t len = 80*1024, nparsed;
char buf[len];
ssize_t recved;
recved = recv(fd, buf, len, 0);
if (recved < 0) {
/* Handle error. */
}
/* Start up / continue the parser.
* Note we pass recved==0 to signal that EOF has been received.
*/
nparsed = http_parser_execute(parser, &settings, buf, recved);
if (parser->upgrade) {
/* handle new protocol */
} else if (nparsed != recved) {
/* Handle error. Usually just close the connection. */
}
```
`http_parser` needs to know where the end of the stream is. For example, sometimes
servers send responses without Content-Length and expect the client to
consume input (for the body) until EOF. To tell `http_parser` about EOF, give
`0` as the fourth parameter to `http_parser_execute()`. Callbacks and errors
can still be encountered during an EOF, so one must still be prepared
to receive them.
Scalar valued message information such as `status_code`, `method`, and the
HTTP version are stored in the parser structure. This data is only
temporally stored in `http_parser` and gets reset on each new message. If
this information is needed later, copy it out of the structure during the
`headers_complete` callback.
The parser decodes the transfer-encoding for both requests and responses
transparently. That is, a chunked encoding is decoded before being sent to
the on_body callback.
The Special Problem of Upgrade
------------------------------
`http_parser` supports upgrading the connection to a different protocol. An
increasingly common example of this is the WebSocket protocol which sends
a request like
GET /demo HTTP/1.1
Upgrade: WebSocket
Connection: Upgrade
Host: example.com
Origin: http://example.com
WebSocket-Protocol: sample
followed by non-HTTP data.
(See [RFC6455](https://tools.ietf.org/html/rfc6455) for more information the
WebSocket protocol.)
To support this, the parser will treat this as a normal HTTP message without a
body, issuing both on_headers_complete and on_message_complete callbacks. However
http_parser_execute() will stop parsing at the end of the headers and return.
The user is expected to check if `parser->upgrade` has been set to 1 after
`http_parser_execute()` returns. Non-HTTP data begins at the buffer supplied
offset by the return value of `http_parser_execute()`.
Callbacks
---------
During the `http_parser_execute()` call, the callbacks set in
`http_parser_settings` will be executed. The parser maintains state and
never looks behind, so buffering the data is not necessary. If you need to
save certain data for later usage, you can do that from the callbacks.
There are two types of callbacks:
* notification `typedef int (*http_cb) (http_parser*);`
Callbacks: on_message_begin, on_headers_complete, on_message_complete.
* data `typedef int (*http_data_cb) (http_parser*, const char *at, size_t length);`
Callbacks: (requests only) on_url,
(common) on_header_field, on_header_value, on_body;
Callbacks must return 0 on success. Returning a non-zero value indicates
error to the parser, making it exit immediately.
For cases where it is necessary to pass local information to/from a callback,
the `http_parser` object's `data` field can be used.
An example of such a case is when using threads to handle a socket connection,
parse a request, and then give a response over that socket. By instantiation
of a thread-local struct containing relevant data (e.g. accepted socket,
allocated memory for callbacks to write into, etc), a parser's callbacks are
able to communicate data between the scope of the thread and the scope of the
callback in a threadsafe manner. This allows `http_parser` to be used in
multi-threaded contexts.
Example:
```c
typedef struct {
socket_t sock;
void* buffer;
int buf_len;
} custom_data_t;
int my_url_callback(http_parser* parser, const char *at, size_t length) {
/* access to thread local custom_data_t struct.
Use this access save parsed data for later use into thread local
buffer, or communicate over socket
*/
parser->data;
...
return 0;
}
...
void http_parser_thread(socket_t sock) {
int nparsed = 0;
/* allocate memory for user data */
custom_data_t *my_data = malloc(sizeof(custom_data_t));
/* some information for use by callbacks.
* achieves thread -> callback information flow */
my_data->sock = sock;
/* instantiate a thread-local parser */
http_parser *parser = malloc(sizeof(http_parser));
http_parser_init(parser, HTTP_REQUEST); /* initialise parser */
/* this custom data reference is accessible through the reference to the
parser supplied to callback functions */
parser->data = my_data;
http_parser_settings settings; /* set up callbacks */
settings.on_url = my_url_callback;
/* execute parser */
nparsed = http_parser_execute(parser, &settings, buf, recved);
...
/* parsed information copied from callback.
can now perform action on data copied into thread-local memory from callbacks.
achieves callback -> thread information flow */
my_data->buffer;
...
}
```
In case you parse HTTP message in chunks (i.e. `read()` request line
from socket, parse, read half headers, parse, etc) your data callbacks
may be called more than once. `http_parser` guarantees that data pointer is only
valid for the lifetime of callback. You can also `read()` into a heap allocated
buffer to avoid copying memory around if this fits your application.
Reading headers may be a tricky task if you read/parse headers partially.
Basically, you need to remember whether last header callback was field or value
and apply the following logic:
(on_header_field and on_header_value shortened to on_h_*)
------------------------ ------------ --------------------------------------------
| State (prev. callback) | Callback | Description/action |
------------------------ ------------ --------------------------------------------
| nothing (first call) | on_h_field | Allocate new buffer and copy callback data |
| | | into it |
------------------------ ------------ --------------------------------------------
| value | on_h_field | New header started. |
| | | Copy current name,value buffers to headers |
| | | list and allocate new buffer for new name |
------------------------ ------------ --------------------------------------------
| field | on_h_field | Previous name continues. Reallocate name |
| | | buffer and append callback data to it |
------------------------ ------------ --------------------------------------------
| field | on_h_value | Value for current header started. Allocate |
| | | new buffer and copy callback data to it |
------------------------ ------------ --------------------------------------------
| value | on_h_value | Value continues. Reallocate value buffer |
| | | and append callback data to it |
------------------------ ------------ --------------------------------------------
Parsing URLs
------------
A simplistic zero-copy URL parser is provided as `http_parser_parse_url()`.
Users of this library may wish to use it to parse URLs constructed from
consecutive `on_url` callbacks.
See examples of reading in headers:
* [partial example](http://gist.github.com/155877) in C
* [from http-parser tests](http://github.com/joyent/http-parser/blob/37a0ff8/test.c#L403) in C
* [from Node library](http://github.com/joyent/node/blob/842eaf4/src/http.js#L284) in Javascript

File diff suppressed because it is too large Load Diff

View File

@@ -1,442 +0,0 @@
/* Copyright Joyent, Inc. and other Node contributors. All rights reserved.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
* IN THE SOFTWARE.
*/
#ifndef http_parser_h
#define http_parser_h
#ifdef __cplusplus
extern "C" {
#endif
/* Also update SONAME in the Makefile whenever you change these. */
#define HTTP_PARSER_VERSION_MAJOR 2
#define HTTP_PARSER_VERSION_MINOR 9
#define HTTP_PARSER_VERSION_PATCH 3
#include <stddef.h>
#if defined(_WIN32) && !defined(__MINGW32__) && \
(!defined(_MSC_VER) || _MSC_VER<1600) && !defined(__WINE__)
#include <BaseTsd.h>
typedef __int8 int8_t;
typedef unsigned __int8 uint8_t;
typedef __int16 int16_t;
typedef unsigned __int16 uint16_t;
typedef __int32 int32_t;
typedef unsigned __int32 uint32_t;
typedef __int64 int64_t;
typedef unsigned __int64 uint64_t;
#else
#include <stdint.h>
#endif
/* Compile with -DHTTP_PARSER_STRICT=0 to make less checks, but run
* faster
*/
#ifndef HTTP_PARSER_STRICT
# define HTTP_PARSER_STRICT 1
#endif
/* Maximium header size allowed. If the macro is not defined
* before including this header then the default is used. To
* change the maximum header size, define the macro in the build
* environment (e.g. -DHTTP_MAX_HEADER_SIZE=<value>). To remove
* the effective limit on the size of the header, define the macro
* to a very large number (e.g. -DHTTP_MAX_HEADER_SIZE=0x7fffffff)
*/
#ifndef HTTP_MAX_HEADER_SIZE
# define HTTP_MAX_HEADER_SIZE (80*1024)
#endif
typedef struct http_parser http_parser;
typedef struct http_parser_settings http_parser_settings;
/* Callbacks should return non-zero to indicate an error. The parser will
* then halt execution.
*
* The one exception is on_headers_complete. In a HTTP_RESPONSE parser
* returning '1' from on_headers_complete will tell the parser that it
* should not expect a body. This is used when receiving a response to a
* HEAD request which may contain 'Content-Length' or 'Transfer-Encoding:
* chunked' headers that indicate the presence of a body.
*
* Returning `2` from on_headers_complete will tell parser that it should not
* expect neither a body nor any futher responses on this connection. This is
* useful for handling responses to a CONNECT request which may not contain
* `Upgrade` or `Connection: upgrade` headers.
*
* http_data_cb does not return data chunks. It will be called arbitrarily
* many times for each string. E.G. you might get 10 callbacks for "on_url"
* each providing just a few characters more data.
*/
typedef int (*http_data_cb) (http_parser*, const char *at, size_t length);
typedef int (*http_cb) (http_parser*);
/* Status Codes */
#define HTTP_STATUS_MAP(XX) \
XX(100, CONTINUE, Continue) \
XX(101, SWITCHING_PROTOCOLS, Switching Protocols) \
XX(102, PROCESSING, Processing) \
XX(200, OK, OK) \
XX(201, CREATED, Created) \
XX(202, ACCEPTED, Accepted) \
XX(203, NON_AUTHORITATIVE_INFORMATION, Non-Authoritative Information) \
XX(204, NO_CONTENT, No Content) \
XX(205, RESET_CONTENT, Reset Content) \
XX(206, PARTIAL_CONTENT, Partial Content) \
XX(207, MULTI_STATUS, Multi-Status) \
XX(208, ALREADY_REPORTED, Already Reported) \
XX(226, IM_USED, IM Used) \
XX(300, MULTIPLE_CHOICES, Multiple Choices) \
XX(301, MOVED_PERMANENTLY, Moved Permanently) \
XX(302, FOUND, Found) \
XX(303, SEE_OTHER, See Other) \
XX(304, NOT_MODIFIED, Not Modified) \
XX(305, USE_PROXY, Use Proxy) \
XX(307, TEMPORARY_REDIRECT, Temporary Redirect) \
XX(308, PERMANENT_REDIRECT, Permanent Redirect) \
XX(400, BAD_REQUEST, Bad Request) \
XX(401, UNAUTHORIZED, Unauthorized) \
XX(402, PAYMENT_REQUIRED, Payment Required) \
XX(403, FORBIDDEN, Forbidden) \
XX(404, NOT_FOUND, Not Found) \
XX(405, METHOD_NOT_ALLOWED, Method Not Allowed) \
XX(406, NOT_ACCEPTABLE, Not Acceptable) \
XX(407, PROXY_AUTHENTICATION_REQUIRED, Proxy Authentication Required) \
XX(408, REQUEST_TIMEOUT, Request Timeout) \
XX(409, CONFLICT, Conflict) \
XX(410, GONE, Gone) \
XX(411, LENGTH_REQUIRED, Length Required) \
XX(412, PRECONDITION_FAILED, Precondition Failed) \
XX(413, PAYLOAD_TOO_LARGE, Payload Too Large) \
XX(414, URI_TOO_LONG, URI Too Long) \
XX(415, UNSUPPORTED_MEDIA_TYPE, Unsupported Media Type) \
XX(416, RANGE_NOT_SATISFIABLE, Range Not Satisfiable) \
XX(417, EXPECTATION_FAILED, Expectation Failed) \
XX(421, MISDIRECTED_REQUEST, Misdirected Request) \
XX(422, UNPROCESSABLE_ENTITY, Unprocessable Entity) \
XX(423, LOCKED, Locked) \
XX(424, FAILED_DEPENDENCY, Failed Dependency) \
XX(426, UPGRADE_REQUIRED, Upgrade Required) \
XX(428, PRECONDITION_REQUIRED, Precondition Required) \
XX(429, TOO_MANY_REQUESTS, Too Many Requests) \
XX(431, REQUEST_HEADER_FIELDS_TOO_LARGE, Request Header Fields Too Large) \
XX(451, UNAVAILABLE_FOR_LEGAL_REASONS, Unavailable For Legal Reasons) \
XX(500, INTERNAL_SERVER_ERROR, Internal Server Error) \
XX(501, NOT_IMPLEMENTED, Not Implemented) \
XX(502, BAD_GATEWAY, Bad Gateway) \
XX(503, SERVICE_UNAVAILABLE, Service Unavailable) \
XX(504, GATEWAY_TIMEOUT, Gateway Timeout) \
XX(505, HTTP_VERSION_NOT_SUPPORTED, HTTP Version Not Supported) \
XX(506, VARIANT_ALSO_NEGOTIATES, Variant Also Negotiates) \
XX(507, INSUFFICIENT_STORAGE, Insufficient Storage) \
XX(508, LOOP_DETECTED, Loop Detected) \
XX(510, NOT_EXTENDED, Not Extended) \
XX(511, NETWORK_AUTHENTICATION_REQUIRED, Network Authentication Required) \
enum http_status
{
#define XX(num, name, string) HTTP_STATUS_##name = num,
HTTP_STATUS_MAP(XX)
#undef XX
};
/* Request Methods */
#define HTTP_METHOD_MAP(XX) \
XX(0, DELETE, DELETE) \
XX(1, GET, GET) \
XX(2, HEAD, HEAD) \
XX(3, POST, POST) \
XX(4, PUT, PUT) \
/* pathological */ \
XX(5, CONNECT, CONNECT) \
XX(6, OPTIONS, OPTIONS) \
XX(7, TRACE, TRACE) \
/* WebDAV */ \
XX(8, COPY, COPY) \
XX(9, LOCK, LOCK) \
XX(10, MKCOL, MKCOL) \
XX(11, MOVE, MOVE) \
XX(12, PROPFIND, PROPFIND) \
XX(13, PROPPATCH, PROPPATCH) \
XX(14, SEARCH, SEARCH) \
XX(15, UNLOCK, UNLOCK) \
XX(16, BIND, BIND) \
XX(17, REBIND, REBIND) \
XX(18, UNBIND, UNBIND) \
XX(19, ACL, ACL) \
/* subversion */ \
XX(20, REPORT, REPORT) \
XX(21, MKACTIVITY, MKACTIVITY) \
XX(22, CHECKOUT, CHECKOUT) \
XX(23, MERGE, MERGE) \
/* upnp */ \
XX(24, MSEARCH, M-SEARCH) \
XX(25, NOTIFY, NOTIFY) \
XX(26, SUBSCRIBE, SUBSCRIBE) \
XX(27, UNSUBSCRIBE, UNSUBSCRIBE) \
/* RFC-5789 */ \
XX(28, PATCH, PATCH) \
XX(29, PURGE, PURGE) \
/* CalDAV */ \
XX(30, MKCALENDAR, MKCALENDAR) \
/* RFC-2068, section 19.6.1.2 */ \
XX(31, LINK, LINK) \
XX(32, UNLINK, UNLINK) \
/* icecast */ \
XX(33, SOURCE, SOURCE) \
enum http_method
{
#define XX(num, name, string) HTTP_##name = num,
HTTP_METHOD_MAP(XX)
#undef XX
};
enum http_parser_type { HTTP_REQUEST, HTTP_RESPONSE, HTTP_BOTH };
/* Flag values for http_parser.flags field */
enum flags
{ F_CHUNKED = 1 << 0
, F_CONNECTION_KEEP_ALIVE = 1 << 1
, F_CONNECTION_CLOSE = 1 << 2
, F_CONNECTION_UPGRADE = 1 << 3
, F_TRAILING = 1 << 4
, F_UPGRADE = 1 << 5
, F_SKIPBODY = 1 << 6
, F_CONTENTLENGTH = 1 << 7
, F_TRANSFER_ENCODING = 1 << 8
};
/* Map for errno-related constants
*
* The provided argument should be a macro that takes 2 arguments.
*/
#define HTTP_ERRNO_MAP(XX) \
/* No error */ \
XX(OK, "success") \
\
/* Callback-related errors */ \
XX(CB_message_begin, "the on_message_begin callback failed") \
XX(CB_url, "the on_url callback failed") \
XX(CB_header_field, "the on_header_field callback failed") \
XX(CB_header_value, "the on_header_value callback failed") \
XX(CB_headers_complete, "the on_headers_complete callback failed") \
XX(CB_body, "the on_body callback failed") \
XX(CB_message_complete, "the on_message_complete callback failed") \
XX(CB_status, "the on_status callback failed") \
XX(CB_chunk_header, "the on_chunk_header callback failed") \
XX(CB_chunk_complete, "the on_chunk_complete callback failed") \
\
/* Parsing-related errors */ \
XX(INVALID_EOF_STATE, "stream ended at an unexpected time") \
XX(HEADER_OVERFLOW, \
"too many header bytes seen; overflow detected") \
XX(CLOSED_CONNECTION, \
"data received after completed connection: close message") \
XX(INVALID_VERSION, "invalid HTTP version") \
XX(INVALID_STATUS, "invalid HTTP status code") \
XX(INVALID_METHOD, "invalid HTTP method") \
XX(INVALID_URL, "invalid URL") \
XX(INVALID_HOST, "invalid host") \
XX(INVALID_PORT, "invalid port") \
XX(INVALID_PATH, "invalid path") \
XX(INVALID_QUERY_STRING, "invalid query string") \
XX(INVALID_FRAGMENT, "invalid fragment") \
XX(LF_EXPECTED, "LF character expected") \
XX(INVALID_HEADER_TOKEN, "invalid character in header") \
XX(INVALID_CONTENT_LENGTH, \
"invalid character in content-length header") \
XX(UNEXPECTED_CONTENT_LENGTH, \
"unexpected content-length header") \
XX(INVALID_CHUNK_SIZE, \
"invalid character in chunk size header") \
XX(INVALID_TRANSFER_ENCODING, \
"request has invalid transfer-encoding") \
XX(INVALID_CONSTANT, "invalid constant string") \
XX(INVALID_INTERNAL_STATE, "encountered unexpected internal state")\
XX(STRICT, "strict mode assertion failed") \
XX(PAUSED, "parser is paused") \
XX(UNKNOWN, "an unknown error occurred")
/* Define HPE_* values for each errno value above */
#define HTTP_ERRNO_GEN(n, s) HPE_##n,
enum http_errno {
HTTP_ERRNO_MAP(HTTP_ERRNO_GEN)
};
#undef HTTP_ERRNO_GEN
/* Get an http_errno value from an http_parser */
#define HTTP_PARSER_ERRNO(p) ((enum http_errno) (p)->http_errno)
struct http_parser {
/** PRIVATE **/
unsigned int type : 2; /* enum http_parser_type */
unsigned int state : 7; /* enum state from http_parser.c */
unsigned int header_state : 7; /* enum header_state from http_parser.c */
unsigned int index : 7; /* index into current matcher */
unsigned int lenient_http_headers : 1;
unsigned int flags : 16; /* F_* values from 'flags' enum; semi-public */
uint32_t nread; /* # bytes read in various scenarios */
uint64_t content_length; /* # bytes in body (0 if no Content-Length header) */
/** READ-ONLY **/
unsigned short http_major;
unsigned short http_minor;
unsigned int status_code : 16; /* responses only */
unsigned int method : 8; /* requests only */
unsigned int http_errno : 7;
/* 1 = Upgrade header was present and the parser has exited because of that.
* 0 = No upgrade header present.
* Should be checked when http_parser_execute() returns in addition to
* error checking.
*/
unsigned int upgrade : 1;
/** PUBLIC **/
void *data; /* A pointer to get hook to the "connection" or "socket" object */
};
struct http_parser_settings {
http_cb on_message_begin;
http_data_cb on_url;
http_data_cb on_status;
http_data_cb on_header_field;
http_data_cb on_header_value;
http_cb on_headers_complete;
http_data_cb on_body;
http_cb on_message_complete;
/* When on_chunk_header is called, the current chunk length is stored
* in parser->content_length.
*/
http_cb on_chunk_header;
http_cb on_chunk_complete;
};
enum http_parser_url_fields
{ UF_SCHEMA = 0
, UF_HOST = 1
, UF_PORT = 2
, UF_PATH = 3
, UF_QUERY = 4
, UF_FRAGMENT = 5
, UF_USERINFO = 6
, UF_MAX = 7
};
/* Result structure for http_parser_parse_url().
*
* Callers should index into field_data[] with UF_* values iff field_set
* has the relevant (1 << UF_*) bit set. As a courtesy to clients (and
* because we probably have padding left over), we convert any port to
* a uint16_t.
*/
struct http_parser_url {
uint16_t field_set; /* Bitmask of (1 << UF_*) values */
uint16_t port; /* Converted UF_PORT string */
struct {
uint16_t off; /* Offset into buffer in which field starts */
uint16_t len; /* Length of run in buffer */
} field_data[UF_MAX];
};
/* Returns the library version. Bits 16-23 contain the major version number,
* bits 8-15 the minor version number and bits 0-7 the patch level.
* Usage example:
*
* unsigned long version = http_parser_version();
* unsigned major = (version >> 16) & 255;
* unsigned minor = (version >> 8) & 255;
* unsigned patch = version & 255;
* printf("http_parser v%u.%u.%u\n", major, minor, patch);
*/
unsigned long http_parser_version(void);
void http_parser_init(http_parser *parser, enum http_parser_type type);
/* Initialize http_parser_settings members to 0
*/
void http_parser_settings_init(http_parser_settings *settings);
/* Executes the parser. Returns number of parsed bytes. Sets
* `parser->http_errno` on error. */
size_t http_parser_execute(http_parser *parser,
const http_parser_settings *settings,
const char *data,
size_t len);
/* If http_should_keep_alive() in the on_headers_complete or
* on_message_complete callback returns 0, then this should be
* the last message on the connection.
* If you are the server, respond with the "Connection: close" header.
* If you are the client, close the connection.
*/
int http_should_keep_alive(const http_parser *parser);
/* Returns a string version of the HTTP method. */
const char *http_method_str(enum http_method m);
/* Returns a string version of the HTTP status code. */
const char *http_status_str(enum http_status s);
/* Return a string name of the given error */
const char *http_errno_name(enum http_errno err);
/* Return a string description of the given error */
const char *http_errno_description(enum http_errno err);
/* Initialize all http_parser_url members to 0 */
void http_parser_url_init(struct http_parser_url *u);
/* Parse a URL; return nonzero on failure */
int http_parser_parse_url(const char *buf, size_t buflen,
int is_connect,
struct http_parser_url *u);
/* Pause or un-pause the parser; a nonzero value pauses */
void http_parser_pause(http_parser *parser, int paused);
/* Checks if this is the final chunk of the body. */
int http_body_is_final(const http_parser *parser);
/* Change the maximum header size provided at compile time. */
void http_parser_set_max_header_size(uint32_t size);
#ifdef __cplusplus
}
#endif
#endif

View File

@@ -1,4 +1,4 @@
cmake_minimum_required (VERSION 2.8)
cmake_minimum_required(VERSION 3.1)
project (hwloc C)
include_directories(include)
@@ -13,23 +13,25 @@ set(HEADERS
)
set(SOURCES
src/base64.c
src/bind.c
src/bitmap.c
src/components.c
src/diff.c
src/distances.c
src/misc.c
src/pci-common.c
src/shmem.c
src/topology.c
src/topology-noos.c
src/topology-synthetic.c
src/topology-windows.c
src/topology-x86.c
src/topology-xml.c
src/topology-xml-nolibxml.c
src/base64.c
src/bind.c
src/bitmap.c
src/components.c
src/diff.c
src/distances.c
src/misc.c
src/pci-common.c
src/shmem.c
src/topology.c
src/topology-noos.c
src/topology-synthetic.c
src/topology-windows.c
src/topology-x86.c
src/topology-xml.c
src/topology-xml-nolibxml.c
src/traversal.c
src/memattrs.c
src/cpukinds.c
)
add_library(hwloc STATIC

View File

@@ -1,7 +1,8 @@
Copyright © 2009 CNRS
Copyright © 2009-2020 Inria. All rights reserved.
Copyright © 2009-2022 Inria. All rights reserved.
Copyright © 2009-2013 Université Bordeaux
Copyright © 2009-2011 Cisco Systems, Inc. All rights reserved.
Copyright © 2020 Hewlett Packard Enterprise. All rights reserved.
$COPYRIGHT$
@@ -16,6 +17,272 @@ bug fixes (and other actions) for each version of hwloc since version
0.9.
Version 2.9.0
-------------
* Backends
+ Expose the memory size of CXL memory devices (Type 3) on Linux.
+ The LevelZero backend now reports the "XeLinkBandwidth" distance
matrix between L0 devices (and subdevices) when available.
+ Add support for CUDA compute capability up to 9.0.
* Tools
+ lstopo now switches to console mode when its output is redirected.
Graphical window mode may be forced back with --of window.
+ hwloc-calc now accepts "numa" in -H, and I/O subtypes such as "gpu"
in -I and -N.
Version 2.8.0
-------------
* API
+ Add HWLOC_TOPOLOGY_FLAG_NO_DISTANCES, _NO_MEMATTRS and _NO_CPUKINDS
to reduce the overhead when unneeded.
+ Add separate Read/Write Bandwidth/Latency memory attributes and
implement them on Linux.
* Backends
+ NUMA nodes may now have a subtype such as DRAM, HBM, SPM, or NVM
on heterogeneous memory platforms on Linux.
- Add DAXType and DAXParent attributes on Linux to tell where a
DAX device or its corresponding NUMA node come from (SPM for
Specific-Purpose or NVM for Non-Volatile Memory).
+ Detect heterogeneous caches in hybrid CPUs on MacOS X,
thanks to Paul Bone for the help.
+ Max frequencies are not ignored in Linux cpukinds anymore (they were
ignored in hwloc 2.7.0), but they may be slightly adjusted to avoid
reporting hybrid CPUs because Intel Turbo Boost Max 3.0.
- See the documentation of environment variable HWLOC_CPUKINDS_MAXFREQ.
+ Hardwire the PCI locality of HPE Cray EX235a nodes.
* Tools
+ lstopo and other tools may now load Linux and x86 cpuid topology files
from a tarball.
+ lstopo may now replace the P# and L# index prefixes with custom strings
thanks to --os-index-prefix and --logical-index-prefix options.
* Misc
+ Add --disable-readme to avoid regenerating the top-level hwloc README
file from the documentation.
Version 2.7.1
-------------
* Workaround crashes when virtual machines report incoherent x86 CPUID
information about numbers of cores and threads.
Thanks to Peter Bense for the report.
* Use setenv() instead of putenv() when trying to force enable oneAPI L0
support, to avoid issues with applications that touch the environment,
thanks to Josh Hursey for the patch.
* Add some warnings at the end of configure when GPU libraries are
missing on the system or their path is missing in the environment.
Version 2.7.0
-------------
* Backends
+ Add support for NUMA nodes and caches with more than 64 PUs across
multiple processor groups on Windows 11 and Windows Server 2022.
+ Group objects are not created for Windows processor groups anymore,
except if HWLOC_WINDOWS_PROCESSOR_GROUP_OBJS=1 in the environment.
+ Expose "Cluster" group objects on Linux kernel 5.16+ for CPUs
that share some internal cache or bus. This can be equivalent
to the L2 Cache level on some platforms (e.g. x86) or a specific
level between L2 and L3 on others (e.g. ARM Kungpeng 920).
Thanks to Jonathan Cameron for the help.
- HWLOC_DONT_MERGE_CLUSTER_GROUPS=1 may be set in the environment
to prevent these groups from being merged with identical caches, etc.
+ Improve the oneAPI LevelZero backend:
- Expose subdevices such as "ze0.1" inside root OS devices ("ze0")
when the hardware contains multiple subdevices.
- Add many new attributes to describe device type, and the
numbers of slices, subslices, execution units and threads.
- Expose the memory information as LevelZeroHBM/DDR/MemorySize infos.
+ Ignore the max frequencies of cores in Linux cpukinds when the
base frequencies are available (to avoid exposing hybrid CPUs
when Intel Turbo Boost Max 3.0 gives slightly different max
frequencies to CPU cores).
- May be reverted by setting HWLOC_CPUKINDS_MAXFREQ=1 in the environment.
* Tools
+ Add --grey and --palette options to switch lstopo to greyscale or
white-background-only graphics, or to tune individual colors.
* Build
+ Windows CMake builds now support non-MSVC compilers, detect several
features at build time, can build/run tests, etc.
Thanks to Michael Hirsch and Alexander Neumann .
Version 2.6.0
-------------
* Backends
+ Expose two cpukinds for energy-efficient cores (icestorm) and
high-performance cores (firestorm) on Apple M1 on Mac OS X.
+ Use sysfs CPU "capacity" to rank hybrid cores by efficiency
on Linux when available (mostly on recent ARM platforms for now).
+ Improve HWLOC_MEMBIND_BIND (without the STRICT flag) on Linux kernel
>= 5.15: If more than one node is given, the kernel may now use all
of them instead of only the first one before falling back to others.
+ Expose cache os_index when available on Linux, it may be needed
when using resctrl to configure cache partitioning, memory bandwidth
monitoring, etc.
+ Add a "XGMIHops" distances matrix in the RSMI backend for AMD GPU
interconnected through XGMI links.
+ Expose AMD GPU memory information (VRAM and GTT) in the RSMI backend.
+ Add OS devices such as "bxi0" for Atos/Bull BXI HCAs on Linux.
* Tools
+ lstopo has a better placement algorithm with respect to I/O
objects, see --children-order in the manpage for details.
+ hwloc-annotate may now change object subtypes and cache or memory
sizes.
* Build
+ Allow to specify the ROCm installation for building the RSMI backend:
- Use a custom installation path if specified with --with-rocm=<dir>.
- Use /opt/rocm-<version> if specified with --with-rocm-version=<version>
or the ROCM_VERSION environment variable.
- Try /opt/rocm if it exists.
- See "How do I enable ROCm SMI and select which version to use?"
in the FAQ for details.
+ Add a CMakeLists for Windows under contrib/windows-cmake/ .
* Documentation
+ Add FAQ entry "How do I create a custom heterogeneous and
asymmetric topology?"
Version 2.5.0
-------------
* API
+ Add hwloc/windows.h to query Windows processor groups.
+ Add hwloc_get_obj_with_same_locality() to convert between objects
with same locality, for instance NUMA nodes and Packages,
or OS devices within a PCI device.
+ Add hwloc_distances_transform() to modify distances structures.
- hwloc-annotate and lstopo have new distances-transform options.
+ hwloc_distances_add() is replaced with _add_create() followed by
_add_values() and _add_commit(). See hwloc/distances.h for details.
+ Add topology flags to mitigate binding modifications during
hwloc discovery, especially on Windows:
- HWLOC_TOPOLOGY_FLAG_RESTRICT_TO_CPUBINDING and _MEMBINDING
restrict discovery to PUs and NUMA nodes inside the binding.
- HWLOC_TOPOLOGY_FLAG_DONT_CHANGE_BINDING prevents from ever
changing the binding during discovery.
* Backends
+ Add a levelzero backend for oneAPI L0 devices, exposed as OS devices
of subtype "LevelZero" and name such as "ze0".
- Add hwloc/levelzero.h for interoperability between converting
between L0 API devices and hwloc cpusets or OS devices.
+ Expose NEC Vector Engine cards on Linux as OS devices of subtype
"VectorEngine" and name "ve0", etc.
Thanks to Anara Kozhokanova, Tim Cramer and Erich Focht for the help.
+ Add a NVLinkBandwidth distances structure between NVIDIA GPUs
(and POWER processor or NVSwitches) in the NVML backend,
and a XGMIBandwidth distances structure between AMD GPUs
in the RSMI backends.
- See "Topology Attributes: Distances, Memory Attributes and CPU Kinds"
in the documentation for details about these new distances.
+ Add support for NUMA node 0 being offline in Linux, thanks to Jirka Hladky.
* Build
+ Add --with-cuda-version=<version> or look at the CUDA_VERSION
environment variable to find the appropriate CUDA pkg-config files.
Thanks to Stephen Herbein for the suggestion.
- Also add --with-cuda=<dir> to specify the CUDA installation path
manually (and its NVML and OpenCL components).
Thanks to Andrea Bocci for the suggestion.
- See "How do I enable CUDA and select which CUDA version to use?"
in the FAQ for details.
* Tools
+ lstopo now has a --windows-processor-groups option on Windows.
+ hwloc-ps now has a --short-name option to avoid long/truncated
command path.
+ hwloc-ps now has a --single-ancestor option to return a single
(possibly too large) object where a process is bound.
+ hwloc-ps --pid-cmd may now query environment variables,
including MPI-specific variables to find out process ranks.
Version 2.4.1
-------------
* Fix AMD OpenCL device locality when PCI bus or device number >= 128.
Thanks to Edgar Leon for reporting the issue.
+ Applications using any of the following inline functions must
be recompiled to get the fix: hwloc_opencl_get_device_pci_busid()
hwloc_opencl_get_device_cpuset(), hwloc_opencl_get_device_osdev().
* Fix the ranking of cpukinds on non-Windows systems,
thanks to Ivan Kochin for the report.
* Fix the insertion of custom Groups after loading the topology,
thanks to Scott Hicks.
* Add support for CPU0 being offline in Linux, thanks to Garrett Clay.
* Fix missing x86 Package and Core objects FreeBSD/NetBSD.
Thanks to Thibault Payet and Yuri Victorovich for the report.
* Fix the import of very large distances with heterogeneous object types.
* Fix a memory leak in the Linux backend,
thanks to Perceval Anichini.
Version 2.4.0
-------------
* API
+ Add hwloc/cpukinds.h for reporting information about hybrid CPUs.
- Use Linux cpufreq frequencies to rank cores by efficiency.
- Use x86 CPUID hybrid leaf and future Linux kernels sysfs CPU type
files to identify Intel Atom and Core cores.
- Use the Windows native EfficiencyClass to separate kinds.
* Backends
+ Properly handle Linux kernel 5.10+ exposing ACPI HMAT information
with knowledge of Generic Initiators.
* Tools
+ lstopo has new --cpukinds and --no-cpukinds options for showing
CPU kinds or not in textual and graphical modes respectively.
+ hwloc-calc has a new --cpukind option for filtering PUs by kind.
+ hwloc-annotate has a new cpukind command for modifying CPU kinds.
* Misc
+ Fix hwloc_bitmap_nr_ulongs(), thanks to Norbert Eicker.
+ Add a documentation section about
"Topology Attributes: Distances, Memory Attributes and CPU Kinds".
+ Silence some spurious warnings in the OpenCL backend and when showing
process binding with lstopo --ps.
Version 2.3.0
-------------
* API
+ Add hwloc/memattrs.h for exposing latency/bandwidth information
between initiators (CPU sets for now) and target NUMA nodes,
typically on heterogeneous platforms.
- When available, bandwidths and latencies are read from the ACPI HMAT
table exposed by Linux kernel 5.2+.
- Attributes may also be customized to expose user-defined performance
information.
+ Add hwloc_get_local_numanode_objs() for listing NUMA nodes that are
local to some locality.
+ The new topology flag HWLOC_TOPOLOGY_FLAG_IMPORT_SUPPORT causes
support arrays to be loaded from XML exported with hwloc 2.3+.
- hwloc_topology_get_support() now returns an additional "misc"
array with feature "imported_support" set when support was imported.
+ Add hwloc_topology_refresh() to refresh internal caches after modifying
the topology and before consulting the topology in a multithread context.
* Backends
+ Add a ROCm SMI backend and a hwloc/rsmi.h helper file for getting
the locality of AMD GPUs, now exposed as "rsmi" OS devices.
Thanks to Mike Li.
+ Remove POWER device-tree-based topology on Linux,
(it was disabled by default since 2.1).
* Tools
+ Command-line options for specifying flags now understand comma-separated
lists of flag names (substrings).
+ hwloc-info and hwloc-calc have new --local-memory --local-memory-flags
and --best-memattr options for reporting local memory nodes and filtering
by memory attributes.
+ hwloc-bind has a new --best-memattr option for filtering by memory attributes
among the memory binding set.
+ Tools that have a --restrict option may now receive a nodeset or
some custom flags for restricting the topology.
+ lstopo now has a --thickness option for changing line thickness in the
graphical output.
+ Fix lstopo drawing when autoresizing on Windows 10.
+ Pressing the F5 key in lstopo X11 and Windows graphical/interactive outputs
now refreshes the display according to the current topology and binding.
+ Add a tikz lstopo graphical backend to generate picture easily included into
LaTeX documents. Thanks to Clement Foyer.
* Misc
+ The default installation path of the Bash completion file has changed to
${datadir}/bash-completion/completions/hwloc. Thanks to Tomasz Kłoczko.
Version 2.2.0
-------------
* API

View File

@@ -23,9 +23,9 @@ APIs are documented after these sections.
Installation
hwloc (http://www.open-mpi.org/projects/hwloc/) is available under the BSD
license. It is hosted as a sub-project of the overall Open MPI project (http://
www.open-mpi.org/). Note that hwloc does not require any functionality from
hwloc (https://www.open-mpi.org/projects/hwloc/) is available under the BSD
license. It is hosted as a sub-project of the overall Open MPI project (https:/
/www.open-mpi.org/). Note that hwloc does not require any functionality from
Open MPI -- it is a wholly separate (and much smaller!) project and code base.
It just happens to be hosted as part of the overall Open MPI project.
@@ -75,10 +75,10 @@ Bugs should be reported in the tracker (https://github.com/open-mpi/hwloc/
issues). Opening a new issue automatically displays lots of hints about how to
debug and report issues.
Questions may be sent to the users or developers mailing lists (http://
Questions may be sent to the users or developers mailing lists (https://
www.open-mpi.org/community/lists/hwloc.php).
There is also a #hwloc IRC channel on Freenode (irc.freenode.net).
There is also a #hwloc IRC channel on Libera Chat (irc.libera.chat).

View File

@@ -8,7 +8,7 @@
# Please update HWLOC_VERSION* in contrib/windows/hwloc_config.h too.
major=2
minor=2
minor=9
release=0
# greek is used for alpha or beta release tags. If it is non-empty,
@@ -22,7 +22,7 @@ greek=
# The date when this release was created
date="Mar 30, 2020"
date="Dec 14, 2022"
# If snapshot=1, then use the value from snapshot_version as the
# entire hwloc version (i.e., ignore major, minor, release, and
@@ -41,7 +41,7 @@ snapshot_version=${major}.${minor}.${release}${greek}-git
# 2. Version numbers are described in the Libtool current:revision:age
# format.
libhwloc_so_version=17:0:2
libhwloc_so_version=21:1:6
libnetloc_so_version=0:0:0
# Please also update the <TargetName> lines in contrib/windows/libhwloc.vcxproj

View File

@@ -1,8 +1,8 @@
/*
* Copyright © 2009 CNRS
* Copyright © 2009-2020 Inria. All rights reserved.
* Copyright © 2009-2022 Inria. All rights reserved.
* Copyright © 2009-2012 Université Bordeaux
* Copyright © 2009-2011 Cisco Systems, Inc. All rights reserved.
* Copyright © 2009-2020 Cisco Systems, Inc. All rights reserved.
* See COPYING in top-level directory.
*/
@@ -11,7 +11,7 @@
* ------------------------------------------------
* $tarball_directory/doc/doxygen-doc/
* or
* http://www.open-mpi.org/projects/hwloc/doc/
* https://www.open-mpi.org/projects/hwloc/doc/
*=====================================================================
*
* FAIR WARNING: Do NOT expect to be able to figure out all the
@@ -29,7 +29,7 @@
* THAT IS IN THE PDF/HTML THAT IS ***NOT*** IN hwloc.h!
*
* There are entire paragraph-length descriptions, discussions, and
* pretty prictures to explain subtle corner cases, provide concrete
* pretty pictures to explain subtle corner cases, provide concrete
* examples, etc.
*
* Please, go read the documentation. :-)
@@ -93,7 +93,7 @@ extern "C" {
* Two stable releases of the same series usually have the same ::HWLOC_API_VERSION
* even if their HWLOC_VERSION are different.
*/
#define HWLOC_API_VERSION 0x00020100
#define HWLOC_API_VERSION 0x00020800
/** \brief Indicate at runtime which hwloc API version was used at build time.
*
@@ -102,7 +102,7 @@ extern "C" {
HWLOC_DECLSPEC unsigned hwloc_get_api_version(void);
/** \brief Current component and plugin ABI version (see hwloc/plugins.h) */
#define HWLOC_COMPONENT_ABI 6
#define HWLOC_COMPONENT_ABI 7
/** @} */
@@ -196,7 +196,7 @@ typedef enum {
*/
HWLOC_OBJ_CORE, /**< \brief Core.
* A computation unit (may be shared by several
* logical processors).
* PUs, aka logical processors).
*/
HWLOC_OBJ_PU, /**< \brief Processing Unit, or (Logical) Processor.
* An execution unit (may share a core with some
@@ -257,22 +257,31 @@ typedef enum {
HWLOC_OBJ_BRIDGE, /**< \brief Bridge (filtered out by default).
* Any bridge (or PCI switch) that connects the host or an I/O bus,
* to another I/O bus.
* They are not added to the topology unless I/O discovery
* is enabled with hwloc_topology_set_flags().
*
* Bridges are not added to the topology unless their
* filtering is changed (see hwloc_topology_set_type_filter()
* and hwloc_topology_set_io_types_filter()).
*
* I/O objects are not listed in the main children list,
* but rather in the dedicated io children list.
* I/O objects have NULL CPU and node sets.
*/
HWLOC_OBJ_PCI_DEVICE, /**< \brief PCI device (filtered out by default).
* They are not added to the topology unless I/O discovery
* is enabled with hwloc_topology_set_flags().
*
* PCI devices are not added to the topology unless their
* filtering is changed (see hwloc_topology_set_type_filter()
* and hwloc_topology_set_io_types_filter()).
*
* I/O objects are not listed in the main children list,
* but rather in the dedicated io children list.
* I/O objects have NULL CPU and node sets.
*/
HWLOC_OBJ_OS_DEVICE, /**< \brief Operating system device (filtered out by default).
* They are not added to the topology unless I/O discovery
* is enabled with hwloc_topology_set_flags().
*
* OS devices are not added to the topology unless their
* filtering is changed (see hwloc_topology_set_type_filter()
* and hwloc_topology_set_io_types_filter()).
*
* I/O objects are not listed in the main children list,
* but rather in the dedicated io children list.
* I/O objects have NULL CPU and node sets.
@@ -282,6 +291,10 @@ typedef enum {
* Objects without particular meaning, that can e.g. be
* added by the application for its own use, or by hwloc
* for miscellaneous objects such as MemoryModule (DIMMs).
*
* They are not added to the topology unless their filtering
* is changed (see hwloc_topology_set_type_filter()).
*
* These objects are not listed in the main children list,
* but rather in the dedicated misc children list.
* Misc objects may only have Misc objects as children,
@@ -304,7 +317,6 @@ typedef enum {
HWLOC_OBJ_DIE, /**< \brief Die within a physical package.
* A subpart of the physical package, that contains multiple cores.
* \hideinitializer
*/
HWLOC_OBJ_TYPE_MAX /**< \private Sentinel value */
@@ -334,12 +346,12 @@ typedef enum hwloc_obj_osdev_type_e {
* For instance the "eth0" interface on Linux. */
HWLOC_OBJ_OSDEV_OPENFABRICS, /**< \brief Operating system openfabrics device.
* For instance the "mlx4_0" InfiniBand HCA,
* or "hfi1_0" Omni-Path interface on Linux. */
* "hfi1_0" Omni-Path interface,
* or "bxi0" Atos/Bull BXI HCA on Linux. */
HWLOC_OBJ_OSDEV_DMA, /**< \brief Operating system dma engine device.
* For instance the "dma0chan0" DMA channel on Linux. */
HWLOC_OBJ_OSDEV_COPROC /**< \brief Operating system co-processor device.
* For instance "mic0" for a Xeon Phi (MIC) on Linux,
* "opencl0d0" for a OpenCL device,
* For instance "opencl0d0" for a OpenCL device,
* "cuda0" for a CUDA device. */
} hwloc_obj_osdev_type_t;
@@ -505,14 +517,14 @@ struct hwloc_obj {
* objects).
*
* If the ::HWLOC_TOPOLOGY_FLAG_INCLUDE_DISALLOWED configuration flag is set,
* some of these CPUs may not be allowed for binding,
* some of these CPUs may be online but not allowed for binding,
* see hwloc_topology_get_allowed_cpuset().
*
* \note All objects have non-NULL CPU and node sets except Misc and I/O objects.
*
* \note Its value must not be changed, hwloc_bitmap_dup() must be used instead.
*/
hwloc_cpuset_t complete_cpuset; /**< \brief The complete CPU set of logical processors of this object,
hwloc_cpuset_t complete_cpuset; /**< \brief The complete CPU set of processors of this object,
*
* This may include not only the same as the cpuset field, but also some CPUs for
* which topology information is unknown or incomplete, some offlines CPUs, and
@@ -533,9 +545,11 @@ struct hwloc_obj {
* between this object and the NUMA node objects).
*
* In the end, these nodes are those that are close to the current object.
* Function hwloc_get_local_numanode_objs() may be used to list those NUMA
* nodes more precisely.
*
* If the ::HWLOC_TOPOLOGY_FLAG_INCLUDE_DISALLOWED configuration flag is set,
* some of these nodes may not be allowed for allocation,
* some of these nodes may be online but not allowed for allocation,
* see hwloc_topology_get_allowed_nodeset().
*
* If there are no NUMA nodes in the machine, all the memory is close to this
@@ -628,7 +642,7 @@ union hwloc_obj_attr_u {
unsigned char revision;
float linkspeed; /* in GB/s */
} pcidev;
/** \brief Bridge specific Object Attribues */
/** \brief Bridge specific Object Attributes */
struct hwloc_bridge_attr_s {
union {
struct hwloc_pcidev_attr_s pci;
@@ -957,7 +971,7 @@ HWLOC_DECLSPEC const char * hwloc_obj_type_string (hwloc_obj_type_t type) __hwlo
*
* If \p size is 0, \p string may safely be \c NULL.
*
* \return the number of character that were actually written if not truncating,
* \return the number of characters that were actually written if not truncating,
* or that would have been written (not including the ending \\0).
*/
HWLOC_DECLSPEC int hwloc_obj_type_snprintf(char * __hwloc_restrict string, size_t size,
@@ -972,7 +986,7 @@ HWLOC_DECLSPEC int hwloc_obj_type_snprintf(char * __hwloc_restrict string, size_
*
* If \p size is 0, \p string may safely be \c NULL.
*
* \return the number of character that were actually written if not truncating,
* \return the number of characters that were actually written if not truncating,
* or that would have been written (not including the ending \\0).
*/
HWLOC_DECLSPEC int hwloc_obj_attr_snprintf(char * __hwloc_restrict string, size_t size,
@@ -1075,7 +1089,7 @@ HWLOC_DECLSPEC int hwloc_obj_add_info(hwloc_obj_t obj, const char *name, const c
*
* Some operating systems only support binding threads or processes to a single PU.
* Others allow binding to larger sets such as entire Cores or Packages or
* even random sets of invididual PUs. In such operating system, the scheduler
* even random sets of individual PUs. In such operating system, the scheduler
* is free to run the task on one of these PU, then migrate it to another PU, etc.
* It is often useful to call hwloc_bitmap_singlify() on the target CPU set before
* passing it to the binding function to avoid these expensive migrations.
@@ -1153,7 +1167,7 @@ typedef enum {
* CPUs are idle, operating systems may execute the thread/process
* on those other CPUs instead of the designated CPUs, to let them
* progress anyway. Strict binding means that the thread/process
* will _never_ execute on other cpus than the designated CPUs, even
* will _never_ execute on other CPUs than the designated CPUs, even
* when those are busy with other tasks and other CPUs are idle.
*
* \note Depending on the operating system, strict binding may not
@@ -1190,7 +1204,7 @@ typedef enum {
HWLOC_CPUBIND_NOMEMBIND = (1<<3)
} hwloc_cpubind_flags_t;
/** \brief Bind current process or thread on cpus given in physical bitmap \p set.
/** \brief Bind current process or thread on CPUs given in physical bitmap \p set.
*
* \return -1 with errno set to ENOSYS if the action is not supported
* \return -1 with errno set to EXDEV if the binding cannot be enforced
@@ -1199,12 +1213,13 @@ HWLOC_DECLSPEC int hwloc_set_cpubind(hwloc_topology_t topology, hwloc_const_cpus
/** \brief Get current process or thread binding.
*
* Writes into \p set the physical cpuset which the process or thread (according to \e
* flags) was last bound to.
* The CPU-set \p set (previously allocated by the caller)
* is filled with the list of PUs which the process or
* thread (according to \e flags) was last bound to.
*/
HWLOC_DECLSPEC int hwloc_get_cpubind(hwloc_topology_t topology, hwloc_cpuset_t set, int flags);
/** \brief Bind a process \p pid on cpus given in physical bitmap \p set.
/** \brief Bind a process \p pid on CPUs given in physical bitmap \p set.
*
* \note \p hwloc_pid_t is \p pid_t on Unix platforms,
* and \p HANDLE on native Windows platforms.
@@ -1218,6 +1233,10 @@ HWLOC_DECLSPEC int hwloc_get_cpubind(hwloc_topology_t topology, hwloc_cpuset_t s
HWLOC_DECLSPEC int hwloc_set_proc_cpubind(hwloc_topology_t topology, hwloc_pid_t pid, hwloc_const_cpuset_t set, int flags);
/** \brief Get the current physical binding of process \p pid.
*
* The CPU-set \p set (previously allocated by the caller)
* is filled with the list of PUs which the process
* was last bound to.
*
* \note \p hwloc_pid_t is \p pid_t on Unix platforms,
* and \p HANDLE on native Windows platforms.
@@ -1231,7 +1250,7 @@ HWLOC_DECLSPEC int hwloc_set_proc_cpubind(hwloc_topology_t topology, hwloc_pid_t
HWLOC_DECLSPEC int hwloc_get_proc_cpubind(hwloc_topology_t topology, hwloc_pid_t pid, hwloc_cpuset_t set, int flags);
#ifdef hwloc_thread_t
/** \brief Bind a thread \p thread on cpus given in physical bitmap \p set.
/** \brief Bind a thread \p thread on CPUs given in physical bitmap \p set.
*
* \note \p hwloc_thread_t is \p pthread_t on Unix platforms,
* and \p HANDLE on native Windows platforms.
@@ -1243,6 +1262,10 @@ HWLOC_DECLSPEC int hwloc_set_thread_cpubind(hwloc_topology_t topology, hwloc_thr
#ifdef hwloc_thread_t
/** \brief Get the current physical binding of thread \p tid.
*
* The CPU-set \p set (previously allocated by the caller)
* is filled with the list of PUs which the thread
* was last bound to.
*
* \note \p hwloc_thread_t is \p pthread_t on Unix platforms,
* and \p HANDLE on native Windows platforms.
@@ -1253,6 +1276,10 @@ HWLOC_DECLSPEC int hwloc_get_thread_cpubind(hwloc_topology_t topology, hwloc_thr
#endif
/** \brief Get the last physical CPU where the current process or thread ran.
*
* The CPU-set \p set (previously allocated by the caller)
* is filled with the list of PUs which the process or
* thread (according to \e flags) last ran on.
*
* The operating system may move some tasks from one processor
* to another at any time according to their binding,
@@ -1268,6 +1295,10 @@ HWLOC_DECLSPEC int hwloc_get_thread_cpubind(hwloc_topology_t topology, hwloc_thr
HWLOC_DECLSPEC int hwloc_get_last_cpu_location(hwloc_topology_t topology, hwloc_cpuset_t set, int flags);
/** \brief Get the last physical CPU where a process ran.
*
* The CPU-set \p set (previously allocated by the caller)
* is filled with the list of PUs which the process
* last ran on.
*
* The operating system may move some tasks from one processor
* to another at any time according to their binding,
@@ -1498,6 +1529,9 @@ HWLOC_DECLSPEC int hwloc_set_membind(hwloc_topology_t topology, hwloc_const_bitm
/** \brief Query the default memory binding policy and physical locality of the
* current process or thread.
*
* The bitmap \p set (previously allocated by the caller)
* is filled with the process or thread memory binding.
*
* This function has two output parameters: \p set and \p policy.
* The values returned in these parameters depend on both the \p flags
* passed in and the current memory binding policies and nodesets in
@@ -1558,6 +1592,9 @@ HWLOC_DECLSPEC int hwloc_set_proc_membind(hwloc_topology_t topology, hwloc_pid_t
/** \brief Query the default memory binding policy and physical locality of the
* specified process.
*
* The bitmap \p set (previously allocated by the caller)
* is filled with the process memory binding.
*
* This function has two output parameters: \p set and \p policy.
* The values returned in these parameters depend on both the \p flags
* passed in and the current memory binding policies and nodesets in
@@ -1611,6 +1648,9 @@ HWLOC_DECLSPEC int hwloc_set_area_membind(hwloc_topology_t topology, const void
/** \brief Query the CPUs near the physical NUMA node(s) and binding policy of
* the memory identified by (\p addr, \p len ).
*
* The bitmap \p set (previously allocated by the caller)
* is filled with the memory area binding.
*
* This function has two output parameters: \p set and \p policy.
* The values returned in these parameters depend on both the \p flags
* passed in and the memory binding policies and nodesets of the pages
@@ -1639,7 +1679,8 @@ HWLOC_DECLSPEC int hwloc_get_area_membind(hwloc_topology_t topology, const void
/** \brief Get the NUMA nodes where memory identified by (\p addr, \p len ) is physically allocated.
*
* Fills \p set according to the NUMA nodes where the memory area pages
* The bitmap \p set (previously allocated by the caller)
* is filled according to the NUMA nodes where the memory area pages
* are physically allocated. If no page is actually allocated yet,
* \p set may be empty.
*
@@ -1685,9 +1726,12 @@ HWLOC_DECLSPEC void *hwloc_alloc_membind(hwloc_topology_t topology, size_t len,
/** \brief Allocate some memory on NUMA memory nodes specified by \p set
*
* This is similar to hwloc_alloc_membind_nodeset() except that it is allowed to change
* the current memory binding policy, thus providing more binding support, at
* the expense of changing the current state.
* First, try to allocate properly with hwloc_alloc_membind().
* On failure, the current process or thread memory binding policy
* is changed with hwloc_set_membind() before allocating memory.
* Thus this function works in more cases, at the expense of changing
* the current state (possibly affecting future allocations that
* would not specify any policy).
*
* If ::HWLOC_MEMBIND_BYNODESET is specified, set is considered a nodeset.
* Otherwise it's a cpuset.
@@ -1870,8 +1914,9 @@ HWLOC_DECLSPEC int hwloc_topology_set_components(hwloc_topology_t __hwloc_restri
enum hwloc_topology_flags_e {
/** \brief Detect the whole system, ignore reservations, include disallowed objects.
*
* Gather all resources, even if some were disabled by the administrator.
* Gather all online resources, even if some were disabled by the administrator.
* For instance, ignore Linux Cgroup/Cpusets and gather all processors and memory nodes.
* However offline PUs and NUMA nodes are still ignored.
*
* When this flag is not set, PUs and NUMA nodes that are disallowed are not added to the topology.
* Parent objects (package, core, cache, etc.) are added only if some of their children are allowed.
@@ -1929,17 +1974,124 @@ enum hwloc_topology_flags_e {
* would result in the same behavior.
* \hideinitializer
*/
HWLOC_TOPOLOGY_FLAG_THISSYSTEM_ALLOWED_RESOURCES = (1UL<<2)
HWLOC_TOPOLOGY_FLAG_THISSYSTEM_ALLOWED_RESOURCES = (1UL<<2),
/** \brief Import support from the imported topology.
*
* When importing a XML topology from a remote machine, binding is
* disabled by default (see ::HWLOC_TOPOLOGY_FLAG_IS_THISSYSTEM).
* This disabling is also marked by putting zeroes in the corresponding
* supported feature bits reported by hwloc_topology_get_support().
*
* The flag ::HWLOC_TOPOLOGY_FLAG_IMPORT_SUPPORT actually imports
* support bits from the remote machine. It also sets the flag
* \p imported_support in the struct hwloc_topology_misc_support array.
* If the imported XML did not contain any support information
* (exporter hwloc is too old), this flag is not set.
*
* Note that these supported features are only relevant for the hwloc
* installation that actually exported the XML topology
* (it may vary with the operating system, or with how hwloc was compiled).
*
* Note that setting this flag however does not enable binding for the
* locally imported hwloc topology, it only reports what the remote
* hwloc and machine support.
*
*/
HWLOC_TOPOLOGY_FLAG_IMPORT_SUPPORT = (1UL<<3),
/** \brief Do not consider resources outside of the process CPU binding.
*
* If the binding of the process is limited to a subset of cores,
* ignore the other cores during discovery.
*
* The resulting topology is identical to what a call to hwloc_topology_restrict()
* would generate, but this flag also prevents hwloc from ever touching other
* resources during the discovery.
*
* This flag especially tells the x86 backend to never temporarily
* rebind a thread on any excluded core. This is useful on Windows
* because such temporary rebinding can change the process binding.
* Another use-case is to avoid cores that would not be able to
* perform the hwloc discovery anytime soon because they are busy
* executing some high-priority real-time tasks.
*
* If process CPU binding is not supported,
* the thread CPU binding is considered instead if supported,
* or the flag is ignored.
*
* This flag requires ::HWLOC_TOPOLOGY_FLAG_IS_THISSYSTEM as well
* since binding support is required.
*/
HWLOC_TOPOLOGY_FLAG_RESTRICT_TO_CPUBINDING = (1UL<<4),
/** \brief Do not consider resources outside of the process memory binding.
*
* If the binding of the process is limited to a subset of NUMA nodes,
* ignore the other NUMA nodes during discovery.
*
* The resulting topology is identical to what a call to hwloc_topology_restrict()
* would generate, but this flag also prevents hwloc from ever touching other
* resources during the discovery.
*
* This flag is meant to be used together with
* ::HWLOC_TOPOLOGY_FLAG_RESTRICT_TO_CPUBINDING when both cores
* and NUMA nodes should be ignored outside of the process binding.
*
* If process memory binding is not supported,
* the thread memory binding is considered instead if supported,
* or the flag is ignored.
*
* This flag requires ::HWLOC_TOPOLOGY_FLAG_IS_THISSYSTEM as well
* since binding support is required.
*/
HWLOC_TOPOLOGY_FLAG_RESTRICT_TO_MEMBINDING = (1UL<<5),
/** \brief Do not ever modify the process or thread binding during discovery.
*
* This flag disables all hwloc discovery steps that require a change of
* the process or thread binding. This currently only affects the x86
* backend which gets entirely disabled.
*
* This is useful when hwloc_topology_load() is called while the
* application also creates additional threads or modifies the binding.
*
* This flag is also a strict way to make sure the process binding will
* not change to due thread binding changes on Windows
* (see ::HWLOC_TOPOLOGY_FLAG_RESTRICT_TO_CPUBINDING).
*/
HWLOC_TOPOLOGY_FLAG_DONT_CHANGE_BINDING = (1UL<<6),
/** \brief Ignore distances.
*
* Ignore distance information from the operating systems (and from XML)
* and hence do not use distances for grouping.
*/
HWLOC_TOPOLOGY_FLAG_NO_DISTANCES = (1UL<<7),
/** \brief Ignore memory attributes.
*
* Ignore memory attribues from the operating systems (and from XML).
*/
HWLOC_TOPOLOGY_FLAG_NO_MEMATTRS = (1UL<<8),
/** \brief Ignore CPU Kinds.
*
* Ignore CPU kind information from the operating systems (and from XML).
*/
HWLOC_TOPOLOGY_FLAG_NO_CPUKINDS = (1UL<<9)
};
/** \brief Set OR'ed flags to non-yet-loaded topology.
*
* Set a OR'ed set of ::hwloc_topology_flags_e onto a topology that was not yet loaded.
*
* If this function is called multiple times, the last invokation will erase
* If this function is called multiple times, the last invocation will erase
* and replace the set of flags that was previously set.
*
* The flags set in a topology may be retrieved with hwloc_topology_get_flags()
* By default, no flags are set (\c 0).
*
* The flags set in a topology may be retrieved with hwloc_topology_get_flags().
*/
HWLOC_DECLSPEC int hwloc_topology_set_flags (hwloc_topology_t topology, unsigned long flags);
@@ -1947,6 +2099,9 @@ HWLOC_DECLSPEC int hwloc_topology_set_flags (hwloc_topology_t topology, unsigned
*
* Get the OR'ed set of ::hwloc_topology_flags_e of a topology.
*
* If hwloc_topology_set_flags() was not called earlier,
* no flags are set (\c 0 is returned).
*
* \return the flags previously set with hwloc_topology_set_flags().
*/
HWLOC_DECLSPEC unsigned long hwloc_topology_get_flags (hwloc_topology_t topology);
@@ -1972,6 +2127,8 @@ struct hwloc_topology_discovery_support {
unsigned char disallowed_pu;
/** \brief Detecting and identifying NUMA nodes that are not available to the current process is supported. */
unsigned char disallowed_numa;
/** \brief Detecting the efficiency of CPU kinds is supported, see \ref hwlocality_cpukinds. */
unsigned char cpukind_efficiency;
};
/** \brief Flags describing actual PU binding support for this topology.
@@ -2042,6 +2199,13 @@ struct hwloc_topology_membind_support {
unsigned char get_area_memlocation;
};
/** \brief Flags describing miscellaneous features.
*/
struct hwloc_topology_misc_support {
/** Support was imported when importing another topology, see ::HWLOC_TOPOLOGY_FLAG_IMPORT_SUPPORT. */
unsigned char imported_support;
};
/** \brief Set of flags describing actual support for this topology.
*
* This is retrieved with hwloc_topology_get_support() and will be valid until
@@ -2052,6 +2216,7 @@ struct hwloc_topology_support {
struct hwloc_topology_discovery_support *discovery;
struct hwloc_topology_cpubind_support *cpubind;
struct hwloc_topology_membind_support *membind;
struct hwloc_topology_misc_support *misc;
};
/** \brief Retrieve the topology support.
@@ -2062,6 +2227,18 @@ struct hwloc_topology_support {
* call may still fail in some corner cases.
*
* These features are also listed by hwloc-info \--support
*
* The reported features are what the current topology supports
* on the current machine. If the topology was exported to XML
* from another machine and later imported here, support still
* describes what is supported for this imported topology after
* import. By default, binding will be reported as unsupported
* in this case (see ::HWLOC_TOPOLOGY_FLAG_IS_THISSYSTEM).
*
* Topology flag ::HWLOC_TOPOLOGY_FLAG_IMPORT_SUPPORT may be used
* to report the supported features of the original remote machine
* instead. If it was successfully imported, \p imported_support
* will be set in the struct hwloc_topology_misc_support array.
*/
HWLOC_DECLSPEC const struct hwloc_topology_support *hwloc_topology_get_support(hwloc_topology_t __hwloc_restrict topology);
@@ -2108,8 +2285,8 @@ enum hwloc_type_filter_e {
*
* It is only useful for I/O object types.
* For ::HWLOC_OBJ_PCI_DEVICE and ::HWLOC_OBJ_OS_DEVICE, it means that only objects
* of major/common kinds are kept (storage, network, OpenFabrics, Intel MICs, CUDA,
* OpenCL, NVML, and displays).
* of major/common kinds are kept (storage, network, OpenFabrics, CUDA,
* OpenCL, RSMI, NVML, and displays).
* Also, only OS devices directly attached on PCI (e.g. no USB) are reported.
* For ::HWLOC_OBJ_BRIDGE, it means that bridges are kept only if they have children.
*
@@ -2303,22 +2480,9 @@ HWLOC_DECLSPEC hwloc_obj_t hwloc_topology_insert_misc_object(hwloc_topology_t to
/** \brief Allocate a Group object to insert later with hwloc_topology_insert_group_object().
*
* This function returns a new Group object.
* The caller should (at least) initialize its sets before inserting the object.
* See hwloc_topology_insert_group_object().
*
* The \p subtype object attribute may be set to display something else
* than "Group" as the type name for this object in lstopo.
* Custom name/value info pairs may be added with hwloc_obj_add_info() after
* insertion.
*
* The \p kind group attribute should be 0. The \p subkind group attribute may
* be set to identify multiple Groups of the same level.
*
* It is recommended not to set any other object attribute before insertion,
* since the Group may get discarded during insertion.
*
* The object will be destroyed if passed to hwloc_topology_insert_group_object()
* without any set defined.
* The caller should (at least) initialize its sets before inserting
* the object in the topology. See hwloc_topology_insert_group_object().
*/
HWLOC_DECLSPEC hwloc_obj_t hwloc_topology_alloc_group_object(hwloc_topology_t topology);
@@ -2329,34 +2493,44 @@ HWLOC_DECLSPEC hwloc_obj_t hwloc_topology_alloc_group_object(hwloc_topology_t to
* the final location of the Group in the topology.
* Then the object can be passed to this function for actual insertion in the topology.
*
* The group \p dont_merge attribute may be set to prevent the core from
* ever merging this object with another object hierarchically-identical.
*
* Either the cpuset or nodeset field (or both, if compatible) must be set
* to a non-empty bitmap. The complete_cpuset or complete_nodeset may be set
* instead if inserting with respect to the complete topology
* (including disallowed, offline or unknown objects).
*
* It grouping several objects, hwloc_obj_add_other_obj_sets() is an easy way
* If grouping several objects, hwloc_obj_add_other_obj_sets() is an easy way
* to build the Group sets iteratively.
*
* These sets cannot be larger than the current topology, or they would get
* restricted silently.
*
* The core will setup the other sets after actual insertion.
*
* The \p subtype object attribute may be defined (to a dynamically
* allocated string) to display something else than "Group" as the
* type name for this object in lstopo.
* Custom name/value info pairs may be added with hwloc_obj_add_info() after
* insertion.
*
* The group \p dont_merge attribute may be set to \c 1 to prevent
* the hwloc core from ever merging this object with another
* hierarchically-identical object.
* This is useful when the Group itself describes an important feature
* that cannot be exposed anywhere else in the hierarchy.
*
* The group \p kind attribute may be set to a high value such
* as \c 0xffffffff to tell hwloc that this new Group should always
* be discarded in favor of any existing Group with the same locality.
*
* \return The inserted object if it was properly inserted.
*
* \return An existing object if the Group was discarded because the topology already
* contained an object at the same location (the Group did not add any locality information).
* Any name/info key pair set before inserting is appended to the existing object.
* \return An existing object if the Group was merged or discarded
* because the topology already contained an object at the same
* location (the Group did not add any hierarchy information).
*
* \return \c NULL if the insertion failed because of conflicting sets in topology tree.
*
* \return \c NULL if Group objects are filtered-out of the topology (::HWLOC_TYPE_FILTER_KEEP_NONE).
*
* \return \c NULL if the object was discarded because no set was initialized in the Group
* before insert, or all of them were empty.
* \return \c NULL if the object was discarded because no set was
* initialized in the Group before insert, or all of them were empty.
*/
HWLOC_DECLSPEC hwloc_obj_t hwloc_topology_insert_group_object(hwloc_topology_t topology, hwloc_obj_t group);
@@ -2371,6 +2545,22 @@ HWLOC_DECLSPEC hwloc_obj_t hwloc_topology_insert_group_object(hwloc_topology_t t
*/
HWLOC_DECLSPEC int hwloc_obj_add_other_obj_sets(hwloc_obj_t dst, hwloc_obj_t src);
/** \brief Refresh internal structures after topology modification.
*
* Modifying the topology (by restricting, adding objects, modifying structures
* such as distances or memory attributes, etc.) may cause some internal caches
* to become invalid. These caches are automatically refreshed when accessed
* but this refreshing is not thread-safe.
*
* This function is not thread-safe either, but it is a good way to end a
* non-thread-safe phase of topology modification. Once this refresh is done,
* multiple threads may concurrently consult the topology, objects, distances,
* attributes, etc.
*
* See also \ref threadsafety
*/
HWLOC_DECLSPEC int hwloc_topology_refresh(hwloc_topology_t topology);
/** @} */
@@ -2386,6 +2576,12 @@ HWLOC_DECLSPEC int hwloc_obj_add_other_obj_sets(hwloc_obj_t dst, hwloc_obj_t src
/* inline code of some functions above */
#include "hwloc/inlines.h"
/* memory attributes */
#include "hwloc/memattrs.h"
/* kinds of CPU cores */
#include "hwloc/cpukinds.h"
/* exporting to XML or synthetic */
#include "hwloc/export.h"

View File

@@ -1,6 +1,6 @@
/*
* Copyright © 2009 CNRS
* Copyright © 2009-2019 Inria. All rights reserved.
* Copyright © 2009-2022 Inria. All rights reserved.
* Copyright © 2009-2012 Université Bordeaux
* Copyright © 2009-2011 Cisco Systems, Inc. All rights reserved.
* See COPYING in top-level directory.
@@ -11,9 +11,9 @@
#ifndef HWLOC_CONFIG_H
#define HWLOC_CONFIG_H
#define HWLOC_VERSION "2.2.0"
#define HWLOC_VERSION "2.9.0"
#define HWLOC_VERSION_MAJOR 2
#define HWLOC_VERSION_MINOR 2
#define HWLOC_VERSION_MINOR 9
#define HWLOC_VERSION_RELEASE 0
#define HWLOC_VERSION_GREEK ""

View File

@@ -1,6 +1,6 @@
/*
* Copyright © 2009 CNRS
* Copyright © 2009-2018 Inria. All rights reserved.
* Copyright © 2009-2022 Inria. All rights reserved.
* Copyright © 2009-2012 Université Bordeaux
* Copyright © 2009-2011 Cisco Systems, Inc. All rights reserved.
* See COPYING in top-level directory.
@@ -112,7 +112,7 @@ HWLOC_DECLSPEC int hwloc_bitmap_copy(hwloc_bitmap_t dst, hwloc_const_bitmap_t sr
*
* If \p buflen is 0, \p buf may safely be \c NULL.
*
* \return the number of character that were actually written if not truncating,
* \return the number of characters that were actually written if not truncating,
* or that would have been written (not including the ending \\0).
*/
HWLOC_DECLSPEC int hwloc_bitmap_snprintf(char * __hwloc_restrict buf, size_t buflen, hwloc_const_bitmap_t bitmap);
@@ -137,7 +137,7 @@ HWLOC_DECLSPEC int hwloc_bitmap_sscanf(hwloc_bitmap_t bitmap, const char * __hwl
*
* If \p buflen is 0, \p buf may safely be \c NULL.
*
* \return the number of character that were actually written if not truncating,
* \return the number of characters that were actually written if not truncating,
* or that would have been written (not including the ending \\0).
*/
HWLOC_DECLSPEC int hwloc_bitmap_list_snprintf(char * __hwloc_restrict buf, size_t buflen, hwloc_const_bitmap_t bitmap);
@@ -161,7 +161,7 @@ HWLOC_DECLSPEC int hwloc_bitmap_list_sscanf(hwloc_bitmap_t bitmap, const char *
*
* If \p buflen is 0, \p buf may safely be \c NULL.
*
* \return the number of character that were actually written if not truncating,
* \return the number of characters that were actually written if not truncating,
* or that would have been written (not including the ending \\0).
*/
HWLOC_DECLSPEC int hwloc_bitmap_taskset_snprintf(char * __hwloc_restrict buf, size_t buflen, hwloc_const_bitmap_t bitmap);
@@ -231,7 +231,7 @@ HWLOC_DECLSPEC int hwloc_bitmap_clr_range(hwloc_bitmap_t bitmap, unsigned begin,
/** \brief Keep a single index among those set in bitmap \p bitmap
*
* May be useful before binding so that the process does not
* have a chance of migrating between multiple logical CPUs
* have a chance of migrating between multiple processors
* in the original mask.
* Instead of running the task on any PU inside the given CPU set,
* the operating system scheduler will be forced to run it on a single
@@ -357,11 +357,11 @@ HWLOC_DECLSPEC int hwloc_bitmap_last_unset(hwloc_const_bitmap_t bitmap) __hwloc_
* The loop must start with hwloc_bitmap_foreach_begin() and end
* with hwloc_bitmap_foreach_end() followed by a terminating ';'.
*
* \p index is the loop variable; it should be an unsigned int. The
* first iteration will set \p index to the lowest index in the bitmap.
* \p id is the loop variable; it should be an unsigned int. The
* first iteration will set \p id to the lowest index in the bitmap.
* Successive iterations will iterate through, in order, all remaining
* indexes set in the bitmap. To be specific: each iteration will return a
* value for \p index such that hwloc_bitmap_isset(bitmap, index) is true.
* value for \p id such that hwloc_bitmap_isset(bitmap, id) is true.
*
* The assert prevents the loop from being infinite if the bitmap is infinitely set.
*

View File

@@ -0,0 +1,193 @@
/*
* Copyright © 2020-2021 Inria. All rights reserved.
* See COPYING in top-level directory.
*/
/** \file
* \brief Kinds of CPU cores.
*/
#ifndef HWLOC_CPUKINDS_H
#define HWLOC_CPUKINDS_H
#include "hwloc.h"
#ifdef __cplusplus
extern "C" {
#elif 0
}
#endif
/** \defgroup hwlocality_cpukinds Kinds of CPU cores
*
* Platforms with heterogeneous CPUs may have some cores with
* different features or frequencies.
* This API exposes identical PUs in sets called CPU kinds.
* Each PU of the topology may only be in a single kind.
*
* The number of kinds may be obtained with hwloc_cpukinds_get_nr().
* If the platform is homogeneous, there may be a single kind
* with all PUs.
* If the platform or operating system does not expose any
* information about CPU cores, there may be no kind at all.
*
* The index of the kind that describes a given CPU set
* (if any, and not partially)
* may be obtained with hwloc_cpukinds_get_by_cpuset().
*
* From the index of a kind, it is possible to retrieve information
* with hwloc_cpukinds_get_info():
* an abstracted efficiency value,
* and an array of info attributes
* (for instance the "CoreType" and "FrequencyMaxMHz",
* see \ref topoattrs_cpukinds).
*
* A higher efficiency value means greater intrinsic performance
* (and possibly less performance/power efficiency).
* Kinds with lower efficiency values are ranked first:
* Passing 0 as \p kind_index to hwloc_cpukinds_get_info() will
* return information about the CPU kind with lower performance
* but higher energy-efficiency.
* Higher \p kind_index values would rather return information
* about power-hungry high-performance cores.
*
* When available, efficiency values are gathered from the operating system.
* If so, \p cpukind_efficiency is set in the struct hwloc_topology_discovery_support array.
* This is currently available on Windows 10, Mac OS X (Darwin),
* and on some Linux platforms where core "capacity" is exposed in sysfs.
*
* If the operating system does not expose core efficiencies natively,
* hwloc tries to compute efficiencies by comparing CPU kinds using
* frequencies (on ARM), or core types and frequencies (on other architectures).
* The environment variable HWLOC_CPUKINDS_RANKING may be used
* to change this heuristics, see \ref envvar.
*
* If hwloc fails to rank any kind, for instance because the operating
* system does not expose efficiencies and core frequencies,
* all kinds will have an unknown efficiency (\c -1),
* and they are not indexed/ordered in any specific way.
*
* @{
*/
/** \brief Get the number of different kinds of CPU cores in the topology.
*
* \p flags must be \c 0 for now.
*
* \return The number of CPU kinds (positive integer) on success.
* \return \c 0 if no information about kinds was found.
* \return \c -1 with \p errno set to \c EINVAL if \p flags is invalid.
*/
HWLOC_DECLSPEC int
hwloc_cpukinds_get_nr(hwloc_topology_t topology,
unsigned long flags);
/** \brief Get the index of the CPU kind that contains CPUs listed in \p cpuset.
*
* \p flags must be \c 0 for now.
*
* \return The index of the CPU kind (positive integer or 0) on success.
* \return \c -1 with \p errno set to \c EXDEV if \p cpuset is
* only partially included in the some kind.
* \return \c -1 with \p errno set to \c ENOENT if \p cpuset is
* not included in any kind, even partially.
* \return \c -1 with \p errno set to \c EINVAL if parameters are invalid.
*/
HWLOC_DECLSPEC int
hwloc_cpukinds_get_by_cpuset(hwloc_topology_t topology,
hwloc_const_bitmap_t cpuset,
unsigned long flags);
/** \brief Get the CPU set and infos about a CPU kind in the topology.
*
* \p kind_index identifies one kind of CPU between 0 and the number
* of kinds returned by hwloc_cpukinds_get_nr() minus 1.
*
* If not \c NULL, the bitmap \p cpuset will be filled with
* the set of PUs of this kind.
*
* The integer pointed by \p efficiency, if not \c NULL will, be filled
* with the ranking of this kind of CPU in term of efficiency (see above).
* It ranges from \c 0 to the number of kinds
* (as reported by hwloc_cpukinds_get_nr()) minus 1.
*
* Kinds with lower efficiency are reported first.
*
* If there is a single kind in the topology, its efficiency \c 0.
* If the efficiency of some kinds of cores is unknown,
* the efficiency of all kinds is set to \c -1,
* and kinds are reported in no specific order.
*
* The array of info attributes (for instance the "CoreType",
* "FrequencyMaxMHz" or "FrequencyBaseMHz", see \ref topoattrs_cpukinds)
* and its length are returned in \p infos or \p nr_infos.
* The array belongs to the topology, it should not be freed or modified.
*
* If \p nr_infos or \p infos is \c NULL, no info is returned.
*
* \p flags must be \c 0 for now.
*
* \return \c 0 on success.
* \return \c -1 with \p errno set to \c ENOENT if \p kind_index does not match any CPU kind.
* \return \c -1 with \p errno set to \c EINVAL if parameters are invalid.
*/
HWLOC_DECLSPEC int
hwloc_cpukinds_get_info(hwloc_topology_t topology,
unsigned kind_index,
hwloc_bitmap_t cpuset,
int *efficiency,
unsigned *nr_infos, struct hwloc_info_s **infos,
unsigned long flags);
/** \brief Register a kind of CPU in the topology.
*
* Mark the PUs listed in \p cpuset as being of the same kind
* with respect to the given attributes.
*
* \p forced_efficiency should be \c -1 if unknown.
* Otherwise it is an abstracted efficiency value to enforce
* the ranking of all kinds if all of them have valid (and
* different) efficiencies.
*
* The array \p infos of size \p nr_infos may be used to provide
* info names and values describing this kind of PUs.
*
* \p flags must be \c 0 for now.
*
* Parameters \p cpuset and \p infos will be duplicated internally,
* the caller is responsible for freeing them.
*
* If \p cpuset overlaps with some existing kinds, those might get
* modified or split. For instance if existing kind A contains
* PUs 0 and 1, and one registers another kind for PU 1 and 2,
* there will be 3 resulting kinds:
* existing kind A is restricted to only PU 0;
* new kind B contains only PU 1 and combines information from A
* and from the newly-registered kind;
* new kind C contains only PU 2 and only gets information from
* the newly-registered kind.
*
* \note The efficiency \p forced_efficiency provided to this function
* may be different from the one reported later by hwloc_cpukinds_get_info()
* because hwloc will scale efficiency values down to
* between 0 and the number of kinds minus 1.
*
* \return \c 0 on success.
* \return \c -1 with \p errno set to \c EINVAL if some parameters are invalid,
* for instance if \p cpuset is \c NULL or empty.
*/
HWLOC_DECLSPEC int
hwloc_cpukinds_register(hwloc_topology_t topology,
hwloc_bitmap_t cpuset,
int forced_efficiency,
unsigned nr_infos, struct hwloc_info_s *infos,
unsigned long flags);
/** @} */
#ifdef __cplusplus
} /* extern "C" */
#endif
#endif /* HWLOC_CPUKINDS_H */

View File

@@ -1,5 +1,5 @@
/*
* Copyright © 2010-2017 Inria. All rights reserved.
* Copyright © 2010-2021 Inria. All rights reserved.
* Copyright © 2010-2011 Université Bordeaux
* Copyright © 2011 Cisco Systems, Inc. All rights reserved.
* See COPYING in top-level directory.
@@ -72,10 +72,10 @@ hwloc_cuda_get_device_pci_ids(hwloc_topology_t topology __hwloc_attribute_unused
return 0;
}
/** \brief Get the CPU set of logical processors that are physically
/** \brief Get the CPU set of processors that are physically
* close to device \p cudevice.
*
* Return the CPU set describing the locality of the CUDA device \p cudevice.
* Store in \p set the CPU-set describing the locality of the CUDA device \p cudevice.
*
* Topology \p topology and device \p cudevice must match the local machine.
* I/O devices detection and the CUDA component are not needed in the topology.
@@ -120,8 +120,8 @@ hwloc_cuda_get_device_cpuset(hwloc_topology_t topology __hwloc_attribute_unused,
/** \brief Get the hwloc PCI device object corresponding to the
* CUDA device \p cudevice.
*
* Return the PCI device object describing the CUDA device \p cudevice.
* Return NULL if there is none.
* \return The hwloc PCI device object describing the CUDA device \p cudevice.
* \return \c NULL if none could be found.
*
* Topology \p topology and device \p cudevice must match the local machine.
* I/O devices detection must be enabled in topology \p topology.
@@ -140,8 +140,8 @@ hwloc_cuda_get_device_pcidev(hwloc_topology_t topology, CUdevice cudevice)
/** \brief Get the hwloc OS device object corresponding to CUDA device \p cudevice.
*
* Return the hwloc OS device object that describes the given
* CUDA device \p cudevice. Return NULL if there is none.
* \return The hwloc OS device object that describes the given CUDA device \p cudevice.
* \return \c NULL if none could be found.
*
* Topology \p topology and device \p cudevice must match the local machine.
* I/O devices detection and the CUDA component must be enabled in the topology.
@@ -183,8 +183,8 @@ hwloc_cuda_get_device_osdev(hwloc_topology_t topology, CUdevice cudevice)
/** \brief Get the hwloc OS device object corresponding to the
* CUDA device whose index is \p idx.
*
* Return the OS device object describing the CUDA device whose
* index is \p idx. Return NULL if there is none.
* \return The hwloc OS device object describing the CUDA device whose index is \p idx.
* \return \c NULL if none could be found.
*
* The topology \p topology does not necessarily have to match the current
* machine. For instance the topology may be an XML import of a remote host.

View File

@@ -1,5 +1,5 @@
/*
* Copyright © 2010-2017 Inria. All rights reserved.
* Copyright © 2010-2021 Inria. All rights reserved.
* Copyright © 2010-2011 Université Bordeaux
* Copyright © 2011 Cisco Systems, Inc. All rights reserved.
* See COPYING in top-level directory.
@@ -69,10 +69,10 @@ hwloc_cudart_get_device_pci_ids(hwloc_topology_t topology __hwloc_attribute_unus
return 0;
}
/** \brief Get the CPU set of logical processors that are physically
/** \brief Get the CPU set of processors that are physically
* close to device \p idx.
*
* Return the CPU set describing the locality of the CUDA device
* Store in \p set the CPU-set describing the locality of the CUDA device
* whose index is \p idx.
*
* Topology \p topology and device \p idx must match the local machine.
@@ -117,8 +117,8 @@ hwloc_cudart_get_device_cpuset(hwloc_topology_t topology __hwloc_attribute_unuse
/** \brief Get the hwloc PCI device object corresponding to the
* CUDA device whose index is \p idx.
*
* Return the PCI device object describing the CUDA device whose
* index is \p idx. Return NULL if there is none.
* \return The hwloc PCI device object describing the CUDA device whose index is \p idx.
* \return \c NULL if none could be found.
*
* Topology \p topology and device \p idx must match the local machine.
* I/O devices detection must be enabled in topology \p topology.
@@ -138,8 +138,8 @@ hwloc_cudart_get_device_pcidev(hwloc_topology_t topology, int idx)
/** \brief Get the hwloc OS device object corresponding to the
* CUDA device whose index is \p idx.
*
* Return the OS device object describing the CUDA device whose
* index is \p idx. Return NULL if there is none.
* \return The hwloc OS device object describing the CUDA device whose index is \p idx.
* \return \c NULL if none could be found.
*
* The topology \p topology does not necessarily have to match the current
* machine. For instance the topology may be an XML import of a remote host.

View File

@@ -1,6 +1,6 @@
/*
* Copyright © 2009 CNRS
* Copyright © 2009-2018 Inria. All rights reserved.
* Copyright © 2009-2022 Inria. All rights reserved.
* Copyright © 2009-2012 Université Bordeaux
* Copyright © 2009-2010 Cisco Systems, Inc. All rights reserved.
* See COPYING in top-level directory.
@@ -30,6 +30,15 @@ extern "C" {
/* backward compat with v1.10 before Node->NUMANode clarification */
#define HWLOC_OBJ_NODE HWLOC_OBJ_NUMANODE
/** \brief Add a distances structure.
*
* Superseded by hwloc_distances_add_create()+hwloc_distances_add_values()+hwloc_distances_add_commit()
* in v2.5.
*/
HWLOC_DECLSPEC int hwloc_distances_add(hwloc_topology_t topology,
unsigned nbobjs, hwloc_obj_t *objs, hwloc_uint64_t *values,
unsigned long kind, unsigned long flags) __hwloc_attribute_deprecated;
/** \brief Insert a misc object by parent.
*
* Identical to hwloc_topology_insert_misc_object().
@@ -46,7 +55,7 @@ hwloc_topology_insert_misc_object_by_parent(hwloc_topology_t topology, hwloc_obj
*
* If \p size is 0, \p string may safely be \c NULL.
*
* \return the number of character that were actually written if not truncating,
* \return the number of characters that were actually written if not truncating,
* or that would have been written (not including the ending \\0).
*/
static __hwloc_inline int

View File

@@ -1,5 +1,5 @@
/*
* Copyright © 2013-2018 Inria. All rights reserved.
* Copyright © 2013-2020 Inria. All rights reserved.
* See COPYING in top-level directory.
*/
@@ -110,7 +110,7 @@ union hwloc_topology_diff_obj_attr_u {
*/
typedef enum hwloc_topology_diff_type_e {
/** \brief An object attribute was changed.
* The union is a hwloc_topology_diff_obj_attr_u::hwloc_topology_diff_obj_attr_s.
* The union is a hwloc_topology_diff_u::hwloc_topology_diff_obj_attr_s.
*/
HWLOC_TOPOLOGY_DIFF_OBJ_ATTR,
@@ -119,7 +119,7 @@ typedef enum hwloc_topology_diff_type_e {
* this object has not been checked.
* hwloc_topology_diff_build() will return 1.
*
* The union is a hwloc_topology_diff_obj_attr_u::hwloc_topology_diff_too_complex_s.
* The union is a hwloc_topology_diff_u::hwloc_topology_diff_too_complex_s.
*/
HWLOC_TOPOLOGY_DIFF_TOO_COMPLEX
} hwloc_topology_diff_type_t;

View File

@@ -1,5 +1,5 @@
/*
* Copyright © 2010-2019 Inria. All rights reserved.
* Copyright © 2010-2022 Inria. All rights reserved.
* See COPYING in top-level directory.
*/
@@ -34,9 +34,21 @@ extern "C" {
* It corresponds to the latency for accessing the memory of one node
* from a core in another node.
* The corresponding kind is ::HWLOC_DISTANCES_KIND_FROM_OS | ::HWLOC_DISTANCES_KIND_FROM_USER.
* The name of this distances structure is "NUMALatency".
* Others distance structures include and "XGMIBandwidth", "XGMIHops",
* "XeLinkBandwidth" and "NVLinkBandwidth".
*
* The matrix may also contain bandwidths between random sets of objects,
* possibly provided by the user, as specified in the \p kind attribute.
*
* Pointers \p objs and \p values should not be replaced, reallocated, freed, etc.
* However callers are allowed to modify \p kind as well as the contents
* of \p objs and \p values arrays.
* For instance, if there is a single NUMA node per Package,
* hwloc_get_obj_with_same_locality() may be used to convert between them
* and replace NUMA nodes in the \p objs array with the corresponding Packages.
* See also hwloc_distances_transform() for applying some transformations
* to the structure.
*/
struct hwloc_distances_s {
unsigned nbobjs; /**< \brief Number of objects described by the distance matrix. */
@@ -90,6 +102,8 @@ enum hwloc_distances_kind_e {
HWLOC_DISTANCES_KIND_MEANS_BANDWIDTH = (1UL<<3),
/** \brief This distances structure covers objects of different types.
* This may apply to the "NVLinkBandwidth" structure in presence
* of a NVSwitch or POWER processor NVLink port.
* \hideinitializer
*/
HWLOC_DISTANCES_KIND_HETEROGENEOUS_TYPES = (1UL<<4)
@@ -144,6 +158,10 @@ hwloc_distances_get_by_type(hwloc_topology_t topology, hwloc_obj_type_t type,
/** \brief Retrieve a distance matrix with the given name.
*
* Usually only one distances structure may match a given name.
*
* The name of the most common structure is "NUMALatency".
* Others include "XGMIBandwidth", "XGMIHops", "XeLinkBandwidth",
* and "NVLinkBandwidth".
*/
HWLOC_DECLSPEC int
hwloc_distances_get_by_name(hwloc_topology_t topology, const char *name,
@@ -165,6 +183,85 @@ hwloc_distances_get_name(hwloc_topology_t topology, struct hwloc_distances_s *di
HWLOC_DECLSPEC void
hwloc_distances_release(hwloc_topology_t topology, struct hwloc_distances_s *distances);
/** \brief Transformations of distances structures. */
enum hwloc_distances_transform_e {
/** \brief Remove \c NULL objects from the distances structure.
*
* Every object that was replaced with \c NULL in the \p objs array
* is removed and the \p values array is updated accordingly.
*
* At least \c 2 objects must remain, otherwise hwloc_distances_transform()
* will return \c -1 with \p errno set to \c EINVAL.
*
* \p kind will be updated with or without ::HWLOC_DISTANCES_KIND_HETEROGENEOUS_TYPES
* according to the remaining objects.
*
* \hideinitializer
*/
HWLOC_DISTANCES_TRANSFORM_REMOVE_NULL = 0,
/** \brief Replace bandwidth values with a number of links.
*
* Usually all values will be either \c 0 (no link) or \c 1 (one link).
* However some matrices could get larger values if some pairs of
* peers are connected by different numbers of links.
*
* Values on the diagonal are set to \c 0.
*
* This transformation only applies to bandwidth matrices.
*
* \hideinitializer
*/
HWLOC_DISTANCES_TRANSFORM_LINKS = 1,
/** \brief Merge switches with multiple ports into a single object.
* This currently only applies to NVSwitches where GPUs seem connected to different
* separate switch ports in the NVLinkBandwidth matrix. This transformation will
* replace all of them with the same port connected to all GPUs.
* Other ports are removed by applying ::HWLOC_DISTANCES_TRANSFORM_REMOVE_NULL internally.
* \hideinitializer
*/
HWLOC_DISTANCES_TRANSFORM_MERGE_SWITCH_PORTS = 2,
/** \brief Apply a transitive closure to the matrix to connect objects across switches.
* This currently only applies to GPUs and NVSwitches in the NVLinkBandwidth matrix.
* All pairs of GPUs will be reported as directly connected.
* \hideinitializer
*/
HWLOC_DISTANCES_TRANSFORM_TRANSITIVE_CLOSURE = 3
};
/** \brief Apply a transformation to a distances structure.
*
* Modify a distances structure that was previously obtained with
* hwloc_distances_get() or one of its variants.
*
* This modifies the local copy of the distances structures but does
* not modify the distances information stored inside the topology
* (retrieved by another call to hwloc_distances_get() or exported to XML).
* To do so, one should add a new distances structure with same
* name, kind, objects and values (see \ref hwlocality_distances_add)
* and then remove this old one with hwloc_distances_release_remove().
*
* \p transform must be one of the transformations listed
* in ::hwloc_distances_transform_e.
*
* These transformations may modify the contents of the \p objs or \p values arrays.
*
* \p transform_attr must be \c NULL for now.
*
* \p flags must be \c 0 for now.
*
* \note Objects in distances array \p objs may be directly modified
* in place without using hwloc_distances_transform().
* One may use hwloc_get_obj_with_same_locality() to easily convert
* between similar objects of different types.
*/
HWLOC_DECLSPEC int hwloc_distances_transform(hwloc_topology_t topology, struct hwloc_distances_s *distances,
enum hwloc_distances_transform_e transform,
void *transform_attr,
unsigned long flags);
/** @} */
@@ -212,13 +309,84 @@ hwloc_distances_obj_pair_values(struct hwloc_distances_s *distances,
/** \defgroup hwlocality_distances_add Add or remove distances between objects
/** \defgroup hwlocality_distances_add Add distances between objects
*
* The usual way to add distances is:
* \code
* hwloc_distances_add_handle_t handle;
* int err = -1;
* handle = hwloc_distances_add_create(topology, "name", kind, 0);
* if (handle) {
* err = hwloc_distances_add_values(topology, handle, nbobjs, objs, values, 0);
* if (!err)
* err = hwloc_distances_add_commit(topology, handle, flags);
* }
* \endcode
* If \p err is \c 0 at the end, then addition was successful.
*
* @{
*/
/** \brief Handle to a new distances structure during its addition to the topology. */
typedef void * hwloc_distances_add_handle_t;
/** \brief Create a new empty distances structure.
*
* Create an empty distances structure
* to be filled with hwloc_distances_add_values()
* and then committed with hwloc_distances_add_commit().
*
* Parameter \p name is optional, it may be \c NULL.
* Otherwise, it will be copied internally and may later be freed by the caller.
*
* \p kind specifies the kind of distance as a OR'ed set of ::hwloc_distances_kind_e.
* Kind ::HWLOC_DISTANCES_KIND_HETEROGENEOUS_TYPES will be automatically set
* according to objects having different types in hwloc_distances_add_values().
*
* \p flags must be \c 0 for now.
*
* \return A hwloc_distances_add_handle_t that should then be passed
* to hwloc_distances_add_values() and hwloc_distances_add_commit().
*
* \return \c NULL on error.
*/
HWLOC_DECLSPEC hwloc_distances_add_handle_t
hwloc_distances_add_create(hwloc_topology_t topology,
const char *name, unsigned long kind,
unsigned long flags);
/** \brief Specify the objects and values in a new empty distances structure.
*
* Specify the objects and values for a new distances structure
* that was returned as a handle by hwloc_distances_add_create().
* The structure must then be committed with hwloc_distances_add_commit().
*
* The number of objects is \p nbobjs and the array of objects is \p objs.
* Distance values are stored as a one-dimension array in \p values.
* The distance from object i to object j is in slot i*nbobjs+j.
*
* \p nbobjs must be at least 2.
*
* Arrays \p objs and \p values will be copied internally,
* they may later be freed by the caller.
*
* On error, the temporary distances structure and its content are destroyed.
*
* \p flags must be \c 0 for now.
*
* \return \c 0 on success.
* \return \c -1 on error.
*/
HWLOC_DECLSPEC int hwloc_distances_add_values(hwloc_topology_t topology,
hwloc_distances_add_handle_t handle,
unsigned nbobjs, hwloc_obj_t *objs,
hwloc_uint64_t *values,
unsigned long flags);
/** \brief Flags for adding a new distances to a topology. */
enum hwloc_distances_add_flag_e {
/** \brief Try to group objects based on the newly provided distance information.
* This is ignored for distances between objects of different types.
* \hideinitializer
*/
HWLOC_DISTANCES_ADD_FLAG_GROUP = (1UL<<0),
@@ -230,23 +398,33 @@ enum hwloc_distances_add_flag_e {
HWLOC_DISTANCES_ADD_FLAG_GROUP_INACCURATE = (1UL<<1)
};
/** \brief Provide a new distance matrix.
/** \brief Commit a new distances structure.
*
* Provide the matrix of distances between a set of objects given by \p nbobjs
* and the \p objs array. \p nbobjs must be at least 2.
* The distances are stored as a one-dimension array in \p values.
* The distance from object i to object j is in slot i*nbobjs+j.
* This function finalizes the distances structure and inserts in it the topology.
*
* \p kind specifies the kind of distance as a OR'ed set of ::hwloc_distances_kind_e.
* Kind ::HWLOC_DISTANCES_KIND_HETEROGENEOUS_TYPES will be automatically added
* if objects of different types are given.
* Parameter \p handle was previously returned by hwloc_distances_add_create().
* Then objects and values were specified with hwloc_distances_add_values().
*
* \p flags configures the behavior of the function using an optional OR'ed set of
* ::hwloc_distances_add_flag_e.
* It may be used to request the grouping of existing objects based on distances.
*
* On error, the temporary distances structure and its content are destroyed.
*
* \return \c 0 on success.
* \return \c -1 on error.
*/
HWLOC_DECLSPEC int hwloc_distances_add_commit(hwloc_topology_t topology,
hwloc_distances_add_handle_t handle,
unsigned long flags);
/** @} */
/** \defgroup hwlocality_distances_remove Remove distances between objects
* @{
*/
HWLOC_DECLSPEC int hwloc_distances_add(hwloc_topology_t topology,
unsigned nbobjs, hwloc_obj_t *objs, hwloc_uint64_t *values,
unsigned long kind, unsigned long flags);
/** \brief Remove all distance matrices from a topology.
*

View File

@@ -1,6 +1,6 @@
/*
* Copyright © 2012 Blue Brain Project, EPFL. All rights reserved.
* Copyright © 2012-2013 Inria. All rights reserved.
* Copyright © 2012-2021 Inria. All rights reserved.
* See COPYING in top-level directory.
*/
@@ -39,9 +39,9 @@ extern "C" {
/** \brief Get the hwloc OS device object corresponding to the
* OpenGL display given by port and device index.
*
* Return the OS device object describing the OpenGL display
* \return The hwloc OS device object describing the OpenGL display
* whose port (server) is \p port and device (screen) is \p device.
* Return NULL if there is none.
* \return \c NULL if none could be found.
*
* The topology \p topology does not necessarily have to match the current
* machine. For instance the topology may be an XML import of a remote host.
@@ -70,9 +70,9 @@ hwloc_gl_get_display_osdev_by_port_device(hwloc_topology_t topology,
/** \brief Get the hwloc OS device object corresponding to the
* OpenGL display given by name.
*
* Return the OS device object describing the OpenGL display
* \return The hwloc OS device object describing the OpenGL display
* whose name is \p name, built as ":port.device" such as ":0.0" .
* Return NULL if there is none.
* \return \c NULL if none could be found.
*
* The topology \p topology does not necessarily have to match the current
* machine. For instance the topology may be an XML import of a remote host.
@@ -99,9 +99,10 @@ hwloc_gl_get_display_osdev_by_name(hwloc_topology_t topology,
/** \brief Get the OpenGL display port and device corresponding
* to the given hwloc OS object.
*
* Return the OpenGL display port (server) in \p port and device (screen)
* Retrieves the OpenGL display port (server) in \p port and device (screen)
* in \p screen that correspond to the given hwloc OS device object.
* Return \c -1 if there is none.
*
* \return \c -1 if none could be found.
*
* The topology \p topology does not necessarily have to match the current
* machine. For instance the topology may be an XML import of a remote host.

View File

@@ -1,6 +1,6 @@
/*
* Copyright © 2009 CNRS
* Copyright © 2009-2013 inria. All rights reserved.
* Copyright © 2009-2020 Inria. All rights reserved.
* Copyright © 2009-2011 Université Bordeaux
* Copyright © 2011 Cisco Systems, Inc. All rights reserved.
* See COPYING in top-level directory.
@@ -22,7 +22,7 @@
#include <assert.h>
#if !defined _GNU_SOURCE || !defined _SCHED_H || (!defined CPU_SETSIZE && !defined sched_priority)
#if !defined _GNU_SOURCE || (!defined _SCHED_H && !defined _SCHED_H_) || (!defined CPU_SETSIZE && !defined sched_priority)
#error Please make sure to include sched.h before including glibc-sched.h, and define _GNU_SOURCE before any inclusion of sched.h
#endif

View File

@@ -1,6 +1,6 @@
/*
* Copyright © 2009 CNRS
* Copyright © 2009-2020 Inria. All rights reserved.
* Copyright © 2009-2022 Inria. All rights reserved.
* Copyright © 2009-2012 Université Bordeaux
* Copyright © 2009-2010 Cisco Systems, Inc. All rights reserved.
* See COPYING in top-level directory.
@@ -807,6 +807,49 @@ hwloc_get_obj_below_array_by_type (hwloc_topology_t topology, int nr, hwloc_obj_
return obj;
}
/** \brief Return an object of a different type with same locality.
*
* If the source object \p src is a normal or memory type,
* this function returns an object of type \p type with same
* CPU and node sets, either below or above in the hierarchy.
*
* If the source object \p src is a PCI or an OS device within a PCI
* device, the function may either return that PCI device, or another
* OS device in the same PCI parent.
* This may for instance be useful for converting between OS devices
* such as "nvml0" or "rsmi1" used in distance structures into the
* the PCI device, or the CUDA or OpenCL OS device that correspond
* to the same physical card.
*
* If not \c NULL, parameter \p subtype only select objects whose
* subtype attribute exists and is \p subtype (case-insensitively),
* for instance "OpenCL" or "CUDA".
*
* If not \c NULL, parameter \p nameprefix only selects objects whose
* name attribute exists and starts with \p nameprefix (case-insensitively),
* for instance "rsmi" for matching "rsmi0".
*
* If multiple objects match, the first one is returned.
*
* This function will not walk the hierarchy across bridges since
* the PCI locality may become different.
* This function cannot also convert between normal/memory objects
* and I/O or Misc objects.
*
* \p flags must be \c 0 for now.
*
* \return An object with identical locality,
* matching \p subtype and \p nameprefix if any.
*
* \return \c NULL if no matching object could be found,
* or if the source object and target type are incompatible,
* for instance if converting between CPU and I/O objects.
*/
HWLOC_DECLSPEC hwloc_obj_t
hwloc_get_obj_with_same_locality(hwloc_topology_t topology, hwloc_obj_t src,
hwloc_obj_type_t type, const char *subtype, const char *nameprefix,
unsigned long flags);
/** @} */
@@ -843,9 +886,6 @@ enum hwloc_distrib_flags_e {
* \p flags should be 0 or a OR'ed set of ::hwloc_distrib_flags_e.
*
* \note This function requires the \p roots objects to have a CPU set.
*
* \note This function replaces the now deprecated hwloc_distribute()
* and hwloc_distributev() functions.
*/
static __hwloc_inline int
hwloc_distrib(hwloc_topology_t topology,
@@ -872,8 +912,8 @@ hwloc_distrib(hwloc_topology_t topology,
unsigned chunk, weight;
hwloc_obj_t root = roots[flags & HWLOC_DISTRIB_FLAG_REVERSE ? n_roots-1-i : i];
hwloc_cpuset_t cpuset = root->cpuset;
if (root->type == HWLOC_OBJ_NUMANODE)
/* NUMANodes have same cpuset as their parent, but we need normal objects below */
while (!hwloc_obj_type_is_normal(root->type))
/* If memory/io/misc, walk up to normal parent */
root = root->parent;
weight = (unsigned) hwloc_bitmap_weight(cpuset);
if (!weight)
@@ -919,7 +959,7 @@ hwloc_distrib(hwloc_topology_t topology,
/** \brief Get complete CPU set
*
* \return the complete CPU set of logical processors of the system.
* \return the complete CPU set of processors of the system.
*
* \note The returned cpuset is not newly allocated and should thus not be
* changed or freed; hwloc_bitmap_dup() must be used to obtain a local copy.
@@ -931,7 +971,7 @@ hwloc_topology_get_complete_cpuset(hwloc_topology_t topology) __hwloc_attribute_
/** \brief Get topology CPU set
*
* \return the CPU set of logical processors of the system for which hwloc
* \return the CPU set of processors of the system for which hwloc
* provides topology information. This is equivalent to the cpuset of the
* system object.
*
@@ -945,7 +985,7 @@ hwloc_topology_get_topology_cpuset(hwloc_topology_t topology) __hwloc_attribute_
/** \brief Get allowed CPU set
*
* \return the CPU set of allowed logical processors of the system.
* \return the CPU set of allowed processors of the system.
*
* \note If the topology flag ::HWLOC_TOPOLOGY_FLAG_INCLUDE_DISALLOWED was not set,
* this is identical to hwloc_topology_get_topology_cpuset(), which means

View File

@@ -1,136 +0,0 @@
/*
* Copyright © 2013-2016 Inria. All rights reserved.
* See COPYING in top-level directory.
*/
/** \file
* \brief Macros to help interaction between hwloc and Intel Xeon Phi (MIC).
*
* Applications that use both hwloc and Intel Xeon Phi (MIC) may want to
* include this file so as to get topology information for MIC devices.
*/
#ifndef HWLOC_INTEL_MIC_H
#define HWLOC_INTEL_MIC_H
#include "hwloc.h"
#include "hwloc/autogen/config.h"
#include "hwloc/helper.h"
#ifdef HWLOC_LINUX_SYS
#include "hwloc/linux.h"
#include <dirent.h>
#include <string.h>
#endif
#include <stdio.h>
#include <stdlib.h>
#ifdef __cplusplus
extern "C" {
#endif
/** \defgroup hwlocality_intel_mic Interoperability with Intel Xeon Phi (MIC)
*
* This interface offers ways to retrieve topology information about
* Intel Xeon Phi (MIC) devices.
*
* @{
*/
/** \brief Get the CPU set of logical processors that are physically
* close to MIC device whose index is \p idx.
*
* Return the CPU set describing the locality of the MIC device whose index is \p idx.
*
* Topology \p topology and device index \p idx must match the local machine.
* I/O devices detection is not needed in the topology.
*
* The function only returns the locality of the device.
* If more information about the device is needed, OS objects should
* be used instead, see hwloc_intel_mic_get_device_osdev_by_index().
*
* This function is currently only implemented in a meaningful way for
* Linux; other systems will simply get a full cpuset.
*/
static __hwloc_inline int
hwloc_intel_mic_get_device_cpuset(hwloc_topology_t topology __hwloc_attribute_unused,
int idx __hwloc_attribute_unused,
hwloc_cpuset_t set)
{
#ifdef HWLOC_LINUX_SYS
/* If we're on Linux, use the sysfs mechanism to get the local cpus */
#define HWLOC_INTEL_MIC_DEVICE_SYSFS_PATH_MAX 128
char path[HWLOC_INTEL_MIC_DEVICE_SYSFS_PATH_MAX];
DIR *sysdir = NULL;
struct dirent *dirent;
unsigned pcibus, pcidev, pcifunc;
if (!hwloc_topology_is_thissystem(topology)) {
errno = EINVAL;
return -1;
}
sprintf(path, "/sys/class/mic/mic%d", idx);
sysdir = opendir(path);
if (!sysdir)
return -1;
while ((dirent = readdir(sysdir)) != NULL) {
if (sscanf(dirent->d_name, "pci_%02x:%02x.%02x", &pcibus, &pcidev, &pcifunc) == 3) {
sprintf(path, "/sys/class/mic/mic%d/pci_%02x:%02x.%02x/local_cpus", idx, pcibus, pcidev, pcifunc);
if (hwloc_linux_read_path_as_cpumask(path, set) < 0
|| hwloc_bitmap_iszero(set))
hwloc_bitmap_copy(set, hwloc_topology_get_complete_cpuset(topology));
break;
}
}
closedir(sysdir);
#else
/* Non-Linux systems simply get a full cpuset */
hwloc_bitmap_copy(set, hwloc_topology_get_complete_cpuset(topology));
#endif
return 0;
}
/** \brief Get the hwloc OS device object corresponding to the
* MIC device for the given index.
*
* Return the OS device object describing the MIC device whose index is \p idx.
* Return NULL if there is none.
*
* The topology \p topology does not necessarily have to match the current
* machine. For instance the topology may be an XML import of a remote host.
* I/O devices detection must be enabled in the topology.
*
* \note The corresponding PCI device object can be obtained by looking
* at the OS device parent object.
*/
static __hwloc_inline hwloc_obj_t
hwloc_intel_mic_get_device_osdev_by_index(hwloc_topology_t topology,
unsigned idx)
{
hwloc_obj_t osdev = NULL;
while ((osdev = hwloc_get_next_osdev(topology, osdev)) != NULL) {
if (HWLOC_OBJ_OSDEV_COPROC == osdev->attr->osdev.type
&& osdev->name
&& !strncmp("mic", osdev->name, 3)
&& atoi(osdev->name + 3) == (int) idx)
return osdev;
}
return NULL;
}
/** @} */
#ifdef __cplusplus
} /* extern "C" */
#endif
#endif /* HWLOC_INTEL_MIC_H */

View File

@@ -0,0 +1,157 @@
/*
* Copyright © 2021 Inria. All rights reserved.
* See COPYING in top-level directory.
*/
/** \file
* \brief Macros to help interaction between hwloc and the oneAPI Level Zero interface.
*
* Applications that use both hwloc and Level Zero may want to
* include this file so as to get topology information for L0 devices.
*/
#ifndef HWLOC_LEVELZERO_H
#define HWLOC_LEVELZERO_H
#include "hwloc.h"
#include "hwloc/autogen/config.h"
#include "hwloc/helper.h"
#ifdef HWLOC_LINUX_SYS
#include "hwloc/linux.h"
#endif
#include <level_zero/ze_api.h>
#include <level_zero/zes_api.h>
#ifdef __cplusplus
extern "C" {
#endif
/** \defgroup hwlocality_levelzero Interoperability with the oneAPI Level Zero interface.
*
* This interface offers ways to retrieve topology information about
* devices managed by the Level Zero API.
*
* @{
*/
/** \brief Get the CPU set of logical processors that are physically
* close to the Level Zero device \p device
*
* Store in \p set the CPU-set describing the locality of
* the Level Zero device \p device.
*
* Topology \p topology and device \p device must match the local machine.
* The Level Zero must have been initialized with Sysman enabled
* (ZES_ENABLE_SYSMAN=1 in the environment).
* I/O devices detection and the Level Zero component are not needed in the
* topology.
*
* The function only returns the locality of the device.
* If more information about the device is needed, OS objects should
* be used instead, see hwloc_levelzero_get_device_osdev().
*
* This function is currently only implemented in a meaningful way for
* Linux; other systems will simply get a full cpuset.
*/
static __hwloc_inline int
hwloc_levelzero_get_device_cpuset(hwloc_topology_t topology __hwloc_attribute_unused,
ze_device_handle_t device, hwloc_cpuset_t set)
{
#ifdef HWLOC_LINUX_SYS
/* If we're on Linux, use the sysfs mechanism to get the local cpus */
#define HWLOC_LEVELZERO_DEVICE_SYSFS_PATH_MAX 128
char path[HWLOC_LEVELZERO_DEVICE_SYSFS_PATH_MAX];
zes_pci_properties_t pci;
zes_device_handle_t sdevice = device;
ze_result_t res;
if (!hwloc_topology_is_thissystem(topology)) {
errno = EINVAL;
return -1;
}
res = zesDevicePciGetProperties(sdevice, &pci);
if (res != ZE_RESULT_SUCCESS) {
errno = EINVAL;
return -1;
}
sprintf(path, "/sys/bus/pci/devices/%04x:%02x:%02x.%01x/local_cpus",
pci.address.domain, pci.address.bus, pci.address.device, pci.address.function);
if (hwloc_linux_read_path_as_cpumask(path, set) < 0
|| hwloc_bitmap_iszero(set))
hwloc_bitmap_copy(set, hwloc_topology_get_complete_cpuset(topology));
#else
/* Non-Linux systems simply get a full cpuset */
hwloc_bitmap_copy(set, hwloc_topology_get_complete_cpuset(topology));
#endif
return 0;
}
/** \brief Get the hwloc OS device object corresponding to Level Zero device
* \p device.
*
* \return The hwloc OS device object that describes the given Level Zero device \p device.
* \return \c NULL if none could be found.
*
* Topology \p topology and device \p dv_ind must match the local machine.
* I/O devices detection and the Level Zero component must be enabled in the
* topology. If not, the locality of the object may still be found using
* hwloc_levelzero_get_device_cpuset().
*
* \note The corresponding hwloc PCI device may be found by looking
* at the result parent pointer (unless PCI devices are filtered out).
*/
static __hwloc_inline hwloc_obj_t
hwloc_levelzero_get_device_osdev(hwloc_topology_t topology, ze_device_handle_t device)
{
zes_device_handle_t sdevice = device;
zes_pci_properties_t pci;
ze_result_t res;
hwloc_obj_t osdev;
if (!hwloc_topology_is_thissystem(topology)) {
errno = EINVAL;
return NULL;
}
res = zesDevicePciGetProperties(sdevice, &pci);
if (res != ZE_RESULT_SUCCESS) {
/* L0 was likely initialized without sysman, don't bother */
errno = EINVAL;
return NULL;
}
osdev = NULL;
while ((osdev = hwloc_get_next_osdev(topology, osdev)) != NULL) {
hwloc_obj_t pcidev = osdev->parent;
if (strncmp(osdev->name, "ze", 2))
continue;
if (pcidev
&& pcidev->type == HWLOC_OBJ_PCI_DEVICE
&& pcidev->attr->pcidev.domain == pci.address.domain
&& pcidev->attr->pcidev.bus == pci.address.bus
&& pcidev->attr->pcidev.dev == pci.address.device
&& pcidev->attr->pcidev.func == pci.address.function)
return osdev;
/* FIXME: when we'll have serialnumber, try it in case PCI is filtered-out */
}
return NULL;
}
/** @} */
#ifdef __cplusplus
} /* extern "C" */
#endif
#endif /* HWLOC_LEVELZERO_H */

View File

@@ -1,6 +1,6 @@
/*
* Copyright © 2009 CNRS
* Copyright © 2009-2016 Inria. All rights reserved.
* Copyright © 2009-2021 Inria. All rights reserved.
* Copyright © 2009-2011 Université Bordeaux
* See COPYING in top-level directory.
*/
@@ -44,6 +44,10 @@ extern "C" {
HWLOC_DECLSPEC int hwloc_linux_set_tid_cpubind(hwloc_topology_t topology, pid_t tid, hwloc_const_cpuset_t set);
/** \brief Get the current binding of thread \p tid
*
* The CPU-set \p set (previously allocated by the caller)
* is filled with the list of PUs which the thread
* was last bound to.
*
* The behavior is exactly the same as the Linux sched_getaffinity system call,
* but uses a hwloc cpuset.
@@ -54,6 +58,9 @@ HWLOC_DECLSPEC int hwloc_linux_set_tid_cpubind(hwloc_topology_t topology, pid_t
HWLOC_DECLSPEC int hwloc_linux_get_tid_cpubind(hwloc_topology_t topology, pid_t tid, hwloc_cpuset_t set);
/** \brief Get the last physical CPU where thread \p tid ran.
*
* The CPU-set \p set (previously allocated by the caller)
* is filled with the PU which the thread last ran on.
*
* \note This is equivalent to calling hwloc_get_proc_last_cpu_location() with
* ::HWLOC_CPUBIND_THREAD as flags.

View File

@@ -0,0 +1,518 @@
/*
* Copyright © 2019-2022 Inria. All rights reserved.
* See COPYING in top-level directory.
*/
/** \file
* \brief Memory node attributes.
*/
#ifndef HWLOC_MEMATTR_H
#define HWLOC_MEMATTR_H
#include "hwloc.h"
#ifdef __cplusplus
extern "C" {
#elif 0
}
#endif
/** \defgroup hwlocality_memattrs Comparing memory node attributes for finding where to allocate on
*
* Platforms with heterogeneous memory require ways to decide whether
* a buffer should be allocated on "fast" memory (such as HBM),
* "normal" memory (DDR) or even "slow" but large-capacity memory
* (non-volatile memory).
* These memory nodes are called "Targets" while the CPU accessing them
* is called the "Initiator". Access performance depends on their
* locality (NUMA platforms) as well as the intrinsic performance
* of the targets (heterogeneous platforms).
*
* The following attributes describe the performance of memory accesses
* from an Initiator to a memory Target, for instance their latency
* or bandwidth.
* Initiators performing these memory accesses are usually some PUs or Cores
* (described as a CPU set).
* Hence a Core may choose where to allocate a memory buffer by comparing
* the attributes of different target memory nodes nearby.
*
* There are also some attributes that are system-wide.
* Their value does not depend on a specific initiator performing
* an access.
* The memory node Capacity is an example of such attribute without
* initiator.
*
* One way to use this API is to start with a cpuset describing the Cores where
* a program is bound. The best target NUMA node for allocating memory in this
* program on these Cores may be obtained by passing this cpuset as an initiator
* to hwloc_memattr_get_best_target() with the relevant memory attribute.
* For instance, if the code is latency limited, use the Latency attribute.
*
* A more flexible approach consists in getting the list of local NUMA nodes
* by passing this cpuset to hwloc_get_local_numanode_objs().
* Attribute values for these nodes, if any, may then be obtained with
* hwloc_memattr_get_value() and manually compared with the desired criteria.
*
* \sa An example is available in doc/examples/memory-attributes.c in the source tree.
*
* \note The API also supports specific objects as initiator,
* but it is currently not used internally by hwloc.
* Users may for instance use it to provide custom performance
* values for host memory accesses performed by GPUs.
*
* \note The interface actually also accepts targets that are not NUMA nodes.
* @{
*/
/** \brief Memory node attributes. */
enum hwloc_memattr_id_e {
/** \brief
* The \"Capacity\" is returned in bytes (local_memory attribute in objects).
*
* Best capacity nodes are nodes with <b>higher capacity</b>.
*
* No initiator is involved when looking at this attribute.
* The corresponding attribute flags are ::HWLOC_MEMATTR_FLAG_HIGHER_FIRST.
* \hideinitializer
*/
HWLOC_MEMATTR_ID_CAPACITY = 0,
/** \brief
* The \"Locality\" is returned as the number of PUs in that locality
* (e.g. the weight of its cpuset).
*
* Best locality nodes are nodes with <b>smaller locality</b>
* (nodes that are local to very few PUs).
* Poor locality nodes are nodes with larger locality
* (nodes that are local to the entire machine).
*
* No initiator is involved when looking at this attribute.
* The corresponding attribute flags are ::HWLOC_MEMATTR_FLAG_HIGHER_FIRST.
* \hideinitializer
*/
HWLOC_MEMATTR_ID_LOCALITY = 1,
/** \brief
* The \"Bandwidth\" is returned in MiB/s, as seen from the given initiator location.
*
* Best bandwidth nodes are nodes with <b>higher bandwidth</b>.
*
* The corresponding attribute flags are ::HWLOC_MEMATTR_FLAG_HIGHER_FIRST
* and ::HWLOC_MEMATTR_FLAG_NEED_INITIATOR.
*
* This is the average bandwidth for read and write accesses. If the platform
* provides individual read and write bandwidths but no explicit average value,
* hwloc computes and returns the average.
* \hideinitializer
*/
HWLOC_MEMATTR_ID_BANDWIDTH = 2,
/** \brief
* The \"ReadBandwidth\" is returned in MiB/s, as seen from the given initiator location.
*
* Best bandwidth nodes are nodes with <b>higher bandwidth</b>.
*
* The corresponding attribute flags are ::HWLOC_MEMATTR_FLAG_HIGHER_FIRST
* and ::HWLOC_MEMATTR_FLAG_NEED_INITIATOR.
* \hideinitializer
*/
HWLOC_MEMATTR_ID_READ_BANDWIDTH = 4,
/** \brief
* The \"WriteBandwidth\" is returned in MiB/s, as seen from the given initiator location.
*
* Best bandwidth nodes are nodes with <b>higher bandwidth</b>.
*
* The corresponding attribute flags are ::HWLOC_MEMATTR_FLAG_HIGHER_FIRST
* and ::HWLOC_MEMATTR_FLAG_NEED_INITIATOR.
* \hideinitializer
*/
HWLOC_MEMATTR_ID_WRITE_BANDWIDTH = 5,
/** \brief
* The \"Latency\" is returned as nanoseconds, as seen from the given initiator location.
*
* Best latency nodes are nodes with <b>smaller latency</b>.
*
* The corresponding attribute flags are ::HWLOC_MEMATTR_FLAG_LOWER_FIRST
* and ::HWLOC_MEMATTR_FLAG_NEED_INITIATOR.
*
* This is the average latency for read and write accesses. If the platform
* provides individual read and write latencies but no explicit average value,
* hwloc computes and returns the average.
* \hideinitializer
*/
HWLOC_MEMATTR_ID_LATENCY = 3,
/** \brief
* The \"ReadLatency\" is returned as nanoseconds, as seen from the given initiator location.
*
* Best latency nodes are nodes with <b>smaller latency</b>.
*
* The corresponding attribute flags are ::HWLOC_MEMATTR_FLAG_LOWER_FIRST
* and ::HWLOC_MEMATTR_FLAG_NEED_INITIATOR.
* \hideinitializer
*/
HWLOC_MEMATTR_ID_READ_LATENCY = 6,
/** \brief
* The \"WriteLatency\" is returned as nanoseconds, as seen from the given initiator location.
*
* Best latency nodes are nodes with <b>smaller latency</b>.
*
* The corresponding attribute flags are ::HWLOC_MEMATTR_FLAG_LOWER_FIRST
* and ::HWLOC_MEMATTR_FLAG_NEED_INITIATOR.
* \hideinitializer
*/
HWLOC_MEMATTR_ID_WRITE_LATENCY = 7,
/* TODO persistence? */
HWLOC_MEMATTR_ID_MAX /**< \private Sentinel value */
};
/** \brief A memory attribute identifier.
* May be either one of ::hwloc_memattr_id_e or a new id returned by hwloc_memattr_register().
*/
typedef unsigned hwloc_memattr_id_t;
/** \brief Return the identifier of the memory attribute with the given name.
*/
HWLOC_DECLSPEC int
hwloc_memattr_get_by_name(hwloc_topology_t topology,
const char *name,
hwloc_memattr_id_t *id);
/** \brief Type of location. */
enum hwloc_location_type_e {
/** \brief Location is given as a cpuset, in the location cpuset union field. \hideinitializer */
HWLOC_LOCATION_TYPE_CPUSET = 1,
/** \brief Location is given as an object, in the location object union field. \hideinitializer */
HWLOC_LOCATION_TYPE_OBJECT = 0
};
/** \brief Where to measure attributes from. */
struct hwloc_location {
/** \brief Type of location. */
enum hwloc_location_type_e type;
/** \brief Actual location. */
union hwloc_location_u {
/** \brief Location as a cpuset, when the location type is ::HWLOC_LOCATION_TYPE_CPUSET. */
hwloc_cpuset_t cpuset;
/** \brief Location as an object, when the location type is ::HWLOC_LOCATION_TYPE_OBJECT. */
hwloc_obj_t object;
} location;
};
/** \brief Flags for selecting target NUMA nodes. */
enum hwloc_local_numanode_flag_e {
/** \brief Select NUMA nodes whose locality is larger than the given cpuset.
* For instance, if a single PU (or its cpuset) is given in \p initiator,
* select all nodes close to the package that contains this PU.
* \hideinitializer
*/
HWLOC_LOCAL_NUMANODE_FLAG_LARGER_LOCALITY = (1UL<<0),
/** \brief Select NUMA nodes whose locality is smaller than the given cpuset.
* For instance, if a package (or its cpuset) is given in \p initiator,
* also select nodes that are attached to only a half of that package.
* \hideinitializer
*/
HWLOC_LOCAL_NUMANODE_FLAG_SMALLER_LOCALITY = (1UL<<1),
/** \brief Select all NUMA nodes in the topology.
* The initiator \p initiator is ignored.
* \hideinitializer
*/
HWLOC_LOCAL_NUMANODE_FLAG_ALL = (1UL<<2)
};
/** \brief Return an array of local NUMA nodes.
*
* By default only select the NUMA nodes whose locality is exactly
* the given \p location. More nodes may be selected if additional flags
* are given as a OR'ed set of ::hwloc_local_numanode_flag_e.
*
* If \p location is given as an explicit object, its CPU set is used
* to find NUMA nodes with the corresponding locality.
* If the object does not have a CPU set (e.g. I/O object), the CPU
* parent (where the I/O object is attached) is used.
*
* On input, \p nr points to the number of nodes that may be stored
* in the \p nodes array.
* On output, \p nr will be changed to the number of stored nodes,
* or the number of nodes that would have been stored if there were
* enough room.
*
* \note Some of these NUMA nodes may not have any memory attribute
* values and hence not be reported as actual targets in other functions.
*
* \note The number of NUMA nodes in the topology (obtained by
* hwloc_bitmap_weight() on the root object nodeset) may be used
* to allocate the \p nodes array.
*
* \note When an object CPU set is given as locality, for instance a Package,
* and when flags contain both ::HWLOC_LOCAL_NUMANODE_FLAG_LARGER_LOCALITY
* and ::HWLOC_LOCAL_NUMANODE_FLAG_SMALLER_LOCALITY,
* the returned array corresponds to the nodeset of that object.
*/
HWLOC_DECLSPEC int
hwloc_get_local_numanode_objs(hwloc_topology_t topology,
struct hwloc_location *location,
unsigned *nr,
hwloc_obj_t *nodes,
unsigned long flags);
/** \brief Return an attribute value for a specific target NUMA node.
*
* If the attribute does not relate to a specific initiator
* (it does not have the flag ::HWLOC_MEMATTR_FLAG_NEED_INITIATOR),
* location \p initiator is ignored and may be \c NULL.
*
* \p flags must be \c 0 for now.
*
* \note The initiator \p initiator should be of type ::HWLOC_LOCATION_TYPE_CPUSET
* when refering to accesses performed by CPU cores.
* ::HWLOC_LOCATION_TYPE_OBJECT is currently unused internally by hwloc,
* but users may for instance use it to provide custom information about
* host memory accesses performed by GPUs.
*/
HWLOC_DECLSPEC int
hwloc_memattr_get_value(hwloc_topology_t topology,
hwloc_memattr_id_t attribute,
hwloc_obj_t target_node,
struct hwloc_location *initiator,
unsigned long flags,
hwloc_uint64_t *value);
/** \brief Return the best target NUMA node for the given attribute and initiator.
*
* If the attribute does not relate to a specific initiator
* (it does not have the flag ::HWLOC_MEMATTR_FLAG_NEED_INITIATOR),
* location \p initiator is ignored and may be \c NULL.
*
* If \p value is non \c NULL, the corresponding value is returned there.
*
* If multiple targets have the same attribute values, only one is
* returned (and there is no way to clarify how that one is chosen).
* Applications that want to detect targets with identical/similar
* values, or that want to look at values for multiple attributes,
* should rather get all values using hwloc_memattr_get_value()
* and manually select the target they consider the best.
*
* \p flags must be \c 0 for now.
*
* If there are no matching targets, \c -1 is returned with \p errno set to \c ENOENT;
*
* \note The initiator \p initiator should be of type ::HWLOC_LOCATION_TYPE_CPUSET
* when refering to accesses performed by CPU cores.
* ::HWLOC_LOCATION_TYPE_OBJECT is currently unused internally by hwloc,
* but users may for instance use it to provide custom information about
* host memory accesses performed by GPUs.
*/
HWLOC_DECLSPEC int
hwloc_memattr_get_best_target(hwloc_topology_t topology,
hwloc_memattr_id_t attribute,
struct hwloc_location *initiator,
unsigned long flags,
hwloc_obj_t *best_target, hwloc_uint64_t *value);
/** \brief Return the best initiator for the given attribute and target NUMA node.
*
* If the attribute does not relate to a specific initiator
* (it does not have the flag ::HWLOC_MEMATTR_FLAG_NEED_INITIATOR),
* \c -1 is returned and \p errno is set to \c EINVAL.
*
* If \p value is non \c NULL, the corresponding value is returned there.
*
* If multiple initiators have the same attribute values, only one is
* returned (and there is no way to clarify how that one is chosen).
* Applications that want to detect initiators with identical/similar
* values, or that want to look at values for multiple attributes,
* should rather get all values using hwloc_memattr_get_value()
* and manually select the initiator they consider the best.
*
* The returned initiator should not be modified or freed,
* it belongs to the topology.
*
* \p flags must be \c 0 for now.
*
* If there are no matching initiators, \c -1 is returned with \p errno set to \c ENOENT;
*/
HWLOC_DECLSPEC int
hwloc_memattr_get_best_initiator(hwloc_topology_t topology,
hwloc_memattr_id_t attribute,
hwloc_obj_t target,
unsigned long flags,
struct hwloc_location *best_initiator, hwloc_uint64_t *value);
/** @} */
/** \defgroup hwlocality_memattrs_manage Managing memory attributes
* @{
*/
/** \brief Return the name of a memory attribute.
*/
HWLOC_DECLSPEC int
hwloc_memattr_get_name(hwloc_topology_t topology,
hwloc_memattr_id_t attribute,
const char **name);
/** \brief Return the flags of the given attribute.
*
* Flags are a OR'ed set of ::hwloc_memattr_flag_e.
*/
HWLOC_DECLSPEC int
hwloc_memattr_get_flags(hwloc_topology_t topology,
hwloc_memattr_id_t attribute,
unsigned long *flags);
/** \brief Memory attribute flags.
* Given to hwloc_memattr_register() and returned by hwloc_memattr_get_flags().
*/
enum hwloc_memattr_flag_e {
/** \brief The best nodes for this memory attribute are those with the higher values.
* For instance Bandwidth.
*/
HWLOC_MEMATTR_FLAG_HIGHER_FIRST = (1UL<<0),
/** \brief The best nodes for this memory attribute are those with the lower values.
* For instance Latency.
*/
HWLOC_MEMATTR_FLAG_LOWER_FIRST = (1UL<<1),
/** \brief The value returned for this memory attribute depends on the given initiator.
* For instance Bandwidth and Latency, but not Capacity.
*/
HWLOC_MEMATTR_FLAG_NEED_INITIATOR = (1UL<<2)
};
/** \brief Register a new memory attribute.
*
* Add a specific memory attribute that is not defined in ::hwloc_memattr_id_e.
* Flags are a OR'ed set of ::hwloc_memattr_flag_e. It must contain at least
* one of ::HWLOC_MEMATTR_FLAG_HIGHER_FIRST or ::HWLOC_MEMATTR_FLAG_LOWER_FIRST.
*/
HWLOC_DECLSPEC int
hwloc_memattr_register(hwloc_topology_t topology,
const char *name,
unsigned long flags,
hwloc_memattr_id_t *id);
/** \brief Set an attribute value for a specific target NUMA node.
*
* If the attribute does not relate to a specific initiator
* (it does not have the flag ::HWLOC_MEMATTR_FLAG_NEED_INITIATOR),
* location \p initiator is ignored and may be \c NULL.
*
* The initiator will be copied into the topology,
* the caller should free anything allocated to store the initiator,
* for instance the cpuset.
*
* \p flags must be \c 0 for now.
*
* \note The initiator \p initiator should be of type ::HWLOC_LOCATION_TYPE_CPUSET
* when referring to accesses performed by CPU cores.
* ::HWLOC_LOCATION_TYPE_OBJECT is currently unused internally by hwloc,
* but users may for instance use it to provide custom information about
* host memory accesses performed by GPUs.
*/
HWLOC_DECLSPEC int
hwloc_memattr_set_value(hwloc_topology_t topology,
hwloc_memattr_id_t attribute,
hwloc_obj_t target_node,
struct hwloc_location *initiator,
unsigned long flags,
hwloc_uint64_t value);
/** \brief Return the target NUMA nodes that have some values for a given attribute.
*
* Return targets for the given attribute in the \p targets array
* (for the given initiator if any).
* If \p values is not \c NULL, the corresponding attribute values
* are stored in the array it points to.
*
* On input, \p nr points to the number of targets that may be stored
* in the array \p targets (and \p values).
* On output, \p nr points to the number of targets (and values) that
* were actually found, even if some of them couldn't be stored in the array.
* Targets that couldn't be stored are ignored, but the function still
* returns success (\c 0). The caller may find out by comparing the value pointed
* by \p nr before and after the function call.
*
* The returned targets should not be modified or freed,
* they belong to the topology.
*
* Argument \p initiator is ignored if the attribute does not relate to a specific
* initiator (it does not have the flag ::HWLOC_MEMATTR_FLAG_NEED_INITIATOR).
* Otherwise \p initiator may be non \c NULL to report only targets
* that have a value for that initiator.
*
* \p flags must be \c 0 for now.
*
* \note This function is meant for tools and debugging (listing internal information)
* rather than for application queries. Applications should rather select useful
* NUMA nodes with hwloc_get_local_numanode_objs() and then look at their attribute
* values.
*
* \note The initiator \p initiator should be of type ::HWLOC_LOCATION_TYPE_CPUSET
* when referring to accesses performed by CPU cores.
* ::HWLOC_LOCATION_TYPE_OBJECT is currently unused internally by hwloc,
* but users may for instance use it to provide custom information about
* host memory accesses performed by GPUs.
*/
HWLOC_DECLSPEC int
hwloc_memattr_get_targets(hwloc_topology_t topology,
hwloc_memattr_id_t attribute,
struct hwloc_location *initiator,
unsigned long flags,
unsigned *nr, hwloc_obj_t *targets, hwloc_uint64_t *values);
/** \brief Return the initiators that have values for a given attribute for a specific target NUMA node.
*
* Return initiators for the given attribute and target node in the
* \p initiators array.
* If \p values is not \c NULL, the corresponding attribute values
* are stored in the array it points to.
*
* On input, \p nr points to the number of initiators that may be stored
* in the array \p initiators (and \p values).
* On output, \p nr points to the number of initiators (and values) that
* were actually found, even if some of them couldn't be stored in the array.
* Initiators that couldn't be stored are ignored, but the function still
* returns success (\c 0). The caller may find out by comparing the value pointed
* by \p nr before and after the function call.
*
* The returned initiators should not be modified or freed,
* they belong to the topology.
*
* \p flags must be \c 0 for now.
*
* If the attribute does not relate to a specific initiator
* (it does not have the flag ::HWLOC_MEMATTR_FLAG_NEED_INITIATOR),
* no initiator is returned.
*
* \note This function is meant for tools and debugging (listing internal information)
* rather than for application queries. Applications should rather select useful
* NUMA nodes with hwloc_get_local_numanode_objs() and then look at their attribute
* values for some relevant initiators.
*/
HWLOC_DECLSPEC int
hwloc_memattr_get_initiators(hwloc_topology_t topology,
hwloc_memattr_id_t attribute,
hwloc_obj_t target_node,
unsigned long flags,
unsigned *nr, struct hwloc_location *initiators, hwloc_uint64_t *values);
/** @} */
#ifdef __cplusplus
} /* extern "C" */
#endif
#endif /* HWLOC_MEMATTR_H */

View File

@@ -1,5 +1,5 @@
/*
* Copyright © 2012-2016 Inria. All rights reserved.
* Copyright © 2012-2021 Inria. All rights reserved.
* See COPYING in top-level directory.
*/
@@ -36,10 +36,10 @@ extern "C" {
* @{
*/
/** \brief Get the CPU set of logical processors that are physically
/** \brief Get the CPU set of processors that are physically
* close to NVML device \p device.
*
* Return the CPU set describing the locality of the NVML device \p device.
* Store in \p set the CPU-set describing the locality of the NVML device \p device.
*
* Topology \p topology and device \p device must match the local machine.
* I/O devices detection and the NVML component are not needed in the topology.
@@ -88,8 +88,8 @@ hwloc_nvml_get_device_cpuset(hwloc_topology_t topology __hwloc_attribute_unused,
/** \brief Get the hwloc OS device object corresponding to the
* NVML device whose index is \p idx.
*
* Return the OS device object describing the NVML device whose
* index is \p idx. Returns NULL if there is none.
* \return The hwloc OS device object describing the NVML device whose index is \p idx.
* \return \c NULL if none could be found.
*
* The topology \p topology does not necessarily have to match the current
* machine. For instance the topology may be an XML import of a remote host.
@@ -114,8 +114,8 @@ hwloc_nvml_get_device_osdev_by_index(hwloc_topology_t topology, unsigned idx)
/** \brief Get the hwloc OS device object corresponding to NVML device \p device.
*
* Return the hwloc OS device object that describes the given
* NVML device \p device. Return NULL if there is none.
* \return The hwloc OS device object that describes the given NVML device \p device.
* \return \c NULL if none could be found.
*
* Topology \p topology and device \p device must match the local machine.
* I/O devices detection and the NVML component must be enabled in the topology.

View File

@@ -1,5 +1,5 @@
/*
* Copyright © 2012-2019 Inria. All rights reserved.
* Copyright © 2012-2021 Inria. All rights reserved.
* Copyright © 2013, 2018 Université Bordeaux. All right reserved.
* See COPYING in top-level directory.
*/
@@ -82,9 +82,10 @@ hwloc_opencl_get_device_pci_busid(cl_device_id device,
if (CL_SUCCESS == clret
&& HWLOC_CL_DEVICE_TOPOLOGY_TYPE_PCIE_AMD == amdtopo.raw.type) {
*domain = 0; /* can't do anything better */
*bus = (unsigned) amdtopo.pcie.bus;
*dev = (unsigned) amdtopo.pcie.device;
*func = (unsigned) amdtopo.pcie.function;
/* cl_device_topology_amd stores bus ID in cl_char, dont convert those signed char directly to unsigned int */
*bus = (unsigned) (unsigned char) amdtopo.pcie.bus;
*dev = (unsigned) (unsigned char) amdtopo.pcie.device;
*func = (unsigned) (unsigned char) amdtopo.pcie.function;
return 0;
}
@@ -109,10 +110,10 @@ hwloc_opencl_get_device_pci_busid(cl_device_id device,
return -1;
}
/** \brief Get the CPU set of logical processors that are physically
/** \brief Get the CPU set of processors that are physically
* close to OpenCL device \p device.
*
* Return the CPU set describing the locality of the OpenCL device \p device.
* Store in \p set the CPU-set describing the locality of the OpenCL device \p device.
*
* Topology \p topology and device \p device must match the local machine.
* I/O devices detection and the OpenCL component are not needed in the topology.
@@ -161,10 +162,10 @@ hwloc_opencl_get_device_cpuset(hwloc_topology_t topology __hwloc_attribute_unuse
/** \brief Get the hwloc OS device object corresponding to the
* OpenCL device for the given indexes.
*
* Return the OS device object describing the OpenCL device
* \return The hwloc OS device object describing the OpenCL device
* whose platform index is \p platform_index,
* and whose device index within this platform if \p device_index.
* Return NULL if there is none.
* \return \c NULL if there is none.
*
* The topology \p topology does not necessarily have to match the current
* machine. For instance the topology may be an XML import of a remote host.
@@ -191,8 +192,9 @@ hwloc_opencl_get_device_osdev_by_index(hwloc_topology_t topology,
/** \brief Get the hwloc OS device object corresponding to OpenCL device \p deviceX.
*
* Use OpenCL device attributes to find the corresponding hwloc OS device object.
* Return NULL if there is none or if useful attributes are not available.
* \return The hwloc OS device object corresponding to the given OpenCL device \p device.
* \return \c NULL if none could be found, for instance
* if required OpenCL attributes are not available.
*
* This function currently only works on AMD and NVIDIA OpenCL devices that support
* relevant OpenCL extensions. hwloc_opencl_get_device_osdev_by_index()

View File

@@ -1,6 +1,6 @@
/*
* Copyright © 2009 CNRS
* Copyright © 2009-2016 Inria. All rights reserved.
* Copyright © 2009-2021 Inria. All rights reserved.
* Copyright © 2009-2010 Université Bordeaux
* Copyright © 2009-2011 Cisco Systems, Inc. All rights reserved.
* See COPYING in top-level directory.
@@ -41,10 +41,10 @@ extern "C" {
* @{
*/
/** \brief Get the CPU set of logical processors that are physically
/** \brief Get the CPU set of processors that are physically
* close to device \p ibdev.
*
* Return the CPU set describing the locality of the OpenFabrics
* Store in \p set the CPU-set describing the locality of the OpenFabrics
* device \p ibdev (InfiniBand, etc).
*
* Topology \p topology and device \p ibdev must match the local machine.
@@ -88,10 +88,11 @@ hwloc_ibv_get_device_cpuset(hwloc_topology_t topology __hwloc_attribute_unused,
/** \brief Get the hwloc OS device object corresponding to the OpenFabrics
* device named \p ibname.
*
* Return the OS device object describing the OpenFabrics device
* \return The hwloc OS device object describing the OpenFabrics device
* (InfiniBand, Omni-Path, usNIC, etc) whose name is \p ibname
* (mlx5_0, hfi1_0, usnic_0, qib0, etc).
* Returns NULL if there is none.
* \return \c NULL if none could be found.
*
* The name \p ibname is usually obtained from ibv_get_device_name().
*
* The topology \p topology does not necessarily have to match the current
@@ -117,8 +118,9 @@ hwloc_ibv_get_device_osdev_by_name(hwloc_topology_t topology,
/** \brief Get the hwloc OS device object corresponding to the OpenFabrics
* device \p ibdev.
*
* Return the OS device object describing the OpenFabrics device \p ibdev
* (InfiniBand, etc). Returns NULL if there is none.
* \return The hwloc OS device object describing the OpenFabrics
* device \p ibdev (InfiniBand, etc).
* \return \c NULL if none could be found.
*
* Topology \p topology and device \p ibdev must match the local machine.
* I/O devices detection must be enabled in the topology.

View File

@@ -1,5 +1,5 @@
/*
* Copyright © 2013-2020 Inria. All rights reserved.
* Copyright © 2013-2022 Inria. All rights reserved.
* Copyright © 2016 Cisco Systems, Inc. All rights reserved.
* See COPYING in top-level directory.
*/
@@ -27,6 +27,9 @@ struct hwloc_backend;
/** \defgroup hwlocality_disc_components Components and Plugins: Discovery components
*
* \note These structures and functions may change when ::HWLOC_COMPONENT_ABI is modified.
*
* @{
*/
@@ -93,6 +96,9 @@ struct hwloc_disc_component {
/** \defgroup hwlocality_disc_backends Components and Plugins: Discovery backends
*
* \note These structures and functions may change when ::HWLOC_COMPONENT_ABI is modified.
*
* @{
*/
@@ -241,6 +247,9 @@ HWLOC_DECLSPEC int hwloc_backend_enable(struct hwloc_backend *backend);
/** \defgroup hwlocality_generic_components Components and Plugins: Generic components
*
* \note These structures and functions may change when ::HWLOC_COMPONENT_ABI is modified.
*
* @{
*/
@@ -310,10 +319,38 @@ struct hwloc_component {
/** \defgroup hwlocality_components_core_funcs Components and Plugins: Core functions to be used by components
*
* \note These structures and functions may change when ::HWLOC_COMPONENT_ABI is modified.
*
* @{
*/
/** \brief Check whether error messages are hidden.
*
* Callers should print critical error messages
* (e.g. invalid hw topo info, invalid config)
* only if this function returns strictly less than 2.
*
* Callers should print non-critical error messages
* (e.g. failure to initialize CUDA)
* if this function returns 0.
*
* This function return 1 by default (show critical only),
* 0 in lstopo (show all),
* or anything set in HWLOC_HIDE_ERRORS in the environment.
*
* Use macros HWLOC_SHOW_CRITICAL_ERRORS() and HWLOC_SHOW_ALL_ERRORS()
* for clarity.
*/
HWLOC_DECLSPEC int hwloc_hide_errors(void);
#define HWLOC_SHOW_CRITICAL_ERRORS() (hwloc_hide_errors() < 2)
#define HWLOC_SHOW_ALL_ERRORS() (hwloc_hide_errors() == 0)
/** \brief Add an object to the topology.
*
* Insert new object \p obj in the topology starting under existing object \p root
* (if \c NULL, the topology root object is used).
*
* It is sorted along the tree of other objects according to the inclusion of
* cpusets, to eventually be added as a child of the smallest object including
@@ -327,32 +364,20 @@ struct hwloc_component {
*
* This shall only be called before levels are built.
*
* In case of error, hwloc_report_os_error() is called.
*
* The caller should check whether the object type is filtered-out before calling this function.
*
* The topology cpuset/nodesets will be enlarged to include the object sets.
*
* \p reason is a unique string identifying where and why this insertion call was performed
* (it will be displayed in case of internal insertion error).
*
* Returns the object on success.
* Returns NULL and frees obj on error.
* Returns another object and frees obj if it was merged with an identical pre-existing object.
*/
HWLOC_DECLSPEC struct hwloc_obj *hwloc_insert_object_by_cpuset(struct hwloc_topology *topology, hwloc_obj_t obj);
/** \brief Type of error callbacks during object insertion */
typedef void (*hwloc_report_error_t)(const char * msg, int line);
/** \brief Report an insertion error from a backend */
HWLOC_DECLSPEC void hwloc_report_os_error(const char * msg, int line);
/** \brief Check whether insertion errors are hidden */
HWLOC_DECLSPEC int hwloc_hide_errors(void);
/** \brief Add an object to the topology and specify which error callback to use.
*
* This function is similar to hwloc_insert_object_by_cpuset() but it allows specifying
* where to start insertion from (if \p root is NULL, the topology root object is used),
* and specifying the error callback.
*/
HWLOC_DECLSPEC struct hwloc_obj *hwloc__insert_object_by_cpuset(struct hwloc_topology *topology, hwloc_obj_t root, hwloc_obj_t obj, hwloc_report_error_t report_error);
HWLOC_DECLSPEC hwloc_obj_t
hwloc__insert_object_by_cpuset(struct hwloc_topology *topology, hwloc_obj_t root,
hwloc_obj_t obj, const char *reason);
/** \brief Insert an object somewhere in the topology.
*
@@ -461,6 +486,9 @@ hwloc_plugin_check_namespace(const char *pluginname __hwloc_attribute_unused, co
/** \defgroup hwlocality_components_filtering Components and Plugins: Filtering objects
*
* \note These structures and functions may change when ::HWLOC_COMPONENT_ABI is modified.
*
* @{
*/
@@ -475,9 +503,12 @@ hwloc_filter_check_pcidev_subtype_important(unsigned classid)
return (baseclass == 0x03 /* PCI_BASE_CLASS_DISPLAY */
|| baseclass == 0x02 /* PCI_BASE_CLASS_NETWORK */
|| baseclass == 0x01 /* PCI_BASE_CLASS_STORAGE */
|| baseclass == 0x00 /* Unclassified, for Atos/Bull BXI */
|| baseclass == 0x0b /* PCI_BASE_CLASS_PROCESSOR */
|| classid == 0x0c04 /* PCI_CLASS_SERIAL_FIBER */
|| classid == 0x0c06 /* PCI_CLASS_SERIAL_INFINIBAND */
|| classid == 0x0502 /* PCI_CLASS_MEMORY_CXL */
|| baseclass == 0x06 /* PCI_BASE_CLASS_BRIDGE with non-PCI downstream. the core will drop the useless ones later */
|| baseclass == 0x12 /* Processing Accelerators */);
}
@@ -533,6 +564,9 @@ hwloc_filter_check_keep_object(hwloc_topology_t topology, hwloc_obj_t obj)
/** \defgroup hwlocality_components_pcidisc Components and Plugins: helpers for PCI discovery
*
* \note These structures and functions may change when ::HWLOC_COMPONENT_ABI is modified.
*
* @{
*/
@@ -584,18 +618,76 @@ HWLOC_DECLSPEC int hwloc_pcidisc_tree_attach(struct hwloc_topology *topology, st
/** \defgroup hwlocality_components_pcifind Components and Plugins: finding PCI objects during other discoveries
*
* \note These structures and functions may change when ::HWLOC_COMPONENT_ABI is modified.
*
* @{
*/
/** \brief Find the normal parent of a PCI bus ID.
/** \brief Find the object or a parent of a PCI bus ID.
*
* Look at PCI affinity to find out where the given PCI bus ID should be attached.
* When attaching a new object (typically an OS device) whose locality
* is specified by PCI bus ID, this function returns the PCI object
* to use as a parent for attaching.
*
* This function should be used to attach an I/O device under the corresponding
* PCI object (if any), or under a normal (non-I/O) object with same locality.
* If the exact PCI device with this bus ID exists, it is returned.
* Otherwise (for instance if it was filtered out), the function returns
* another object with similar locality (for instance a parent bridge,
* or the local CPU Package).
*/
HWLOC_DECLSPEC struct hwloc_obj * hwloc_pci_find_parent_by_busid(struct hwloc_topology *topology, unsigned domain, unsigned bus, unsigned dev, unsigned func);
/** \brief Find the PCI device or bridge matching a PCI bus ID exactly.
*
* This is useful for adding specific information about some objects
* based on their PCI id. When it comes to attaching objects based on
* PCI locality, hwloc_pci_find_parent_by_busid() should be preferred.
*/
HWLOC_DECLSPEC struct hwloc_obj * hwloc_pci_find_by_busid(struct hwloc_topology *topology, unsigned domain, unsigned bus, unsigned dev, unsigned func);
/** \brief Handle to a new distances structure during its addition to the topology. */
typedef void * hwloc_backend_distances_add_handle_t;
/** \brief Create a new empty distances structure.
*
* This is identical to hwloc_distances_add_create()
* but this variant is designed for backend inserting
* distances during topology discovery.
*/
HWLOC_DECLSPEC hwloc_backend_distances_add_handle_t
hwloc_backend_distances_add_create(hwloc_topology_t topology,
const char *name, unsigned long kind,
unsigned long flags);
/** \brief Specify the objects and values in a new empty distances structure.
*
* This is similar to hwloc_distances_add_values()
* but this variant is designed for backend inserting
* distances during topology discovery.
*
* The only semantical difference is that \p objs and \p values
* are not duplicated, but directly attached to the topology.
* On success, these arrays are given to the core and should not
* ever be freed by the caller anymore.
*/
HWLOC_DECLSPEC int
hwloc_backend_distances_add_values(hwloc_topology_t topology,
hwloc_backend_distances_add_handle_t handle,
unsigned nbobjs, hwloc_obj_t *objs,
hwloc_uint64_t *values,
unsigned long flags);
/** \brief Commit a new distances structure.
*
* This is similar to hwloc_distances_add_commit()
* but this variant is designed for backend inserting
* distances during topology discovery.
*/
HWLOC_DECLSPEC int
hwloc_backend_distances_add_commit(hwloc_topology_t topology,
hwloc_backend_distances_add_handle_t handle,
unsigned long flags);
/** @} */

View File

@@ -1,6 +1,6 @@
/*
* Copyright © 2009-2011 Cisco Systems, Inc. All rights reserved.
* Copyright © 2010-2019 Inria. All rights reserved.
* Copyright © 2010-2022 Inria. All rights reserved.
* See COPYING in top-level directory.
*/
@@ -119,6 +119,13 @@ extern "C" {
#define HWLOC_TOPOLOGY_FLAG_INCLUDE_DISALLOWED HWLOC_NAME_CAPS(TOPOLOGY_FLAG_WITH_DISALLOWED)
#define HWLOC_TOPOLOGY_FLAG_IS_THISSYSTEM HWLOC_NAME_CAPS(TOPOLOGY_FLAG_IS_THISSYSTEM)
#define HWLOC_TOPOLOGY_FLAG_THISSYSTEM_ALLOWED_RESOURCES HWLOC_NAME_CAPS(TOPOLOGY_FLAG_THISSYSTEM_ALLOWED_RESOURCES)
#define HWLOC_TOPOLOGY_FLAG_IMPORT_SUPPORT HWLOC_NAME_CAPS(TOPOLOGY_FLAG_IMPORT_SUPPORT)
#define HWLOC_TOPOLOGY_FLAG_RESTRICT_TO_CPUBINDING HWLOC_NAME_CAPS(TOPOLOGY_FLAG_RESTRICT_TO_CPUBINDING)
#define HWLOC_TOPOLOGY_FLAG_RESTRICT_TO_MEMBINDING HWLOC_NAME_CAPS(TOPOLOGY_FLAG_RESTRICT_TO_MEMBINDING)
#define HWLOC_TOPOLOGY_FLAG_DONT_CHANGE_BINDING HWLOC_NAME_CAPS(TOPOLOGY_FLAG_DONT_CHANGE_BINDING)
#define HWLOC_TOPOLOGY_FLAG_NO_DISTANCES HWLOC_NAME_CAPS(TOPOLOGY_FLAG_NO_DISTANCES)
#define HWLOC_TOPOLOGY_FLAG_NO_MEMATTRS HWLOC_NAME_CAPS(TOPOLOGY_FLAG_NO_MEMATTRS)
#define HWLOC_TOPOLOGY_FLAG_NO_CPUKINDS HWLOC_NAME_CAPS(TOPOLOGY_FLAG_NO_CPUKINDS)
#define hwloc_topology_set_pid HWLOC_NAME(topology_set_pid)
#define hwloc_topology_set_synthetic HWLOC_NAME(topology_set_synthetic)
@@ -134,6 +141,7 @@ extern "C" {
#define hwloc_topology_discovery_support HWLOC_NAME(topology_discovery_support)
#define hwloc_topology_cpubind_support HWLOC_NAME(topology_cpubind_support)
#define hwloc_topology_membind_support HWLOC_NAME(topology_membind_support)
#define hwloc_topology_misc_support HWLOC_NAME(topology_misc_support)
#define hwloc_topology_support HWLOC_NAME(topology_support)
#define hwloc_topology_get_support HWLOC_NAME(topology_get_support)
@@ -170,6 +178,7 @@ extern "C" {
#define hwloc_topology_alloc_group_object HWLOC_NAME(topology_alloc_group_object)
#define hwloc_topology_insert_group_object HWLOC_NAME(topology_insert_group_object)
#define hwloc_obj_add_other_obj_sets HWLOC_NAME(obj_add_other_obj_sets)
#define hwloc_topology_refresh HWLOC_NAME(topology_refresh)
#define hwloc_topology_get_depth HWLOC_NAME(topology_get_depth)
#define hwloc_get_type_depth HWLOC_NAME(get_type_depth)
@@ -353,6 +362,7 @@ extern "C" {
#define hwloc_get_closest_objs HWLOC_NAME(get_closest_objs)
#define hwloc_get_obj_below_by_type HWLOC_NAME(get_obj_below_by_type)
#define hwloc_get_obj_below_array_by_type HWLOC_NAME(get_obj_below_array_by_type)
#define hwloc_get_obj_with_same_locality HWLOC_NAME(get_obj_with_same_locality)
#define hwloc_distrib_flags_e HWLOC_NAME(distrib_flags_e)
#define HWLOC_DISTRIB_FLAG_REVERSE HWLOC_NAME_CAPS(DISTRIB_FLAG_REVERSE)
#define hwloc_distrib HWLOC_NAME(distrib)
@@ -367,6 +377,56 @@ extern "C" {
#define hwloc_cpuset_to_nodeset HWLOC_NAME(cpuset_to_nodeset)
#define hwloc_cpuset_from_nodeset HWLOC_NAME(cpuset_from_nodeset)
/* memattrs.h */
#define hwloc_memattr_id_e HWLOC_NAME(memattr_id_e)
#define HWLOC_MEMATTR_ID_CAPACITY HWLOC_NAME_CAPS(MEMATTR_ID_CAPACITY)
#define HWLOC_MEMATTR_ID_LOCALITY HWLOC_NAME_CAPS(MEMATTR_ID_LOCALITY)
#define HWLOC_MEMATTR_ID_BANDWIDTH HWLOC_NAME_CAPS(MEMATTR_ID_BANDWIDTH)
#define HWLOC_MEMATTR_ID_LATENCY HWLOC_NAME_CAPS(MEMATTR_ID_LATENCY)
#define HWLOC_MEMATTR_ID_READ_BANDWIDTH HWLOC_NAME_CAPS(MEMATTR_ID_READ_BANDWIDTH)
#define HWLOC_MEMATTR_ID_WRITE_BANDWIDTH HWLOC_NAME_CAPS(MEMATTR_ID_WRITE_BANDWIDTH)
#define HWLOC_MEMATTR_ID_READ_LATENCY HWLOC_NAME_CAPS(MEMATTR_ID_READ_LATENCY)
#define HWLOC_MEMATTR_ID_WRITE_LATENCY HWLOC_NAME_CAPS(MEMATTR_ID_WRITE_LATENCY)
#define HWLOC_MEMATTR_ID_MAX HWLOC_NAME_CAPS(MEMATTR_ID_MAX)
#define hwloc_memattr_id_t HWLOC_NAME(memattr_id_t)
#define hwloc_memattr_get_by_name HWLOC_NAME(memattr_get_by_name)
#define hwloc_location HWLOC_NAME(location)
#define hwloc_location_type_e HWLOC_NAME(location_type_e)
#define HWLOC_LOCATION_TYPE_OBJECT HWLOC_NAME_CAPS(LOCATION_TYPE_OBJECT)
#define HWLOC_LOCATION_TYPE_CPUSET HWLOC_NAME_CAPS(LOCATION_TYPE_CPUSET)
#define hwloc_location_u HWLOC_NAME(location_u)
#define hwloc_memattr_get_value HWLOC_NAME(memattr_get_value)
#define hwloc_memattr_get_best_target HWLOC_NAME(memattr_get_best_target)
#define hwloc_memattr_get_best_initiator HWLOC_NAME(memattr_get_best_initiator)
#define hwloc_local_numanode_flag_e HWLOC_NAME(local_numanode_flag_e)
#define HWLOC_LOCAL_NUMANODE_FLAG_LARGER_LOCALITY HWLOC_NAME_CAPS(LOCAL_NUMANODE_FLAG_LARGER_LOCALITY)
#define HWLOC_LOCAL_NUMANODE_FLAG_SMALLER_LOCALITY HWLOC_NAME_CAPS(LOCAL_NUMANODE_FLAG_SMALLER_LOCALITY)
#define HWLOC_LOCAL_NUMANODE_FLAG_ALL HWLOC_NAME_CAPS(LOCAL_NUMANODE_FLAG_ALL)
#define hwloc_get_local_numanode_objs HWLOC_NAME(get_local_numanode_objs)
#define hwloc_memattr_get_name HWLOC_NAME(memattr_get_name)
#define hwloc_memattr_get_flags HWLOC_NAME(memattr_get_flags)
#define hwloc_memattr_flag_e HWLOC_NAME(memattr_flag_e)
#define HWLOC_MEMATTR_FLAG_HIGHER_FIRST HWLOC_NAME_CAPS(MEMATTR_FLAG_HIGHER_FIRST)
#define HWLOC_MEMATTR_FLAG_LOWER_FIRST HWLOC_NAME_CAPS(MEMATTR_FLAG_LOWER_FIRST)
#define HWLOC_MEMATTR_FLAG_NEED_INITIATOR HWLOC_NAME_CAPS(MEMATTR_FLAG_NEED_INITIATOR)
#define hwloc_memattr_register HWLOC_NAME(memattr_register)
#define hwloc_memattr_set_value HWLOC_NAME(memattr_set_value)
#define hwloc_memattr_get_targets HWLOC_NAME(memattr_get_targets)
#define hwloc_memattr_get_initiators HWLOC_NAME(memattr_get_initiators)
/* cpukinds.h */
#define hwloc_cpukinds_get_nr HWLOC_NAME(cpukinds_get_nr)
#define hwloc_cpukinds_get_by_cpuset HWLOC_NAME(cpukinds_get_by_cpuset)
#define hwloc_cpukinds_get_info HWLOC_NAME(cpukinds_get_info)
#define hwloc_cpukinds_register HWLOC_NAME(cpukinds_register)
/* export.h */
#define hwloc_topology_export_xml_flags_e HWLOC_NAME(topology_export_xml_flags_e)
@@ -406,11 +466,22 @@ extern "C" {
#define hwloc_distances_obj_index HWLOC_NAME(distances_obj_index)
#define hwloc_distances_obj_pair_values HWLOC_NAME(distances_pair_values)
#define hwloc_distances_transform_e HWLOC_NAME(distances_transform_e)
#define HWLOC_DISTANCES_TRANSFORM_REMOVE_NULL HWLOC_NAME_CAPS(DISTANCES_TRANSFORM_REMOVE_NULL)
#define HWLOC_DISTANCES_TRANSFORM_LINKS HWLOC_NAME_CAPS(DISTANCES_TRANSFORM_LINKS)
#define HWLOC_DISTANCES_TRANSFORM_MERGE_SWITCH_PORTS HWLOC_NAME_CAPS(DISTANCES_TRANSFORM_MERGE_SWITCH_PORTS)
#define HWLOC_DISTANCES_TRANSFORM_TRANSITIVE_CLOSURE HWLOC_NAME_CAPS(DISTANCES_TRANSFORM_TRANSITIVE_CLOSURE)
#define hwloc_distances_transform HWLOC_NAME(distances_transform)
#define hwloc_distances_add_flag_e HWLOC_NAME(distances_add_flag_e)
#define HWLOC_DISTANCES_ADD_FLAG_GROUP HWLOC_NAME_CAPS(DISTANCES_ADD_FLAG_GROUP)
#define HWLOC_DISTANCES_ADD_FLAG_GROUP_INACCURATE HWLOC_NAME_CAPS(DISTANCES_ADD_FLAG_GROUP_INACCURATE)
#define hwloc_distances_add HWLOC_NAME(distances_add)
#define hwloc_distances_add_handle_t HWLOC_NAME(distances_add_handle_t)
#define hwloc_distances_add_create HWLOC_NAME(distances_add_create)
#define hwloc_distances_add_values HWLOC_NAME(distances_add_values)
#define hwloc_distances_add_commit HWLOC_NAME(distances_add_commit)
#define hwloc_distances_remove HWLOC_NAME(distances_remove)
#define hwloc_distances_remove_by_depth HWLOC_NAME(distances_remove_by_depth)
#define hwloc_distances_remove_by_type HWLOC_NAME(distances_remove_by_type)
@@ -475,6 +546,11 @@ extern "C" {
#define hwloc_linux_get_tid_last_cpu_location HWLOC_NAME(linux_get_tid_last_cpu_location)
#define hwloc_linux_read_path_as_cpumask HWLOC_NAME(linux_read_file_cpumask)
/* windows.h */
#define hwloc_windows_get_nr_processor_groups HWLOC_NAME(windows_get_nr_processor_groups)
#define hwloc_windows_get_processor_group_cpuset HWLOC_NAME(windows_get_processor_group_cpuset)
/* openfabrics-verbs.h */
#define hwloc_ibv_get_device_cpuset HWLOC_NAME(ibv_get_device_cpuset)
@@ -510,6 +586,17 @@ extern "C" {
#define hwloc_nvml_get_device_osdev HWLOC_NAME(nvml_get_device_osdev)
#define hwloc_nvml_get_device_osdev_by_index HWLOC_NAME(nvml_get_device_osdev_by_index)
/* rsmi.h */
#define hwloc_rsmi_get_device_cpuset HWLOC_NAME(rsmi_get_device_cpuset)
#define hwloc_rsmi_get_device_osdev HWLOC_NAME(rsmi_get_device_osdev)
#define hwloc_rsmi_get_device_osdev_by_index HWLOC_NAME(rsmi_get_device_osdev_by_index)
/* levelzero.h */
#define hwloc_levelzero_get_device_cpuset HWLOC_NAME(levelzero_get_device_cpuset)
#define hwloc_levelzero_get_device_osdev HWLOC_NAME(levelzero_get_device_osdev)
/* gl.h */
#define hwloc_gl_get_display_osdev_by_port_device HWLOC_NAME(gl_get_display_osdev_by_port_device)
@@ -547,9 +634,6 @@ extern "C" {
#define hwloc_plugin_check_namespace HWLOC_NAME(plugin_check_namespace)
#define hwloc_insert_object_by_cpuset HWLOC_NAME(insert_object_by_cpuset)
#define hwloc_report_error_t HWLOC_NAME(report_error_t)
#define hwloc_report_os_error HWLOC_NAME(report_os_error)
#define hwloc_hide_errors HWLOC_NAME(hide_errors)
#define hwloc__insert_object_by_cpuset HWLOC_NAME(_insert_object_by_cpuset)
#define hwloc_insert_object_by_parent HWLOC_NAME(insert_object_by_parent)
@@ -569,10 +653,18 @@ extern "C" {
#define hwloc_pcidisc_tree_insert_by_busid HWLOC_NAME(pcidisc_tree_insert_by_busid)
#define hwloc_pcidisc_tree_attach HWLOC_NAME(pcidisc_tree_attach)
#define hwloc_pci_find_by_busid HWLOC_NAME(pcidisc_find_by_busid)
#define hwloc_pci_find_parent_by_busid HWLOC_NAME(pcidisc_find_busid_parent)
#define hwloc_backend_distances_add_handle_t HWLOC_NAME(backend_distances_add_handle_t)
#define hwloc_backend_distances_add_create HWLOC_NAME(backend_distances_add_create)
#define hwloc_backend_distances_add_values HWLOC_NAME(backend_distances_add_values)
#define hwloc_backend_distances_add_commit HWLOC_NAME(backend_distances_add_commit)
/* hwloc/deprecated.h */
#define hwloc_distances_add HWLOC_NAME(distances_add)
#define hwloc_topology_insert_misc_object_by_parent HWLOC_NAME(topology_insert_misc_object_by_parent)
#define hwloc_obj_cpuset_snprintf HWLOC_NAME(obj_cpuset_snprintf)
#define hwloc_obj_type_sscanf HWLOC_NAME(obj_type_sscanf)
@@ -682,7 +774,9 @@ extern "C" {
#define hwloc_cuda_component HWLOC_NAME(cuda_component)
#define hwloc_gl_component HWLOC_NAME(gl_component)
#define hwloc_levelzero_component HWLOC_NAME(levelzero_component)
#define hwloc_nvml_component HWLOC_NAME(nvml_component)
#define hwloc_rsmi_component HWLOC_NAME(rsmi_component)
#define hwloc_opencl_component HWLOC_NAME(opencl_component)
#define hwloc_pci_component HWLOC_NAME(pci_component)
@@ -691,6 +785,8 @@ extern "C" {
/* private/private.h */
#define hwloc_internal_location_s HWLOC_NAME(internal_location_s)
#define hwloc_special_level_s HWLOC_NAME(special_level_s)
#define hwloc_pci_forced_locality_s HWLOC_NAME(pci_forced_locality_s)
@@ -713,16 +809,18 @@ extern "C" {
#define hwloc__attach_memory_object HWLOC_NAME(insert_memory_object)
#define hwloc_get_obj_by_type_and_gp_index HWLOC_NAME(get_obj_by_type_and_gp_index)
#define hwloc_pci_discovery_init HWLOC_NAME(pci_discovery_init)
#define hwloc_pci_discovery_prepare HWLOC_NAME(pci_discovery_prepare)
#define hwloc_pci_discovery_exit HWLOC_NAME(pci_discovery_exit)
#define hwloc_pci_find_by_busid HWLOC_NAME(pcidisc_find_by_busid)
#define hwloc_find_insert_io_parent_by_complete_cpuset HWLOC_NAME(hwloc_find_insert_io_parent_by_complete_cpuset)
#define hwloc__add_info HWLOC_NAME(_add_info)
#define hwloc__add_info_nodup HWLOC_NAME(_add_info_nodup)
#define hwloc__move_infos HWLOC_NAME(_move_infos)
#define hwloc__free_infos HWLOC_NAME(_free_infos)
#define hwloc__tma_dup_infos HWLOC_NAME(_tma_dup_infos)
#define hwloc_binding_hooks HWLOC_NAME(binding_hooks)
#define hwloc_set_native_binding_hooks HWLOC_NAME(set_native_binding_hooks)
@@ -759,11 +857,29 @@ extern "C" {
#define hwloc_internal_distances_dup HWLOC_NAME(internal_distances_dup)
#define hwloc_internal_distances_refresh HWLOC_NAME(internal_distances_refresh)
#define hwloc_internal_distances_destroy HWLOC_NAME(internal_distances_destroy)
#define hwloc_internal_distances_add HWLOC_NAME(internal_distances_add)
#define hwloc_internal_distances_add_by_index HWLOC_NAME(internal_distances_add_by_index)
#define hwloc_internal_distances_invalidate_cached_objs HWLOC_NAME(hwloc_internal_distances_invalidate_cached_objs)
#define hwloc_internal_memattr_s HWLOC_NAME(internal_memattr_s)
#define hwloc_internal_memattr_target_s HWLOC_NAME(internal_memattr_target_s)
#define hwloc_internal_memattr_initiator_s HWLOC_NAME(internal_memattr_initiator_s)
#define hwloc_internal_memattrs_init HWLOC_NAME(internal_memattrs_init)
#define hwloc_internal_memattrs_prepare HWLOC_NAME(internal_memattrs_prepare)
#define hwloc_internal_memattrs_dup HWLOC_NAME(internal_memattrs_dup)
#define hwloc_internal_memattrs_destroy HWLOC_NAME(internal_memattrs_destroy)
#define hwloc_internal_memattrs_need_refresh HWLOC_NAME(internal_memattrs_need_refresh)
#define hwloc_internal_memattrs_refresh HWLOC_NAME(internal_memattrs_refresh)
#define hwloc_internal_memattrs_guess_memory_tiers HWLOC_NAME(internal_memattrs_guess_memory_tiers)
#define hwloc_internal_cpukind_s HWLOC_NAME(internal_cpukind_s)
#define hwloc_internal_cpukinds_init HWLOC_NAME(internal_cpukinds_init)
#define hwloc_internal_cpukinds_destroy HWLOC_NAME(internal_cpukinds_destroy)
#define hwloc_internal_cpukinds_dup HWLOC_NAME(internal_cpukinds_dup)
#define hwloc_internal_cpukinds_register HWLOC_NAME(internal_cpukinds_register)
#define hwloc_internal_cpukinds_rank HWLOC_NAME(internal_cpukinds_rank)
#define hwloc_internal_cpukinds_restrict HWLOC_NAME(internal_cpukinds_restrict)
#define hwloc_encode_to_base64 HWLOC_NAME(encode_to_base64)
#define hwloc_decode_from_base64 HWLOC_NAME(decode_from_base64)

203
src/3rdparty/hwloc/include/hwloc/rsmi.h vendored Normal file
View File

@@ -0,0 +1,203 @@
/*
* Copyright © 2012-2021 Inria. All rights reserved.
* Copyright (c) 2020, Advanced Micro Devices, Inc. All rights reserved.
* Written by Advanced Micro Devices,
* See COPYING in top-level directory.
*/
/** \file
* \brief Macros to help interaction between hwloc and the ROCm SMI Management Library.
*
* Applications that use both hwloc and the ROCm SMI Management Library may want to
* include this file so as to get topology information for AMD GPU devices.
*/
#ifndef HWLOC_RSMI_H
#define HWLOC_RSMI_H
#include "hwloc.h"
#include "hwloc/autogen/config.h"
#include "hwloc/helper.h"
#ifdef HWLOC_LINUX_SYS
#include "hwloc/linux.h"
#endif
#include <rocm_smi/rocm_smi.h>
#ifdef __cplusplus
extern "C" {
#endif
/** \defgroup hwlocality_rsmi Interoperability with the ROCm SMI Management Library
*
* This interface offers ways to retrieve topology information about
* devices managed by the ROCm SMI Management Library.
*
* @{
*/
/** \brief Get the CPU set of logical processors that are physically
* close to AMD GPU device whose index is \p dv_ind.
*
* Store in \p set the CPU-set describing the locality of the AMD GPU device
* whose index is \p dv_ind.
*
* Topology \p topology and device \p dv_ind must match the local machine.
* I/O devices detection and the ROCm SMI component are not needed in the
* topology.
*
* The function only returns the locality of the device.
* If more information about the device is needed, OS objects should
* be used instead, see hwloc_rsmi_get_device_osdev()
* and hwloc_rsmi_get_device_osdev_by_index().
*
* This function is currently only implemented in a meaningful way for
* Linux; other systems will simply get a full cpuset.
*/
static __hwloc_inline int
hwloc_rsmi_get_device_cpuset(hwloc_topology_t topology __hwloc_attribute_unused,
uint32_t dv_ind, hwloc_cpuset_t set)
{
#ifdef HWLOC_LINUX_SYS
/* If we're on Linux, use the sysfs mechanism to get the local cpus */
#define HWLOC_RSMI_DEVICE_SYSFS_PATH_MAX 128
char path[HWLOC_RSMI_DEVICE_SYSFS_PATH_MAX];
rsmi_status_t ret;
uint64_t bdfid = 0;
unsigned domain, device, bus;
if (!hwloc_topology_is_thissystem(topology)) {
errno = EINVAL;
return -1;
}
ret = rsmi_dev_pci_id_get(dv_ind, &bdfid);
if (RSMI_STATUS_SUCCESS != ret) {
errno = EINVAL;
return -1;
}
domain = (bdfid>>32) & 0xffffffff;
bus = ((bdfid & 0xffff)>>8) & 0xff;
device = ((bdfid & 0xff)>>3) & 0x1f;
sprintf(path, "/sys/bus/pci/devices/%04x:%02x:%02x.0/local_cpus", domain, bus, device);
if (hwloc_linux_read_path_as_cpumask(path, set) < 0
|| hwloc_bitmap_iszero(set))
hwloc_bitmap_copy(set, hwloc_topology_get_complete_cpuset(topology));
#else
/* Non-Linux systems simply get a full cpuset */
hwloc_bitmap_copy(set, hwloc_topology_get_complete_cpuset(topology));
#endif
return 0;
}
/** \brief Get the hwloc OS device object corresponding to the
* AMD GPU device whose index is \p dv_ind.
*
* \return The hwloc OS device object describing the AMD GPU device whose
* index is \p dv_ind.
* \return \c NULL if none could be found.
*
* The topology \p topology does not necessarily have to match the current
* machine. For instance the topology may be an XML import of a remote host.
* I/O devices detection and the ROCm SMI component must be enabled in the
* topology.
*
* \note The corresponding PCI device object can be obtained by looking
* at the OS device parent object (unless PCI devices are filtered out).
*/
static __hwloc_inline hwloc_obj_t
hwloc_rsmi_get_device_osdev_by_index(hwloc_topology_t topology, uint32_t dv_ind)
{
hwloc_obj_t osdev = NULL;
while ((osdev = hwloc_get_next_osdev(topology, osdev)) != NULL) {
if (HWLOC_OBJ_OSDEV_GPU == osdev->attr->osdev.type
&& osdev->name
&& !strncmp("rsmi", osdev->name, 4)
&& atoi(osdev->name + 4) == (int) dv_ind)
return osdev;
}
return NULL;
}
/** \brief Get the hwloc OS device object corresponding to AMD GPU device,
* whose index is \p dv_ind.
*
* \return The hwloc OS device object that describes the given
* AMD GPU, whose index is \p dv_ind.
* \return \c NULL if none could be found.
*
* Topology \p topology and device \p dv_ind must match the local machine.
* I/O devices detection and the ROCm SMI component must be enabled in the
* topology. If not, the locality of the object may still be found using
* hwloc_rsmi_get_device_cpuset().
*
* \note The corresponding hwloc PCI device may be found by looking
* at the result parent pointer (unless PCI devices are filtered out).
*/
static __hwloc_inline hwloc_obj_t
hwloc_rsmi_get_device_osdev(hwloc_topology_t topology, uint32_t dv_ind)
{
hwloc_obj_t osdev;
rsmi_status_t ret;
uint64_t bdfid = 0;
unsigned domain, device, bus, func;
uint64_t id;
char uuid[64];
if (!hwloc_topology_is_thissystem(topology)) {
errno = EINVAL;
return NULL;
}
ret = rsmi_dev_pci_id_get(dv_ind, &bdfid);
if (RSMI_STATUS_SUCCESS != ret) {
errno = EINVAL;
return NULL;
}
domain = (bdfid>>32) & 0xffffffff;
bus = ((bdfid & 0xffff)>>8) & 0xff;
device = ((bdfid & 0xff)>>3) & 0x1f;
func = bdfid & 0x7;
ret = rsmi_dev_unique_id_get(dv_ind, &id);
if (RSMI_STATUS_SUCCESS != ret)
uuid[0] = '\0';
else
sprintf(uuid, "%lx", id);
osdev = NULL;
while ((osdev = hwloc_get_next_osdev(topology, osdev)) != NULL) {
hwloc_obj_t pcidev = osdev->parent;
const char *info;
if (strncmp(osdev->name, "rsmi", 4))
continue;
if (pcidev
&& pcidev->type == HWLOC_OBJ_PCI_DEVICE
&& pcidev->attr->pcidev.domain == domain
&& pcidev->attr->pcidev.bus == bus
&& pcidev->attr->pcidev.dev == device
&& pcidev->attr->pcidev.func == func)
return osdev;
info = hwloc_obj_get_info_by_name(osdev, "AMDUUID");
if (info && !strcmp(info, uuid))
return osdev;
}
return NULL;
}
/** @} */
#ifdef __cplusplus
} /* extern "C" */
#endif
#endif /* HWLOC_RSMI_H */

View File

@@ -0,0 +1,76 @@
/*
* Copyright © 2021 Inria. All rights reserved.
* See COPYING in top-level directory.
*/
/** \file
* \brief Macros to help interaction between hwloc and Windows.
*
* Applications that use hwloc on Windows may want to include this file
* for Windows specific hwloc features.
*/
#ifndef HWLOC_WINDOWS_H
#define HWLOC_WINDOWS_H
#include "hwloc.h"
#ifdef __cplusplus
extern "C" {
#endif
/** \defgroup hwlocality_windows Windows-specific helpers
*
* These functions query Windows processor groups.
* These groups partition the operating system into virtual sets
* of up to 64 neighbor PUs.
* Threads and processes may only be bound inside a single group.
* Although Windows processor groups may be exposed in the hwloc
* hierarchy as hwloc Groups, they are also often merged into
* existing hwloc objects such as NUMA nodes or Packages.
* This API provides explicit information about Windows processor
* groups so that applications know whether binding to a large
* set of PUs may fail because it spans over multiple Windows
* processor groups.
*
* @{
*/
/** \brief Get the number of Windows processor groups
*
* \p flags must be 0 for now.
*
* \return at least \c 1 on success.
* \return -1 on error, for instance if the topology does not match
* the current system (e.g. loaded from another machine through XML).
*/
HWLOC_DECLSPEC int hwloc_windows_get_nr_processor_groups(hwloc_topology_t topology, unsigned long flags);
/** \brief Get the CPU-set of a Windows processor group.
*
* Get the set of PU included in the processor group specified
* by \p pg_index.
* \p pg_index must be between \c 0 and the value returned
* by hwloc_windows_get_nr_processor_groups() minus 1.
*
* \p flags must be 0 for now.
*
* \return \c 0 on success.
* \return \c -1 on error, for instance if \p pg_index is invalid,
* or if the topology does not match the current system (e.g. loaded
* from another machine through XML).
*/
HWLOC_DECLSPEC int hwloc_windows_get_processor_group_cpuset(hwloc_topology_t topology, unsigned pg_index, hwloc_cpuset_t cpuset, unsigned long flags);
/** @} */
#ifdef __cplusplus
} /* extern "C" */
#endif
#endif /* HWLOC_WINDOWS_H */

View File

@@ -1,8 +1,8 @@
/*
* Copyright © 2009, 2011, 2012 CNRS. All rights reserved.
* Copyright © 2009-2018 Inria. All rights reserved.
* Copyright © 2009-2021 Inria. All rights reserved.
* Copyright © 2009, 2011, 2012, 2015 Université Bordeaux. All rights reserved.
* Copyright © 2009 Cisco Systems, Inc. All rights reserved.
* Copyright © 2009-2020 Cisco Systems, Inc. All rights reserved.
* $COPYRIGHT$
*
* Additional copyrights may follow
@@ -290,10 +290,6 @@
/* Define to '1' if sysctlbyname is present and usable */
/* #undef HAVE_SYSCTLBYNAME */
/* Define to 1 if the system has the type
`SYSTEM_LOGICAL_PROCESSOR_INFORMATION'. */
#define HAVE_SYSTEM_LOGICAL_PROCESSOR_INFORMATION 1
/* Define to 1 if the system has the type
`SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX'. */
#define HAVE_SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX 1
@@ -575,7 +571,7 @@
#define PACKAGE "hwloc"
/* Define to the address where bug reports for this package should be sent. */
#define PACKAGE_BUGREPORT "http://www.open-mpi.org/projects/hwloc/"
#define PACKAGE_BUGREPORT "https://www.open-mpi.org/projects/hwloc/"
/* Define to the full name of this package. */
#define PACKAGE_NAME "hwloc"
@@ -668,5 +664,9 @@
/* Define this to the thread ID type */
#define hwloc_thread_t HANDLE
/* Define to 1 if you have the declaration of `GetModuleFileName', and to 0 if
you don't. */
#define HAVE_DECL_GETMODULEFILENAME 1
#endif /* HWLOC_CONFIGURE_H */

Some files were not shown because too many files have changed in this diff Show More