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

Compare commits

...

63 Commits

Author SHA1 Message Date
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
83 changed files with 9280 additions and 7205 deletions

View File

@@ -1,3 +1,30 @@
# 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.

View File

@@ -1,4 +1,4 @@
cmake_minimum_required(VERSION 2.8.12)
cmake_minimum_required(VERSION 3.1)
project(xmrig)
option(WITH_HWLOC "Enable hwloc support" ON)

View File

@@ -10,7 +10,7 @@ if ("${CMAKE_BUILD_TYPE}" STREQUAL "")
endif()
if (CMAKE_BUILD_TYPE STREQUAL "Release")
add_definitions(/DNDEBUG)
add_definitions(-DNDEBUG)
endif()
include(CheckSymbolExists)
@@ -32,7 +32,7 @@ if (CMAKE_CXX_COMPILER_ID MATCHES GNU)
set(CMAKE_C_FLAGS "${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)
@@ -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()

View File

@@ -15,7 +15,7 @@ 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()

View File

@@ -1,8 +1,8 @@
#!/bin/bash -e
HWLOC_VERSION_MAJOR="2"
HWLOC_VERSION_MINOR="7"
HWLOC_VERSION_PATCH="1"
HWLOC_VERSION_MINOR="9"
HWLOC_VERSION_PATCH="0"
HWLOC_VERSION="${HWLOC_VERSION_MAJOR}.${HWLOC_VERSION_MINOR}.${HWLOC_VERSION_PATCH}"

View File

@@ -1,6 +1,6 @@
#!/bin/bash -e
OPENSSL_VERSION="1.1.1o"
OPENSSL_VERSION="1.1.1s"
mkdir -p deps
mkdir -p deps/include

View File

@@ -1,6 +1,6 @@
#!/bin/bash -e
OPENSSL_VERSION="3.0.3"
OPENSSL_VERSION="3.0.7"
mkdir -p deps
mkdir -p deps/include

View File

@@ -1,6 +1,6 @@
#!/bin/bash -e
UV_VERSION="1.44.1"
UV_VERSION="1.44.2"
mkdir -p deps
mkdir -p deps/include

View File

@@ -10,14 +10,24 @@ fi
if grep -E 'AMD Ryzen|AMD EPYC' /proc/cpuinfo > /dev/null;
then
if grep "cpu family[[:space:]]:[[:space:]]25" /proc/cpuinfo > /dev/null;
if grep "cpu family[[:space:]]\{1,\}:[[:space:]]25" /proc/cpuinfo > /dev/null;
then
echo "Detected Zen3 CPU"
wrmsr -a 0xc0011020 0x4480000000000
wrmsr -a 0xc0011021 0x1c000200000040
wrmsr -a 0xc0011022 0xc000000401500000
wrmsr -a 0xc001102b 0x2000cc14
echo "MSR register values for 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 Zen1/Zen2 CPU"
wrmsr -a 0xc0011020 0

View File

@@ -1,4 +1,4 @@
cmake_minimum_required(VERSION 2.8.12)
cmake_minimum_required(VERSION 3.1)
project(argon2 C)
set(CMAKE_C_STANDARD 99)

View File

@@ -1,4 +1,4 @@
cmake_minimum_required (VERSION 2.8.12)
cmake_minimum_required(VERSION 3.1)
project (hwloc C)
include_directories(include)

View File

@@ -17,6 +17,50 @@ 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

View File

@@ -78,7 +78,7 @@ debug and report issues.
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

@@ -8,8 +8,8 @@
# Please update HWLOC_VERSION* in contrib/windows/hwloc_config.h too.
major=2
minor=7
release=1
minor=9
release=0
# greek is used for alpha or beta release tags. If it is non-empty,
# it will be appended to the version number. It does not have to be
@@ -22,7 +22,7 @@ greek=
# The date when this release was created
date="Mar 20, 2022"
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=20:3:5
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

@@ -1,6 +1,6 @@
/*
* Copyright © 2009 CNRS
* Copyright © 2009-2021 Inria. All rights reserved.
* Copyright © 2009-2022 Inria. All rights reserved.
* Copyright © 2009-2012 Université Bordeaux
* Copyright © 2009-2020 Cisco Systems, Inc. All rights reserved.
* See COPYING in top-level directory.
@@ -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 0x00020500
#define HWLOC_API_VERSION 0x00020800
/** \brief Indicate at runtime which hwloc API version was used at build time.
*
@@ -971,7 +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,
@@ -986,7 +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,
@@ -2060,7 +2060,26 @@ enum hwloc_topology_flags_e {
* not change to due thread binding changes on Windows
* (see ::HWLOC_TOPOLOGY_FLAG_RESTRICT_TO_CPUBINDING).
*/
HWLOC_TOPOLOGY_FLAG_DONT_CHANGE_BINDING = (1UL<<6)
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.

View File

@@ -1,6 +1,6 @@
/*
* Copyright © 2009 CNRS
* Copyright © 2009-2021 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.
@@ -11,10 +11,10 @@
#ifndef HWLOC_CONFIG_H
#define HWLOC_CONFIG_H
#define HWLOC_VERSION "2.7.1"
#define HWLOC_VERSION "2.9.0"
#define HWLOC_VERSION_MAJOR 2
#define HWLOC_VERSION_MINOR 7
#define HWLOC_VERSION_RELEASE 1
#define HWLOC_VERSION_MINOR 9
#define HWLOC_VERSION_RELEASE 0
#define HWLOC_VERSION_GREEK ""
#define __hwloc_restrict

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 © 2009-2011 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);
@@ -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

@@ -1,6 +1,6 @@
/*
* Copyright © 2009 CNRS
* Copyright © 2009-2021 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.
@@ -55,7 +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 © 2010-2021 Inria. All rights reserved.
* Copyright © 2010-2022 Inria. All rights reserved.
* See COPYING in top-level directory.
*/
@@ -35,8 +35,8 @@ extern "C" {
* 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"
* and "NVLinkBandwidth".
* 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.
@@ -160,7 +160,8 @@ hwloc_distances_get_by_type(hwloc_topology_t topology, hwloc_obj_type_t type,
* Usually only one distances structure may match a given name.
*
* The name of the most common structure is "NUMALatency".
* Others include "XGMIBandwidth", "XGMIHops" and "NVLinkBandwidth".
* Others include "XGMIBandwidth", "XGMIHops", "XeLinkBandwidth",
* and "NVLinkBandwidth".
*/
HWLOC_DECLSPEC int
hwloc_distances_get_by_name(hwloc_topology_t topology, const char *name,

View File

@@ -1,6 +1,6 @@
/*
* Copyright © 2009 CNRS
* Copyright © 2009-2021 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.
@@ -886,9 +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,

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

@@ -54,6 +54,8 @@ extern "C" {
* 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
@@ -65,19 +67,19 @@ extern "C" {
/** \brief Memory node attributes. */
enum hwloc_memattr_id_e {
/** \brief "Capacity".
* The capacity is returned in bytes
* (local_memory attribute in objects).
/** \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 "Locality".
* The locality is returned as the number of PUs in that locality
/** \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>
@@ -87,26 +89,87 @@ enum hwloc_memattr_id_e {
*
* 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 "Bandwidth".
* The bandwidth is returned in MiB/s, as seen from the given initiator location.
/** \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 "Latency".
* The latency is returned as nanoseconds, as seen from the given initiator location.
/** \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
HWLOC_MEMATTR_ID_LATENCY = 3,
/* TODO read vs write, persistence? */
/** \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.

View File

@@ -1,5 +1,5 @@
/*
* Copyright © 2013-2021 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.
*/
@@ -338,9 +338,15 @@ struct hwloc_component {
* 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
@@ -501,6 +507,7 @@ hwloc_filter_check_pcidev_subtype_important(unsigned classid)
|| 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 */);
}

View File

@@ -1,6 +1,6 @@
/*
* Copyright © 2009-2011 Cisco Systems, Inc. All rights reserved.
* Copyright © 2010-2021 Inria. All rights reserved.
* Copyright © 2010-2022 Inria. All rights reserved.
* See COPYING in top-level directory.
*/
@@ -123,6 +123,9 @@ extern "C" {
#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)
@@ -381,6 +384,11 @@ extern "C" {
#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)
@@ -862,6 +870,7 @@ extern "C" {
#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)

View File

@@ -1,6 +1,6 @@
/*
* Copyright © 2009 CNRS
* Copyright © 2009-2021 Inria. All rights reserved.
* Copyright © 2009-2022 Inria. All rights reserved.
* Copyright © 2009-2012, 2020 Université Bordeaux
* Copyright © 2009-2011 Cisco Systems, Inc. All rights reserved.
*
@@ -259,6 +259,7 @@ struct hwloc_topology {
unsigned bus_first, bus_last;
hwloc_bitmap_t cpuset;
} * pci_forced_locality;
hwloc_uint64_t pci_locality_quirks;
/* component blacklisting */
unsigned nr_blacklisted_components;
@@ -419,6 +420,7 @@ extern void hwloc_internal_memattrs_need_refresh(hwloc_topology_t topology);
extern void hwloc_internal_memattrs_refresh(hwloc_topology_t topology);
extern int hwloc_internal_memattrs_dup(hwloc_topology_t new, hwloc_topology_t old);
extern int hwloc_internal_memattr_set_value(hwloc_topology_t topology, hwloc_memattr_id_t id, hwloc_obj_type_t target_type, hwloc_uint64_t target_gp_index, unsigned target_os_index, struct hwloc_internal_location_s *initiator, hwloc_uint64_t value);
extern int hwloc_internal_memattrs_guess_memory_tiers(hwloc_topology_t topology);
extern void hwloc_internal_cpukinds_init(hwloc_topology_t topology);
extern int hwloc_internal_cpukinds_rank(hwloc_topology_t topology);

View File

@@ -1,6 +1,6 @@
/*
* Copyright © 2009 Université Bordeaux
* Copyright © 2020 Inria. All rights reserved.
* Copyright © 2020-2022 Inria. All rights reserved.
*
* See COPYING in top-level directory.
*/
@@ -8,13 +8,22 @@
#ifndef HWLOC_PRIVATE_WINDOWS_H
#define HWLOC_PRIVATE_WINDOWS_H
#ifndef _ANONYMOUS_UNION
#ifdef __GNUC__
#define _ANONYMOUS_UNION __extension__
#define _ANONYMOUS_STRUCT __extension__
#else
#define _ANONYMOUS_UNION
#endif /* __GNUC__ */
#endif /* _ANONYMOUS_UNION */
#ifndef _ANONYMOUS_STRUCT
#ifdef __GNUC__
#define _ANONYMOUS_STRUCT __extension__
#else
#define _ANONYMOUS_STRUCT
#endif /* __GNUC__ */
#endif /* _ANONYMOUS_STRUCT */
#define DUMMYUNIONNAME
#define DUMMYSTRUCTNAME

View File

@@ -1,5 +1,5 @@
/*
* Copyright © 2009-2021 Inria. All rights reserved.
* Copyright © 2009-2022 Inria. All rights reserved.
* Copyright © 2012 Université Bordeaux
* See COPYING in top-level directory.
*/
@@ -386,7 +386,7 @@ hwloc_disc_component_register(struct hwloc_disc_component *component,
|HWLOC_DISC_PHASE_MISC
|HWLOC_DISC_PHASE_ANNOTATE
|HWLOC_DISC_PHASE_TWEAK))) {
if (hwloc_hide_errors() < 2)
if (HWLOC_SHOW_CRITICAL_ERRORS())
fprintf(stderr, "hwloc: Cannot register discovery component `%s' with invalid phases 0x%x\n",
component->name, component->phases);
return -1;
@@ -476,7 +476,7 @@ hwloc_components_init(void)
/* hwloc_static_components is created by configure in static-components.h */
for(i=0; NULL != hwloc_static_components[i]; i++) {
if (hwloc_static_components[i]->flags) {
if (hwloc_hide_errors() < 2)
if (HWLOC_SHOW_CRITICAL_ERRORS())
fprintf(stderr, "hwloc: Ignoring static component with invalid flags %lx\n",
hwloc_static_components[i]->flags);
continue;
@@ -505,7 +505,7 @@ hwloc_components_init(void)
#ifdef HWLOC_HAVE_PLUGINS
for(desc = hwloc_plugins; NULL != desc; desc = desc->next) {
if (desc->component->flags) {
if (hwloc_hide_errors() < 2)
if (HWLOC_SHOW_CRITICAL_ERRORS())
fprintf(stderr, "hwloc: Ignoring plugin `%s' component with invalid flags %lx\n",
desc->name, desc->component->flags);
continue;
@@ -738,7 +738,7 @@ hwloc_disc_component_try_enable(struct hwloc_topology *topology,
backend = comp->instantiate(topology, comp, topology->backend_excluded_phases | blacklisted_phases,
NULL, NULL, NULL);
if (!backend) {
if (hwloc_components_verbose || (envvar_forced && hwloc_hide_errors() < 2))
if (hwloc_components_verbose || (envvar_forced && HWLOC_SHOW_CRITICAL_ERRORS()))
fprintf(stderr, "hwloc: Failed to instantiate discovery component `%s'\n", comp->name);
return -1;
}
@@ -835,7 +835,7 @@ hwloc_disc_components_enable_others(struct hwloc_topology *topology)
if (comp->phases & ~blacklisted_phases)
hwloc_disc_component_try_enable(topology, comp, 1 /* envvar forced */, blacklisted_phases);
} else {
if (hwloc_hide_errors() < 2)
if (HWLOC_SHOW_CRITICAL_ERRORS())
fprintf(stderr, "hwloc: Cannot find discovery component `%s'\n", name);
}
@@ -967,7 +967,7 @@ hwloc_backend_enable(struct hwloc_backend *backend)
/* check backend flags */
if (backend->flags) {
if (hwloc_hide_errors() < 2)
if (HWLOC_SHOW_CRITICAL_ERRORS())
fprintf(stderr, "hwloc: Cannot enable discovery component `%s' phases 0x%x with unknown flags %lx\n",
backend->component->name, backend->component->phases, backend->flags);
return -1;

View File

@@ -1,5 +1,5 @@
/*
* Copyright © 2020-2021 Inria. All rights reserved.
* Copyright © 2020-2022 Inria. All rights reserved.
* See COPYING in top-level directory.
*/
@@ -504,7 +504,7 @@ hwloc_internal_cpukinds_rank(struct hwloc_topology *topology)
heuristics = HWLOC_CPUKINDS_RANKING_FORCED_EFFICIENCY;
else if (!strcmp(env, "no_forced_efficiency"))
heuristics = HWLOC_CPUKINDS_RANKING_NO_FORCED_EFFICIENCY;
else if (hwloc_hide_errors() < 2)
else if (HWLOC_SHOW_CRITICAL_ERRORS())
fprintf(stderr, "hwloc: Failed to recognize HWLOC_CPUKINDS_RANKING value %s\n", env);
}

View File

@@ -1,5 +1,5 @@
/*
* Copyright © 2013-2020 Inria. All rights reserved.
* Copyright © 2013-2022 Inria. All rights reserved.
* See COPYING in top-level directory.
*/
@@ -218,7 +218,7 @@ hwloc_diff_trees(hwloc_topology_t topo1, hwloc_obj_t obj1,
struct hwloc_info_s *info1 = &obj1->infos[i], *info2 = &obj2->infos[i];
if (strcmp(info1->name, info2->name))
goto out_too_complex;
if (strcmp(obj1->infos[i].value, obj2->infos[i].value)) {
if (strcmp(info1->value, info2->value)) {
err = hwloc_append_diff_obj_attr_string(obj1,
HWLOC_TOPOLOGY_DIFF_OBJ_ATTR_INFO,
info1->name,

View File

@@ -1,5 +1,5 @@
/*
* Copyright © 2010-2021 Inria. All rights reserved.
* Copyright © 2010-2022 Inria. All rights reserved.
* Copyright © 2011-2012 Université Bordeaux
* Copyright © 2011 Cisco Systems, Inc. All rights reserved.
* See COPYING in top-level directory.
@@ -860,7 +860,7 @@ struct hwloc_distances_container_s {
struct hwloc_distances_s distances;
};
#define HWLOC_DISTANCES_CONTAINER_OFFSET ((char*)&((struct hwloc_distances_container_s*)NULL)->distances - (char*)NULL)
#define HWLOC_DISTANCES_CONTAINER_OFFSET ((uintptr_t)(&((struct hwloc_distances_container_s*)NULL)->distances) - (uintptr_t)NULL)
#define HWLOC_DISTANCES_CONTAINER(_d) (struct hwloc_distances_container_s *) ( ((char*)_d) - HWLOC_DISTANCES_CONTAINER_OFFSET )
static struct hwloc_internal_distances_s *

View File

@@ -1,11 +1,12 @@
/*
* Copyright © 2020-2021 Inria. All rights reserved.
* Copyright © 2020-2022 Inria. All rights reserved.
* See COPYING in top-level directory.
*/
#include "private/autogen/config.h"
#include "hwloc.h"
#include "private/private.h"
#include "private/debug.h"
/*****************************
@@ -49,36 +50,51 @@ hwloc__setup_memattr(struct hwloc_internal_memattr_s *imattr,
void
hwloc_internal_memattrs_prepare(struct hwloc_topology *topology)
{
#define NR_DEFAULT_MEMATTRS 4
topology->memattrs = malloc(NR_DEFAULT_MEMATTRS * sizeof(*topology->memattrs));
topology->memattrs = malloc(HWLOC_MEMATTR_ID_MAX * sizeof(*topology->memattrs));
if (!topology->memattrs)
return;
assert(HWLOC_MEMATTR_ID_CAPACITY < NR_DEFAULT_MEMATTRS);
hwloc__setup_memattr(&topology->memattrs[HWLOC_MEMATTR_ID_CAPACITY],
(char *) "Capacity",
HWLOC_MEMATTR_FLAG_HIGHER_FIRST,
HWLOC_IMATTR_FLAG_STATIC_NAME|HWLOC_IMATTR_FLAG_CONVENIENCE);
assert(HWLOC_MEMATTR_ID_LOCALITY < NR_DEFAULT_MEMATTRS);
hwloc__setup_memattr(&topology->memattrs[HWLOC_MEMATTR_ID_LOCALITY],
(char *) "Locality",
HWLOC_MEMATTR_FLAG_LOWER_FIRST,
HWLOC_IMATTR_FLAG_STATIC_NAME|HWLOC_IMATTR_FLAG_CONVENIENCE);
assert(HWLOC_MEMATTR_ID_BANDWIDTH < NR_DEFAULT_MEMATTRS);
hwloc__setup_memattr(&topology->memattrs[HWLOC_MEMATTR_ID_BANDWIDTH],
(char *) "Bandwidth",
HWLOC_MEMATTR_FLAG_HIGHER_FIRST|HWLOC_MEMATTR_FLAG_NEED_INITIATOR,
HWLOC_IMATTR_FLAG_STATIC_NAME);
assert(HWLOC_MEMATTR_ID_LATENCY < NR_DEFAULT_MEMATTRS);
hwloc__setup_memattr(&topology->memattrs[HWLOC_MEMATTR_ID_READ_BANDWIDTH],
(char *) "ReadBandwidth",
HWLOC_MEMATTR_FLAG_HIGHER_FIRST|HWLOC_MEMATTR_FLAG_NEED_INITIATOR,
HWLOC_IMATTR_FLAG_STATIC_NAME);
hwloc__setup_memattr(&topology->memattrs[HWLOC_MEMATTR_ID_WRITE_BANDWIDTH],
(char *) "WriteBandwidth",
HWLOC_MEMATTR_FLAG_HIGHER_FIRST|HWLOC_MEMATTR_FLAG_NEED_INITIATOR,
HWLOC_IMATTR_FLAG_STATIC_NAME);
hwloc__setup_memattr(&topology->memattrs[HWLOC_MEMATTR_ID_LATENCY],
(char *) "Latency",
HWLOC_MEMATTR_FLAG_LOWER_FIRST|HWLOC_MEMATTR_FLAG_NEED_INITIATOR,
HWLOC_IMATTR_FLAG_STATIC_NAME);
topology->nr_memattrs = NR_DEFAULT_MEMATTRS;
hwloc__setup_memattr(&topology->memattrs[HWLOC_MEMATTR_ID_READ_LATENCY],
(char *) "ReadLatency",
HWLOC_MEMATTR_FLAG_LOWER_FIRST|HWLOC_MEMATTR_FLAG_NEED_INITIATOR,
HWLOC_IMATTR_FLAG_STATIC_NAME);
hwloc__setup_memattr(&topology->memattrs[HWLOC_MEMATTR_ID_WRITE_LATENCY],
(char *) "WriteLatency",
HWLOC_MEMATTR_FLAG_LOWER_FIRST|HWLOC_MEMATTR_FLAG_NEED_INITIATOR,
HWLOC_IMATTR_FLAG_STATIC_NAME);
topology->nr_memattrs = HWLOC_MEMATTR_ID_MAX;
}
static void
@@ -1197,3 +1213,214 @@ hwloc_get_local_numanode_objs(hwloc_topology_t topology,
*nrp = i;
return 0;
}
/**************************************
* Using memattrs to identify HBM/DRAM
*/
struct hwloc_memory_tier_s {
hwloc_obj_t node;
uint64_t local_bw;
enum hwloc_memory_tier_type_e {
/* warning the order is important for guess_memory_tiers() after qsort() */
HWLOC_MEMORY_TIER_UNKNOWN,
HWLOC_MEMORY_TIER_DRAM,
HWLOC_MEMORY_TIER_HBM,
HWLOC_MEMORY_TIER_SPM, /* Specific-Purpose Memory is usually HBM, we'll use BW to confirm */
HWLOC_MEMORY_TIER_NVM,
HWLOC_MEMORY_TIER_GPU,
} type;
};
static int compare_tiers(const void *_a, const void *_b)
{
const struct hwloc_memory_tier_s *a = _a, *b = _b;
/* sort by type of tier first */
if (a->type != b->type)
return a->type - b->type;
/* then by bandwidth */
if (a->local_bw > b->local_bw)
return -1;
else if (a->local_bw < b->local_bw)
return 1;
return 0;
}
int
hwloc_internal_memattrs_guess_memory_tiers(hwloc_topology_t topology)
{
struct hwloc_internal_memattr_s *imattr;
struct hwloc_memory_tier_s *tiers;
unsigned i, j, n;
const char *env;
int spm_is_hbm = -1; /* -1 will guess from BW, 0 no, 1 forced */
int mark_dram = 1;
unsigned first_spm, first_nvm;
hwloc_uint64_t max_unknown_bw, min_spm_bw;
env = getenv("HWLOC_MEMTIERS_GUESS");
if (env) {
if (!strcmp(env, "none")) {
return 0;
} else if (!strcmp(env, "default")) {
/* nothing */
} else if (!strcmp(env, "spm_is_hbm")) {
hwloc_debug("Assuming SPM-tier is HBM, ignore bandwidth\n");
spm_is_hbm = 1;
} else if (HWLOC_SHOW_CRITICAL_ERRORS()) {
fprintf(stderr, "hwloc: Failed to recognize HWLOC_MEMTIERS_GUESS value %s\n", env);
}
}
imattr = &topology->memattrs[HWLOC_MEMATTR_ID_BANDWIDTH];
if (!(imattr->iflags & HWLOC_IMATTR_FLAG_CACHE_VALID))
hwloc__imattr_refresh(topology, imattr);
n = hwloc_get_nbobjs_by_depth(topology, HWLOC_TYPE_DEPTH_NUMANODE);
assert(n);
tiers = malloc(n * sizeof(*tiers));
if (!tiers)
return -1;
for(i=0; i<n; i++) {
hwloc_obj_t node;
const char *daxtype;
struct hwloc_internal_location_s iloc;
struct hwloc_internal_memattr_target_s *imtg = NULL;
struct hwloc_internal_memattr_initiator_s *imi;
node = hwloc_get_obj_by_depth(topology, HWLOC_TYPE_DEPTH_NUMANODE, i);
assert(node);
tiers[i].node = node;
/* defaults */
tiers[i].type = HWLOC_MEMORY_TIER_UNKNOWN;
tiers[i].local_bw = 0; /* unknown */
daxtype = hwloc_obj_get_info_by_name(node, "DAXType");
/* mark NVM, SPM and GPU nodes */
if (daxtype && !strcmp(daxtype, "NVM"))
tiers[i].type = HWLOC_MEMORY_TIER_NVM;
if (daxtype && !strcmp(daxtype, "SPM"))
tiers[i].type = HWLOC_MEMORY_TIER_SPM;
if (node->subtype && !strcmp(node->subtype, "GPUMemory"))
tiers[i].type = HWLOC_MEMORY_TIER_GPU;
if (spm_is_hbm == -1) {
for(j=0; j<imattr->nr_targets; j++)
if (imattr->targets[j].obj == node) {
imtg = &imattr->targets[j];
break;
}
if (imtg && !hwloc_bitmap_iszero(node->cpuset)) {
iloc.type = HWLOC_LOCATION_TYPE_CPUSET;
iloc.location.cpuset = node->cpuset;
imi = hwloc__memattr_target_get_initiator(imtg, &iloc, 0);
if (imi)
tiers[i].local_bw = imi->value;
}
}
}
/* sort tiers */
qsort(tiers, n, sizeof(*tiers), compare_tiers);
hwloc_debug("Sorting memory tiers...\n");
for(i=0; i<n; i++)
hwloc_debug(" tier %u = node L#%u P#%u with tier type %d and local BW #%llu\n",
i,
tiers[i].node->logical_index, tiers[i].node->os_index,
tiers[i].type, (unsigned long long) tiers[i].local_bw);
/* now we have UNKNOWN tiers (sorted by BW), then SPM tiers (sorted by BW), then NVM, then GPU */
/* iterate over UNKNOWN tiers, and find their BW */
for(i=0; i<n; i++) {
if (tiers[i].type > HWLOC_MEMORY_TIER_UNKNOWN)
break;
}
first_spm = i;
/* get max BW from first */
if (first_spm > 0)
max_unknown_bw = tiers[0].local_bw;
else
max_unknown_bw = 0;
/* there are no DRAM or HBM tiers yet */
/* iterate over SPM tiers, and find their BW */
for(i=first_spm; i<n; i++) {
if (tiers[i].type > HWLOC_MEMORY_TIER_SPM)
break;
}
first_nvm = i;
/* get min BW from last */
if (first_nvm > first_spm)
min_spm_bw = tiers[first_nvm-1].local_bw;
else
min_spm_bw = 0;
/* FIXME: if there's more than 10% between some sets of nodes inside a tier, split it? */
/* FIXME: if there are cpuset-intersecting nodes in same tier, abort? */
if (spm_is_hbm == -1) {
/* if we have BW for all SPM and UNKNOWN
* and all SPM BW are 2x superior to all UNKNOWN BW
*/
hwloc_debug("UNKNOWN-memory-tier max bandwidth %llu\n", (unsigned long long) max_unknown_bw);
hwloc_debug("SPM-memory-tier min bandwidth %llu\n", (unsigned long long) min_spm_bw);
if (max_unknown_bw > 0 && min_spm_bw > 0 && max_unknown_bw*2 < min_spm_bw) {
hwloc_debug("assuming SPM means HBM and !SPM means DRAM since bandwidths are very different\n");
spm_is_hbm = 1;
} else {
hwloc_debug("cannot assume SPM means HBM\n");
spm_is_hbm = 0;
}
}
if (spm_is_hbm) {
for(i=0; i<first_spm; i++)
tiers[i].type = HWLOC_MEMORY_TIER_DRAM;
for(i=first_spm; i<first_nvm; i++)
tiers[i].type = HWLOC_MEMORY_TIER_HBM;
}
if (first_spm == n)
mark_dram = 0;
/* now apply subtypes */
for(i=0; i<n; i++) {
const char *type = NULL;
if (tiers[i].node->subtype) /* don't overwrite the existing subtype */
continue;
switch (tiers[i].type) {
case HWLOC_MEMORY_TIER_DRAM:
if (mark_dram)
type = "DRAM";
break;
case HWLOC_MEMORY_TIER_HBM:
type = "HBM";
break;
case HWLOC_MEMORY_TIER_SPM:
type = "SPM";
break;
case HWLOC_MEMORY_TIER_NVM:
type = "NVM";
break;
default:
/* GPU memory is already marked with subtype="GPUMemory",
* UNKNOWN doesn't deserve any subtype
*/
break;
}
if (type) {
hwloc_debug("Marking node L#%u P#%u as %s\n", tiers[i].node->logical_index, tiers[i].node->os_index, type);
tiers[i].node->subtype = strdup(type);
}
}
free(tiers);
return 0;
}

View File

@@ -1,5 +1,5 @@
/*
* Copyright © 2009-2021 Inria. All rights reserved.
* Copyright © 2009-2022 Inria. All rights reserved.
* See COPYING in top-level directory.
*/
@@ -119,6 +119,13 @@ hwloc_pci_discovery_init(struct hwloc_topology *topology)
topology->pci_forced_locality = NULL;
topology->first_pci_locality = topology->last_pci_locality = NULL;
#define HWLOC_PCI_LOCALITY_QUIRK_CRAY_EX235A (1ULL<<0)
#define HWLOC_PCI_LOCALITY_QUIRK_FAKE (1ULL<<62)
topology->pci_locality_quirks = (uint64_t) -1;
/* -1 is unknown, 0 is disabled, >0 is bitmask of enabled quirks.
* bit 63 should remain unused so that -1 is unaccessible as a bitmask.
*/
}
void
@@ -146,7 +153,7 @@ hwloc_pci_discovery_prepare(struct hwloc_topology *topology)
}
free(buffer);
} else {
if (hwloc_hide_errors() < 2)
if (HWLOC_SHOW_CRITICAL_ERRORS())
fprintf(stderr, "hwloc/pci: Ignoring HWLOC_PCI_LOCALITY file `%s' too large (%lu bytes)\n",
env, (unsigned long) st.st_size);
}
@@ -333,7 +340,7 @@ hwloc_pci_add_object(struct hwloc_obj *parent, struct hwloc_obj **parent_io_firs
}
case HWLOC_PCI_BUSID_EQUAL: {
static int reported = 0;
if (!reported && hwloc_hide_errors() < 2) {
if (!reported && HWLOC_SHOW_CRITICAL_ERRORS()) {
fprintf(stderr, "*********************************************************\n");
fprintf(stderr, "* hwloc %s received invalid PCI information.\n", HWLOC_VERSION);
fprintf(stderr, "*\n");
@@ -442,13 +449,90 @@ hwloc_pcidisc_add_hostbridges(struct hwloc_topology *topology,
return new;
}
static struct hwloc_obj *
hwloc_pci_fixup_busid_parent(struct hwloc_topology *topology __hwloc_attribute_unused,
struct hwloc_pcidev_attr_s *busid __hwloc_attribute_unused,
struct hwloc_obj *parent __hwloc_attribute_unused)
/* return 1 if a quirk was applied */
static int
hwloc__pci_find_busid_parent_quirk(struct hwloc_topology *topology,
struct hwloc_pcidev_attr_s *busid,
hwloc_cpuset_t cpuset)
{
/* no quirk for now */
return parent;
if (topology->pci_locality_quirks == (uint64_t)-1 /* unknown */) {
const char *dmi_board_name, *env;
/* first invokation, detect which quirks are needed */
topology->pci_locality_quirks = 0; /* no quirk yet */
dmi_board_name = hwloc_obj_get_info_by_name(hwloc_get_root_obj(topology), "DMIBoardName");
if (dmi_board_name && !strcmp(dmi_board_name, "HPE CRAY EX235A")) {
hwloc_debug("enabling for PCI locality quirk for HPE Cray EX235A\n");
topology->pci_locality_quirks |= HWLOC_PCI_LOCALITY_QUIRK_CRAY_EX235A;
}
env = getenv("HWLOC_PCI_LOCALITY_QUIRK_FAKE");
if (env && atoi(env)) {
hwloc_debug("enabling for PCI locality fake quirk (attaching everything to last PU)\n");
topology->pci_locality_quirks |= HWLOC_PCI_LOCALITY_QUIRK_FAKE;
}
}
if (topology->pci_locality_quirks & HWLOC_PCI_LOCALITY_QUIRK_FAKE) {
unsigned last = hwloc_bitmap_last(hwloc_topology_get_topology_cpuset(topology));
hwloc_bitmap_set(cpuset, last);
return 1;
}
if (topology->pci_locality_quirks & HWLOC_PCI_LOCALITY_QUIRK_CRAY_EX235A) {
/* AMD Trento has xGMI ports connected to individual CCDs (8 cores + L3)
* instead of NUMA nodes (pairs of CCDs within Trento) as is usual in AMD EPYC CPUs.
* This is not described by the ACPI tables, hence we need to manually hardwire
* the xGMI locality for the (currently single) server that currently uses that CPU.
* It's not clear if ACPI tables can/will ever be fixed (would require one initiator
* proximity domain per CCD), or if Linux can/will work around the issue.
*/
if (busid->domain == 0) {
if (busid->bus >= 0xd0 && busid->bus <= 0xd1) {
hwloc_bitmap_set_range(cpuset, 0, 7);
hwloc_bitmap_set_range(cpuset, 64, 71);
return 1;
}
if (busid->bus >= 0xd4 && busid->bus <= 0xd6) {
hwloc_bitmap_set_range(cpuset, 8, 15);
hwloc_bitmap_set_range(cpuset, 72, 79);
return 1;
}
if (busid->bus >= 0xc8 && busid->bus <= 0xc9) {
hwloc_bitmap_set_range(cpuset, 16, 23);
hwloc_bitmap_set_range(cpuset, 80, 87);
return 1;
}
if (busid->bus >= 0xcc && busid->bus <= 0xce) {
hwloc_bitmap_set_range(cpuset, 24, 31);
hwloc_bitmap_set_range(cpuset, 88, 95);
return 1;
}
if (busid->bus >= 0xd8 && busid->bus <= 0xd9) {
hwloc_bitmap_set_range(cpuset, 32, 39);
hwloc_bitmap_set_range(cpuset, 96, 103);
return 1;
}
if (busid->bus >= 0xdc && busid->bus <= 0xde) {
hwloc_bitmap_set_range(cpuset, 40, 47);
hwloc_bitmap_set_range(cpuset, 104, 111);
return 1;
}
if (busid->bus >= 0xc0 && busid->bus <= 0xc1) {
hwloc_bitmap_set_range(cpuset, 48, 55);
hwloc_bitmap_set_range(cpuset, 112, 119);
return 1;
}
if (busid->bus >= 0xc4 && busid->bus <= 0xc6) {
hwloc_bitmap_set_range(cpuset, 56, 63);
hwloc_bitmap_set_range(cpuset, 120, 127);
return 1;
}
}
}
return 0;
}
static struct hwloc_obj *
@@ -457,7 +541,7 @@ hwloc__pci_find_busid_parent(struct hwloc_topology *topology, struct hwloc_pcide
hwloc_bitmap_t cpuset = hwloc_bitmap_alloc();
hwloc_obj_t parent;
int forced = 0;
int noquirks = 0;
int noquirks = 0, got_quirked = 0;
unsigned i;
int err;
@@ -490,7 +574,7 @@ hwloc__pci_find_busid_parent(struct hwloc_topology *topology, struct hwloc_pcide
if (env) {
static int reported = 0;
if (!topology->pci_has_forced_locality && !reported) {
if (!hwloc_hide_errors())
if (HWLOC_SHOW_ALL_ERRORS())
fprintf(stderr, "hwloc/pci: Environment variable %s is deprecated, please use HWLOC_PCI_LOCALITY instead.\n", env);
reported = 1;
}
@@ -505,7 +589,13 @@ hwloc__pci_find_busid_parent(struct hwloc_topology *topology, struct hwloc_pcide
}
}
if (!forced) {
if (!forced && !noquirks && topology->pci_locality_quirks /* either quirks are unknown yet, or some are enabled */) {
err = hwloc__pci_find_busid_parent_quirk(topology, busid, cpuset);
if (err > 0)
got_quirked = 1;
}
if (!forced && !got_quirked) {
/* get the cpuset by asking the backend that provides the relevant hook, if any. */
struct hwloc_backend *backend = topology->get_pci_busid_cpuset_backend;
if (backend)
@@ -520,11 +610,7 @@ hwloc__pci_find_busid_parent(struct hwloc_topology *topology, struct hwloc_pcide
hwloc_debug_bitmap(" will attach PCI bus to cpuset %s\n", cpuset);
parent = hwloc_find_insert_io_parent_by_complete_cpuset(topology, cpuset);
if (parent) {
if (!noquirks)
/* We found a valid parent. Check that the OS didn't report invalid locality */
parent = hwloc_pci_fixup_busid_parent(topology, busid, parent);
} else {
if (!parent) {
/* Fallback to root */
parent = hwloc_get_root_obj(topology);
}
@@ -805,19 +891,28 @@ hwloc_pcidisc_find_linkspeed(const unsigned char *config,
memcpy(&linksta, &config[offset + HWLOC_PCI_EXP_LNKSTA], 4);
speed = linksta & HWLOC_PCI_EXP_LNKSTA_SPEED; /* PCIe generation */
width = (linksta & HWLOC_PCI_EXP_LNKSTA_WIDTH) >> 4; /* how many lanes */
/* PCIe Gen1 = 2.5GT/s signal-rate per lane with 8/10 encoding = 0.25GB/s data-rate per lane
* PCIe Gen2 = 5 GT/s signal-rate per lane with 8/10 encoding = 0.5 GB/s data-rate per lane
* PCIe Gen3 = 8 GT/s signal-rate per lane with 128/130 encoding = 1 GB/s data-rate per lane
* PCIe Gen4 = 16 GT/s signal-rate per lane with 128/130 encoding = 2 GB/s data-rate per lane
* PCIe Gen5 = 32 GT/s signal-rate per lane with 128/130 encoding = 4 GB/s data-rate per lane
* PCIe Gen6 = 64 GT/s signal-rate per lane with 128/130 encoding = 8 GB/s data-rate per lane
/*
* These are single-direction bandwidths only.
*
* Gen1 used NRZ with 8/10 encoding.
* PCIe Gen1 = 2.5GT/s signal-rate per lane x 8/10 = 0.25GB/s data-rate per lane
* PCIe Gen2 = 5 GT/s signal-rate per lane x 8/10 = 0.5 GB/s data-rate per lane
* Gen3 switched to NRZ with 128/130 encoding.
* PCIe Gen3 = 8 GT/s signal-rate per lane x 128/130 = 1 GB/s data-rate per lane
* PCIe Gen4 = 16 GT/s signal-rate per lane x 128/130 = 2 GB/s data-rate per lane
* PCIe Gen5 = 32 GT/s signal-rate per lane x 128/130 = 4 GB/s data-rate per lane
* Gen6 switched to PAM with with 242/256 FLIT (242B payload protected by 8B CRC + 6B FEC).
* PCIe Gen6 = 64 GT/s signal-rate per lane x 242/256 = 8 GB/s data-rate per lane
* PCIe Gen7 = 128GT/s signal-rate per lane x 242/256 = 16 GB/s data-rate per lane
*/
/* lanespeed in Gbit/s */
if (speed <= 2)
lanespeed = 2.5f * speed * 0.8f;
else if (speed <= 5)
lanespeed = 8.0f * (1<<(speed-3)) * 128/130;
else
lanespeed = 8.0f * (1<<(speed-3)) * 128/130; /* assume Gen7 will be 128 GT/s and so on */
lanespeed = 8.0f * (1<<(speed-3)) * 242/256; /* assume Gen8 will be 256 GT/s and so on */
/* linkspeed in GB/s */
*linkspeed = lanespeed * width / 8;
@@ -944,6 +1039,7 @@ hwloc_pci_class_string(unsigned short class_id)
switch (class_id) {
case 0x0500: return "RAM";
case 0x0501: return "Flash";
case 0x0502: return "CXLMem";
}
return "Memory";
case 0x06:

View File

@@ -1,6 +1,6 @@
/*
* Copyright © 2009 CNRS
* Copyright © 2009-2020 Inria. All rights reserved.
* Copyright © 2009-2022 Inria. All rights reserved.
* Copyright © 2009-2010 Université Bordeaux
* Copyright © 2009-2011 Cisco Systems, Inc. All rights reserved.
* See COPYING in top-level directory.
@@ -323,17 +323,29 @@ hwloc_synthetic_parse_memory_attr(const char *attr, const char **endp)
hwloc_uint64_t size;
size = strtoull(attr, (char **) &endptr, 0);
if (!hwloc_strncasecmp(endptr, "TB", 2)) {
size *= 1000ULL*1000ULL*1000ULL*1000ULL;
endptr += 2;
} else if (!hwloc_strncasecmp(endptr, "TiB", 3)) {
size <<= 40;
endptr += 2;
endptr += 3;
} else if (!hwloc_strncasecmp(endptr, "GB", 2)) {
size *= 1000ULL*1000ULL*1000ULL;
endptr += 2;
} else if (!hwloc_strncasecmp(endptr, "GiB", 3)) {
size <<= 30;
endptr += 2;
endptr += 3;
} else if (!hwloc_strncasecmp(endptr, "MB", 2)) {
size *= 1000ULL*1000ULL;
endptr += 2;
} else if (!hwloc_strncasecmp(endptr, "MiB", 3)) {
size <<= 20;
endptr += 2;
endptr += 3;
} else if (!hwloc_strncasecmp(endptr, "kB", 2)) {
size <<= 10;
size *= 1000ULL;
endptr += 2;
} else if (!hwloc_strncasecmp(endptr, "kiB", 3)) {
size <<= 10;
endptr += 3;
}
*endp = endptr;
return size;
@@ -802,15 +814,15 @@ hwloc_backend_synthetic_init(struct hwloc_synthetic_backend_data_s *data,
} else if (hwloc__obj_type_is_cache(type)) {
if (!curlevel->attr.memorysize) {
if (1 == curlevel->attr.depth)
/* 32Kb in L1 */
/* 32KiB in L1 */
curlevel->attr.memorysize = 32*1024;
else
/* *4 at each level, starting from 1MB for L2, unified */
/* *4 at each level, starting from 1MiB for L2, unified */
curlevel->attr.memorysize = 256ULL*1024 << (2*curlevel->attr.depth);
}
} else if (type == HWLOC_OBJ_NUMANODE && !curlevel->attr.memorysize) {
/* 1GB in memory nodes. */
/* 1GiB in memory nodes. */
curlevel->attr.memorysize = 1024*1024*1024;
}

View File

@@ -1,6 +1,6 @@
/*
* Copyright © 2009 CNRS
* Copyright © 2009-2021 Inria. All rights reserved.
* Copyright © 2009-2022 Inria. All rights reserved.
* Copyright © 2009-2012, 2020 Université Bordeaux
* Copyright © 2011 Cisco Systems, Inc. All rights reserved.
* See COPYING in top-level directory.
@@ -366,7 +366,7 @@ hwloc_win_get_processor_groups(void)
hwloc_debug("found %lu windows processor groups\n", nr_processor_groups);
if (nr_processor_groups > 1 && SIZEOF_VOID_P == 4) {
if (!hwloc_hide_errors())
if (HWLOC_SHOW_ALL_ERRORS())
fprintf(stderr, "hwloc: multiple processor groups found on 32bits Windows, topology may be invalid/incomplete.\n");
}

View File

@@ -1,5 +1,5 @@
/*
* Copyright © 2010-2021 Inria. All rights reserved.
* Copyright © 2010-2022 Inria. All rights reserved.
* Copyright © 2010-2013 Université Bordeaux
* Copyright © 2010-2011 Cisco Systems, Inc. All rights reserved.
* See COPYING in top-level directory.
@@ -1349,7 +1349,7 @@ look_procs(struct hwloc_backend *backend, struct procinfo *infos, unsigned long
if (data->apicid_unique) {
summarize(backend, infos, flags);
if (has_hybrid(features)) {
if (has_hybrid(features) && !(topology->flags & HWLOC_TOPOLOGY_FLAG_NO_CPUKINDS)) {
/* use hybrid info for cpukinds */
hwloc_bitmap_t atomset = hwloc_bitmap_alloc();
hwloc_bitmap_t coreset = hwloc_bitmap_alloc();

View File

@@ -1,6 +1,6 @@
/*
* Copyright © 2009 CNRS
* Copyright © 2009-2021 Inria. All rights reserved.
* Copyright © 2009-2022 Inria. All rights reserved.
* Copyright © 2009-2011, 2020 Université Bordeaux
* Copyright © 2009-2018 Cisco Systems, Inc. All rights reserved.
* See COPYING in top-level directory.
@@ -123,6 +123,17 @@ hwloc__xml_import_object_attr(struct hwloc_topology *topology,
fprintf(stderr, "%s: unexpected zero gp_index, topology may be invalid\n", state->global->msgprefix);
if (obj->gp_index >= topology->next_gp_index)
topology->next_gp_index = obj->gp_index + 1;
} else if (!strcmp(name, "id")) { /* forward compat */
if (!strncmp(value, "obj", 3)) {
obj->gp_index = strtoull(value+3, NULL, 10);
if (!obj->gp_index && hwloc__xml_verbose())
fprintf(stderr, "%s: unexpected zero id, topology may be invalid\n", state->global->msgprefix);
if (obj->gp_index >= topology->next_gp_index)
topology->next_gp_index = obj->gp_index + 1;
} else {
if (hwloc__xml_verbose())
fprintf(stderr, "%s: unexpected id `%s' not-starting with `obj', ignoring\n", state->global->msgprefix, value);
}
} else if (!strcmp(name, "cpuset")) {
if (!obj->cpuset)
obj->cpuset = hwloc_bitmap_alloc();
@@ -263,7 +274,7 @@ hwloc__xml_import_object_attr(struct hwloc_topology *topology,
#ifndef HWLOC_HAVE_32BITS_PCI_DOMAIN
} else if (domain > 0xffff) {
static int warned = 0;
if (!warned && hwloc_hide_errors() < 2)
if (!warned && HWLOC_SHOW_ALL_ERRORS())
fprintf(stderr, "hwloc/xml: Ignoring PCI device with non-16bit domain.\nPass --enable-32bits-pci-domain to configure to support such devices\n(warning: it would break the library ABI, don't enable unless really needed).\n");
warned = 1;
*ignore = 1;
@@ -363,7 +374,7 @@ hwloc__xml_import_object_attr(struct hwloc_topology *topology,
#ifndef HWLOC_HAVE_32BITS_PCI_DOMAIN
} else if (domain > 0xffff) {
static int warned = 0;
if (!warned && hwloc_hide_errors() < 2)
if (!warned && HWLOC_SHOW_ALL_ERRORS())
fprintf(stderr, "hwloc/xml: Ignoring bridge to PCI with non-16bit domain.\nPass --enable-32bits-pci-domain to configure to support such devices\n(warning: it would break the library ABI, don't enable unless really needed).\n");
warned = 1;
*ignore = 1;
@@ -1235,7 +1246,7 @@ hwloc__xml_import_object(hwloc_topology_t topology,
/* next should be before cur */
if (!childrengotignored) {
static int reported = 0;
if (!reported && hwloc_hide_errors() < 2) {
if (!reported && HWLOC_SHOW_CRITICAL_ERRORS()) {
hwloc__xml_import_report_outoforder(topology, next, cur);
reported = 1;
}
@@ -1568,6 +1579,9 @@ hwloc__xml_v2import_distances(hwloc_topology_t topology,
}
}
if (topology->flags & HWLOC_TOPOLOGY_FLAG_NO_DISTANCES)
goto out_ignore;
hwloc_internal_distances_add_by_index(topology, name, unique_type, different_types, nbobjs, indexes, u64values, kind, 0 /* assume grouping was applied when this matrix was discovered before exporting to XML */);
/* prevent freeing below */
@@ -1722,7 +1736,8 @@ hwloc__xml_import_memattr(hwloc_topology_t topology,
}
}
if (name && flags != (unsigned long) -1) {
if (name && flags != (unsigned long) -1
&& !(topology->flags & HWLOC_TOPOLOGY_FLAG_NO_MEMATTRS)) {
hwloc_memattr_id_t _id;
ret = hwloc_memattr_get_by_name(topology, name, &_id);
@@ -1833,7 +1848,13 @@ hwloc__xml_import_cpukind(hwloc_topology_t topology,
goto error;
}
hwloc_internal_cpukinds_register(topology, cpuset, forced_efficiency, infos, nr_infos, HWLOC_CPUKINDS_REGISTER_FLAG_OVERWRITE_FORCED_EFFICIENCY);
if (topology->flags & HWLOC_TOPOLOGY_FLAG_NO_CPUKINDS) {
hwloc__free_infos(infos, nr_infos);
hwloc_bitmap_free(cpuset);
} else {
hwloc_internal_cpukinds_register(topology, cpuset, forced_efficiency, infos, nr_infos, HWLOC_CPUKINDS_REGISTER_FLAG_OVERWRITE_FORCED_EFFICIENCY);
hwloc__free_infos(infos, nr_infos);
}
return state->global->close_tag(state);
@@ -2168,7 +2189,8 @@ done:
* but it would require to have those objects in the original XML order (like the first_numanode cousin-list).
* because the topology order can be different if some parents are ignored during load.
*/
if (nbobjs == data->nbnumanodes) {
if (nbobjs == data->nbnumanodes
&& !(topology->flags & HWLOC_TOPOLOGY_FLAG_NO_DISTANCES)) {
hwloc_obj_t *objs = malloc(nbobjs*sizeof(hwloc_obj_t));
uint64_t *values = malloc(nbobjs*nbobjs*sizeof(*values));
assert(data->nbnumanodes > 0); /* v1dist->nbobjs is >0 after import */
@@ -2650,7 +2672,7 @@ hwloc__xml_export_object_contents (hwloc__xml_export_state_t state, hwloc_topolo
logical_to_v2array = malloc(nbobjs * sizeof(*logical_to_v2array));
if (!logical_to_v2array) {
if (!hwloc_hide_errors())
if (HWLOC_SHOW_ALL_ERRORS())
fprintf(stderr, "hwloc/xml/export/v1: failed to allocated logical_to_v2array\n");
continue;
}
@@ -3124,9 +3146,11 @@ hwloc__xml_export_memattrs(hwloc__xml_export_state_t state, hwloc_topology_t top
continue;
imattr = &topology->memattrs[id];
if ((id == HWLOC_MEMATTR_ID_LATENCY || id == HWLOC_MEMATTR_ID_BANDWIDTH)
&& !imattr->nr_targets)
/* no need to export target-less attributes for initial attributes, no release support attributes without those definitions */
if (id < HWLOC_MEMATTR_ID_MAX && !imattr->nr_targets)
/* no need to export standard attributes without any target,
* their definition is now standardized,
* the old hwloc importing this XML may recreate these attributes just like it would for a non-imported topology.
*/
continue;
state->new_child(state, &mstate, "memattr");

View File

@@ -1,6 +1,6 @@
/*
* Copyright © 2009 CNRS
* Copyright © 2009-2021 Inria. All rights reserved.
* Copyright © 2009-2022 Inria. All rights reserved.
* Copyright © 2009-2012, 2020 Université Bordeaux
* Copyright © 2009-2011 Cisco Systems, Inc. All rights reserved.
* Copyright © 2022 IBM Corporation. All rights reserved.
@@ -114,14 +114,25 @@ int hwloc_topology_abi_check(hwloc_topology_t topology)
return topology->topology_abi != HWLOC_TOPOLOGY_ABI ? -1 : 0;
}
/* callers should rather use wrappers HWLOC_SHOW_ALL_ERRORS() and HWLOC_SHOW_CRITICAL_ERRORS() for clarity */
int hwloc_hide_errors(void)
{
static int hide = 1; /* only show critical errors by default. lstopo will show others */
static int checked = 0;
if (!checked) {
const char *envvar = getenv("HWLOC_HIDE_ERRORS");
if (envvar)
if (envvar) {
hide = atoi(envvar);
#ifdef HWLOC_DEBUG
} else {
/* if debug is enabled and HWLOC_DEBUG_VERBOSE isn't forced to 0,
* show all errors jus like we show all debug messages.
*/
envvar = getenv("HWLOC_DEBUG_VERBOSE");
if (!envvar || atoi(envvar))
hide = 0;
#endif
}
checked = 1;
}
return hide;
@@ -158,7 +169,7 @@ static void report_insert_error(hwloc_obj_t new, hwloc_obj_t old, const char *ms
{
static int reported = 0;
if (reason && !reported && hwloc_hide_errors() < 2) {
if (reason && !reported && HWLOC_SHOW_CRITICAL_ERRORS()) {
char newstr[512];
char oldstr[512];
report_insert_error_format_obj(newstr, sizeof(newstr), new);
@@ -3178,7 +3189,7 @@ hwloc_connect_levels(hwloc_topology_t topology)
tmpnbobjs = realloc(topology->level_nbobjects,
2 * topology->nb_levels_allocated * sizeof(*topology->level_nbobjects));
if (!tmplevels || !tmpnbobjs) {
if (hwloc_hide_errors() < 2)
if (HWLOC_SHOW_CRITICAL_ERRORS())
fprintf(stderr, "hwloc: failed to realloc level arrays to %u\n", topology->nb_levels_allocated * 2);
/* if one realloc succeeded, make sure the caller will free the new buffer */
@@ -3536,6 +3547,8 @@ hwloc_discover(struct hwloc_topology *topology,
/*
* Additional discovery
*/
hwloc_pci_discovery_prepare(topology);
if (topology->backend_phases & HWLOC_DISC_PHASE_PCI) {
dstatus->phase = HWLOC_DISC_PHASE_PCI;
hwloc_discover_by_phase(topology, dstatus, "PCI");
@@ -3553,6 +3566,8 @@ hwloc_discover(struct hwloc_topology *topology,
hwloc_discover_by_phase(topology, dstatus, "ANNOTATE");
}
hwloc_pci_discovery_exit(topology); /* pci needed up to annotate */
if (getenv("HWLOC_DEBUG_SORT_CHILDREN"))
hwloc_debug_sort_children(topology->levels[0][0]);
@@ -3565,17 +3580,17 @@ hwloc_discover(struct hwloc_topology *topology,
hwloc_debug("%s", "\nRemoving empty objects\n");
remove_empty(topology, &topology->levels[0][0]);
if (!topology->levels[0][0]) {
if (hwloc_hide_errors() < 2)
if (HWLOC_SHOW_CRITICAL_ERRORS())
fprintf(stderr, "hwloc: Topology became empty, aborting!\n");
return -1;
}
if (hwloc_bitmap_iszero(topology->levels[0][0]->cpuset)) {
if (hwloc_hide_errors() < 2)
if (HWLOC_SHOW_CRITICAL_ERRORS())
fprintf(stderr, "hwloc: Topology does not contain any PU, aborting!\n");
return -1;
}
if (hwloc_bitmap_iszero(topology->levels[0][0]->nodeset)) {
if (hwloc_hide_errors() < 2)
if (HWLOC_SHOW_CRITICAL_ERRORS())
fprintf(stderr, "hwloc: Topology does not contain any NUMA node, aborting!\n");
return -1;
}
@@ -3811,7 +3826,16 @@ hwloc_topology_set_flags (struct hwloc_topology *topology, unsigned long flags)
return -1;
}
if (flags & ~(HWLOC_TOPOLOGY_FLAG_INCLUDE_DISALLOWED|HWLOC_TOPOLOGY_FLAG_IS_THISSYSTEM|HWLOC_TOPOLOGY_FLAG_THISSYSTEM_ALLOWED_RESOURCES|HWLOC_TOPOLOGY_FLAG_IMPORT_SUPPORT|HWLOC_TOPOLOGY_FLAG_RESTRICT_TO_CPUBINDING|HWLOC_TOPOLOGY_FLAG_RESTRICT_TO_MEMBINDING|HWLOC_TOPOLOGY_FLAG_DONT_CHANGE_BINDING)) {
if (flags & ~(HWLOC_TOPOLOGY_FLAG_INCLUDE_DISALLOWED
|HWLOC_TOPOLOGY_FLAG_IS_THISSYSTEM
|HWLOC_TOPOLOGY_FLAG_THISSYSTEM_ALLOWED_RESOURCES
|HWLOC_TOPOLOGY_FLAG_IMPORT_SUPPORT
|HWLOC_TOPOLOGY_FLAG_RESTRICT_TO_CPUBINDING
|HWLOC_TOPOLOGY_FLAG_RESTRICT_TO_MEMBINDING
|HWLOC_TOPOLOGY_FLAG_DONT_CHANGE_BINDING
|HWLOC_TOPOLOGY_FLAG_NO_DISTANCES
|HWLOC_TOPOLOGY_FLAG_NO_MEMATTRS
|HWLOC_TOPOLOGY_FLAG_NO_CPUKINDS)) {
errno = EINVAL;
return -1;
}
@@ -4076,15 +4100,11 @@ hwloc_topology_load (struct hwloc_topology *topology)
*/
hwloc_set_binding_hooks(topology);
hwloc_pci_discovery_prepare(topology);
/* actual topology discovery */
err = hwloc_discover(topology, &dstatus);
if (err < 0)
goto out;
hwloc_pci_discovery_exit(topology);
#ifndef HWLOC_DEBUG
if (getenv("HWLOC_DEBUG_CHECK"))
#endif
@@ -4106,6 +4126,7 @@ hwloc_topology_load (struct hwloc_topology *topology)
/* Same for memattrs */
hwloc_internal_memattrs_need_refresh(topology);
hwloc_internal_memattrs_refresh(topology);
hwloc_internal_memattrs_guess_memory_tiers(topology);
topology->is_loaded = 1;

View File

@@ -1,4 +1,4 @@
cmake_minimum_required (VERSION 2.8.12)
cmake_minimum_required(VERSION 3.1)
project (ethash C)
set(CMAKE_C_FLAGS_RELEASE "${CMAKE_C_FLAGS_RELEASE} -Os")

View File

@@ -33,6 +33,7 @@
#include "crypto/common/Nonce.h"
#include "crypto/common/VirtualMemory.h"
#include "crypto/rx/Rx.h"
#include "crypto/rx/RxCache.h"
#include "crypto/rx/RxDataset.h"
#include "crypto/rx/RxVm.h"
#include "crypto/ghostrider/ghostrider.h"
@@ -77,8 +78,11 @@ xmrig::CpuWorker<N>::CpuWorker(size_t id, const CpuLaunchData &data) :
{
# ifdef XMRIG_ALGO_CN_HEAVY
// cn-heavy optimization for Zen3 CPUs
const bool is_vermeer = (Cpu::info()->arch() == ICpuInfo::ARCH_ZEN3) && (Cpu::info()->model() == 0x21);
if ((N == 1) && (m_av == CnHash::AV_SINGLE) && (m_algorithm.family() == Algorithm::CN_HEAVY) && (m_assembly != Assembly::NONE) && is_vermeer) {
const auto arch = Cpu::info()->arch();
const uint32_t model = Cpu::info()->model();
const bool is_vermeer = (arch == ICpuInfo::ARCH_ZEN3) && (model == 0x21);
const bool is_raphael = (arch == ICpuInfo::ARCH_ZEN4) && (model == 0x61);
if ((N == 1) && (m_av == CnHash::AV_SINGLE) && (m_algorithm.family() == Algorithm::CN_HEAVY) && (m_assembly != Assembly::NONE) && (is_vermeer || is_raphael)) {
std::lock_guard<std::mutex> lock(cn_heavyZen3MemoryMutex);
if (!cn_heavyZen3Memory) {
// Round up number of threads to the multiple of 8
@@ -142,6 +146,11 @@ void xmrig::CpuWorker<N>::allocateRandomX_VM()
uint8_t* scratchpad = m_memory->isHugePages() ? m_memory->scratchpad() : dataset->tryAllocateScrathpad();
m_vm = RxVm::create(dataset, scratchpad ? scratchpad : m_memory->scratchpad(), !m_hwAES, m_assembly, node());
}
else if (!dataset->get() && (m_job.currentJob().seed() != m_seed)) {
// Update RandomX light VM with the new seed
randomx_vm_set_cache(m_vm, dataset->cache()->get());
}
m_seed = m_job.currentJob().seed();
}
#endif

View File

@@ -97,6 +97,7 @@ private:
# ifdef XMRIG_ALGO_RANDOMX
randomx_vm *m_vm = nullptr;
Buffer m_seed;
# endif
# ifdef XMRIG_ALGO_GHOSTRIDER

View File

@@ -45,19 +45,21 @@ public:
ARCH_ZEN,
ARCH_ZEN_PLUS,
ARCH_ZEN2,
ARCH_ZEN3
ARCH_ZEN3,
ARCH_ZEN4
};
enum MsrMod : uint32_t {
MSR_MOD_NONE,
MSR_MOD_RYZEN_17H,
MSR_MOD_RYZEN_19H,
MSR_MOD_RYZEN_19H_ZEN4,
MSR_MOD_INTEL,
MSR_MOD_CUSTOM,
MSR_MOD_MAX
};
# define MSR_NAMES_LIST "none", "ryzen_17h", "ryzen_19h", "intel", "custom"
# define MSR_NAMES_LIST "none", "ryzen_17h", "ryzen_19h", "ryzen_19h_zen4", "intel", "custom"
enum Flag : uint32_t {
FLAG_AES,

View File

@@ -64,7 +64,7 @@ static_assert(kCpuFlagsSize == ICpuInfo::FLAG_MAX, "kCpuFlagsSize and FLAG_MAX m
#ifdef XMRIG_FEATURE_MSR
constexpr size_t kMsrArraySize = 5;
constexpr size_t kMsrArraySize = 6;
static const std::array<const char *, kMsrArraySize> msrNames = { MSR_NAMES_LIST };
static_assert(kMsrArraySize == ICpuInfo::MSR_MOD_MAX, "kMsrArraySize and MSR_MOD_MAX mismatch");
#endif
@@ -250,8 +250,14 @@ xmrig::BasicCpuInfo::BasicCpuInfo() :
break;
case 0x19:
m_arch = ARCH_ZEN3;
m_msrMod = MSR_MOD_RYZEN_19H;
if (m_model == 0x61) {
m_arch = ARCH_ZEN4;
m_msrMod = MSR_MOD_RYZEN_19H_ZEN4;
}
else {
m_arch = ARCH_ZEN3;
m_msrMod = MSR_MOD_RYZEN_19H;
}
break;
default:

View File

@@ -27,7 +27,7 @@
#if __ARM_FEATURE_CRYPTO && !defined(__APPLE__)
# include <sys/auxv.h>
# ifndef __FreeBSD__
# if !defined(XMRIG_OS_FREEBSD)
# include <asm/hwcap.h>
# else
# include <stdint.h>
@@ -71,7 +71,7 @@ xmrig::BasicCpuInfo::BasicCpuInfo() :
# if __ARM_FEATURE_CRYPTO
# if defined(__APPLE__)
m_flags.set(FLAG_AES, true);
# elif defined(__FreeBSD__)
# elif defined(XMRIG_OS_FREEBSD)
uint64_t isar0 = READ_SPECIALREG(id_aa64isar0_el1);
m_flags.set(FLAG_AES, ID_AA64ISAR0_AES_VAL(isar0) >= ID_AA64ISAR0_AES_BASE);
# else

View File

@@ -23,6 +23,9 @@
*/
#include <stdexcept>
#include "backend/opencl/runners/OclBaseRunner.h"
#include "backend/opencl/cl/OclSource.h"
#include "backend/opencl/OclCache.h"

View File

@@ -16,6 +16,9 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <stdexcept>
#include "backend/opencl/runners/OclCnRunner.h"
#include "backend/opencl/kernels/Cn0Kernel.h"
#include "backend/opencl/kernels/Cn1Kernel.h"

View File

@@ -16,6 +16,9 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <stdexcept>
#include "backend/opencl/runners/OclKawPowRunner.h"
#include "backend/common/Tags.h"
#include "3rdparty/libethash/ethash_internal.h"

View File

@@ -16,6 +16,9 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include <stdexcept>
#include "backend/opencl/runners/OclRxJitRunner.h"
#include "backend/opencl/cl/rx/randomx_run_gfx803.h"
#include "backend/opencl/cl/rx/randomx_run_gfx900.h"

View File

@@ -1,6 +1,6 @@
/* XMRig
* Copyright (c) 2018-2021 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2021 XMRig <https://github.com/xmrig>, <support@xmrig.com>
* Copyright (c) 2018-2023 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2023 XMRig <https://github.com/xmrig>, <support@xmrig.com>
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -16,7 +16,6 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include "base/kernel/Platform.h"
@@ -42,9 +41,12 @@ void xmrig::Platform::init(const char *userAgent)
# ifdef XMRIG_FEATURE_TLS
SSL_library_init();
SSL_load_error_strings();
# if OPENSSL_VERSION_NUMBER < 0x30000000L || defined(LIBRESSL_VERSION_NUMBER)
ERR_load_BIO_strings();
ERR_load_crypto_strings();
SSL_load_error_strings();
# endif
OpenSSL_add_all_digests();
# endif

View File

@@ -16,10 +16,12 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#ifdef __FreeBSD__
#ifdef XMRIG_OS_FREEBSD
# include <sys/types.h>
# include <sys/param.h>
# include <sys/cpuset.h>
# ifndef __DragonFly__
# include <sys/cpuset.h>
# endif
# include <pthread_np.h>
#endif
@@ -41,11 +43,6 @@
#include "version.h"
#ifdef __FreeBSD__
typedef cpuset_t cpu_set_t;
#endif
char *xmrig::Platform::createUserAgent()
{
constexpr const size_t max = 256;
@@ -74,6 +71,19 @@ char *xmrig::Platform::createUserAgent()
#ifndef XMRIG_FEATURE_HWLOC
#ifdef __DragonFly__
bool xmrig::Platform::setThreadAffinity(uint64_t cpu_id)
{
return true;
}
#else
#ifdef XMRIG_OS_FREEBSD
typedef cpuset_t cpu_set_t;
#endif
bool xmrig::Platform::setThreadAffinity(uint64_t cpu_id)
{
cpu_set_t mn;
@@ -89,7 +99,9 @@ bool xmrig::Platform::setThreadAffinity(uint64_t cpu_id)
std::this_thread::sleep_for(std::chrono::milliseconds(1));
return result;
}
#endif
#endif // __DragonFly__
#endif // XMRIG_FEATURE_HWLOC
void xmrig::Platform::setProcessPriority(int)

View File

@@ -247,6 +247,7 @@ void xmrig::BaseTransform::transform(rapidjson::Document &doc, int key, const ch
case IConfig::HttpPort: /* --http-port */
case IConfig::DonateLevelKey: /* --donate-level */
case IConfig::DaemonPollKey: /* --daemon-poll-interval */
case IConfig::DaemonJobTimeoutKey: /* --daemon-job-timeout */
case IConfig::DnsTtlKey: /* --dns-ttl */
case IConfig::DaemonZMQPortKey: /* --daemon-zmq-port */
return transformUint64(doc, key, static_cast<uint64_t>(strtol(arg, nullptr, 10)));
@@ -360,6 +361,9 @@ void xmrig::BaseTransform::transformUint64(rapidjson::Document &doc, int key, ui
case IConfig::DaemonPollKey: /* --daemon-poll-interval */
return add(doc, Pools::kPools, Pool::kDaemonPollInterval, arg);
case IConfig::DaemonJobTimeoutKey: /* --daemon-job-timeout */
return add(doc, Pools::kPools, Pool::kDaemonJobTimeout, arg);
case IConfig::DaemonZMQPortKey: /* --daemon-zmq-port */
return add(doc, Pools::kPools, Pool::kDaemonZMQPort, arg);
# endif

View File

@@ -88,6 +88,7 @@ public:
DaemonZMQPortKey = 1056,
HugePagesJitKey = 1057,
RotationKey = 1058,
DaemonJobTimeoutKey = 1059,
// xmrig common
CPUPriorityKey = 1021,

View File

@@ -1,6 +1,6 @@
/* XMRig
* Copyright (c) 2018-2021 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2021 XMRig <https://github.com/xmrig>, <support@xmrig.com>
* Copyright (c) 2018-2023 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2023 XMRig <https://github.com/xmrig>, <support@xmrig.com>
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -46,11 +46,11 @@ xmrig::String xmrig::DnsRecord::ip() const
if (m_type == AAAA) {
buf = new char[45]();
uv_ip6_name(reinterpret_cast<sockaddr_in6*>(m_data), buf, 45);
uv_ip6_name(reinterpret_cast<const sockaddr_in6*>(m_data), buf, 45);
}
else {
buf = new char[16]();
uv_ip4_name(reinterpret_cast<sockaddr_in*>(m_data), buf, 16);
uv_ip4_name(reinterpret_cast<const sockaddr_in*>(m_data), buf, 16);
}
return buf;

View File

@@ -1,6 +1,6 @@
/* XMRig
* Copyright (c) 2018-2021 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2021 XMRig <https://github.com/xmrig>, <support@xmrig.com>
* Copyright (c) 2018-2023 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2023 XMRig <https://github.com/xmrig>, <support@xmrig.com>
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -28,18 +28,19 @@
namespace xmrig {
static Storage<DnsUvBackend>* storage = nullptr;
Storage<DnsUvBackend>& DnsUvBackend::getStorage()
static Storage<DnsUvBackend> *storage = nullptr;
Storage<DnsUvBackend> &DnsUvBackend::getStorage()
{
if (storage == nullptr) storage = new Storage<DnsUvBackend>();
if (storage == nullptr) {
storage = new Storage<DnsUvBackend>();
}
return *storage;
}
void DnsUvBackend::releaseStorage()
{
delete storage;
}
static addrinfo hints{};
@@ -61,8 +62,14 @@ xmrig::DnsUvBackend::DnsUvBackend()
xmrig::DnsUvBackend::~DnsUvBackend()
{
getStorage().release(m_key);
releaseStorage();
assert(storage);
storage->release(m_key);
if (storage->isEmpty()) {
delete storage;
storage = nullptr;
}
}

View File

@@ -21,6 +21,7 @@
#define XMRIG_HTTPRESPONSE_H
#include <cstdint>
#include <map>
#include <string>

View File

@@ -1018,7 +1018,7 @@ void xmrig::Client::onConnect(uv_connect_t *req, int status)
if (status < 0) {
if (!client->isQuiet()) {
LOG_ERR("%s " RED("connect error: ") RED_BOLD("\"%s\""), client->tag(), uv_strerror(status));
LOG_ERR("%s %s " RED("connect error: ") RED_BOLD("\"%s\""), client->tag(), client->ip().data(), uv_strerror(status));
}
if (client->state() == ReconnectingState || client->state() == ClosingState) {

View File

@@ -303,6 +303,18 @@ void xmrig::DaemonClient::onHttpData(const HttpData &data)
void xmrig::DaemonClient::onTimer(const Timer *)
{
if (m_pool.zmq_port() >= 0) {
m_prevHash = nullptr;
m_blocktemplateRequestHash = nullptr;
send(kGetHeight);
return;
}
if (Chrono::steadyMSecs() >= m_jobSteadyMs + m_pool.jobTimeout()) {
m_prevHash = nullptr;
m_blocktemplateRequestHash = nullptr;
}
if (m_state == ConnectingState) {
connect();
}
@@ -352,7 +364,7 @@ void xmrig::DaemonClient::onResolved(const DnsRecords &records, int status, cons
bool xmrig::DaemonClient::isOutdated(uint64_t height, const char *hash) const
{
return m_job.height() != height || m_prevHash != hash;
return m_job.height() != height || m_prevHash != hash || Chrono::steadyMSecs() >= m_jobSteadyMs + m_pool.jobTimeout();
}
@@ -468,6 +480,7 @@ bool xmrig::DaemonClient::parseJob(const rapidjson::Value &params, int *code)
m_job = std::move(job);
m_blocktemplateStr = std::move(blocktemplate);
m_prevHash = Json::getString(params, "prev_hash");
m_jobSteadyMs = Chrono::steadyMSecs();
if (m_state == ConnectingState) {
setState(ConnectedState);
@@ -596,6 +609,10 @@ void xmrig::DaemonClient::setState(SocketState state)
const uint64_t interval = std::max<uint64_t>(20, m_pool.pollInterval());
m_timer->start(interval, interval);
}
else {
const uint64_t t = m_pool.jobTimeout();
m_timer->start(t, t);
}
}
break;
@@ -865,7 +882,12 @@ void xmrig::DaemonClient::ZMQParse()
// Clear previous hash and check daemon height to guarantee that xmrig will call get_block_template RPC later
// We can't call get_block_template directly because daemon is not ready yet
m_prevHash = nullptr;
m_blocktemplateRequestHash = nullptr;
send(kGetHeight);
const uint64_t t = m_pool.jobTimeout();
m_timer->stop();
m_timer->start(t, t);
}

View File

@@ -104,6 +104,7 @@ private:
String m_blocktemplateStr;
String m_currentJobId;
String m_prevHash;
uint64_t m_jobSteadyMs = 0;
String m_tlsFingerprint;
String m_tlsVersion;
Timer *m_timer;

View File

@@ -48,7 +48,13 @@ xmrig::Job::Job(bool nicehash, const Algorithm &algorithm, const String &clientI
bool xmrig::Job::isEqual(const Job &other) const
{
return m_id == other.m_id && m_clientId == other.m_clientId && memcmp(m_blob, other.m_blob, sizeof(m_blob)) == 0 && m_target == other.m_target;
return m_id == other.m_id && m_clientId == other.m_clientId && isEqualBlob(other) && m_target == other.m_target;
}
bool xmrig::Job::isEqualBlob(const Job &other) const
{
return (m_size == other.m_size) && (memcmp(m_blob, other.m_blob, m_size) == 0);
}
@@ -58,19 +64,19 @@ bool xmrig::Job::setBlob(const char *blob)
return false;
}
m_size = strlen(blob);
if (m_size % 2 != 0) {
size_t size = strlen(blob);
if (size % 2 != 0) {
return false;
}
m_size /= 2;
size /= 2;
const size_t minSize = nonceOffset() + nonceSize();
if (m_size < minSize || m_size >= sizeof(m_blob)) {
if (size < minSize || size >= sizeof(m_blob)) {
return false;
}
if (!Cvt::fromHex(m_blob, sizeof(m_blob), blob, m_size * 2)) {
if (!Cvt::fromHex(m_blob, sizeof(m_blob), blob, size * 2)) {
return false;
}
@@ -80,9 +86,10 @@ bool xmrig::Job::setBlob(const char *blob)
# ifdef XMRIG_PROXY_PROJECT
memset(m_rawBlob, 0, sizeof(m_rawBlob));
memcpy(m_rawBlob, blob, m_size * 2);
memcpy(m_rawBlob, blob, size * 2);
# endif
m_size = size;
return true;
}

View File

@@ -59,6 +59,7 @@ public:
~Job() = default;
bool isEqual(const Job &other) const;
bool isEqualBlob(const Job &other) const;
bool setBlob(const char *blob);
bool setSeedHash(const char *hash);
bool setTarget(const char *target);

View File

@@ -65,6 +65,7 @@ const char *Pool::kAlgo = "algo";
const char *Pool::kCoin = "coin";
const char *Pool::kDaemon = "daemon";
const char *Pool::kDaemonPollInterval = "daemon-poll-interval";
const char *Pool::kDaemonJobTimeout = "daemon-job-timeout";
const char *Pool::kDaemonZMQPort = "daemon-zmq-port";
const char *Pool::kEnabled = "enabled";
const char *Pool::kFingerprint = "tls-fingerprint";
@@ -88,6 +89,7 @@ const char *Pool::kNicehashHost = "nicehash.com";
xmrig::Pool::Pool(const char *url) :
m_flags(1 << FLAG_ENABLED),
m_pollInterval(kDefaultPollInterval),
m_jobTimeout(kDefaultJobTimeout),
m_url(url)
{
}
@@ -101,6 +103,7 @@ xmrig::Pool::Pool(const char *host, uint16_t port, const char *user, const char
m_user(user),
m_spendSecretKey(spendSecretKey),
m_pollInterval(kDefaultPollInterval),
m_jobTimeout(kDefaultJobTimeout),
m_url(host, port, tls)
{
m_flags.set(FLAG_NICEHASH, nicehash || strstr(host, kNicehashHost));
@@ -111,6 +114,7 @@ xmrig::Pool::Pool(const char *host, uint16_t port, const char *user, const char
xmrig::Pool::Pool(const rapidjson::Value &object) :
m_flags(1 << FLAG_ENABLED),
m_pollInterval(kDefaultPollInterval),
m_jobTimeout(kDefaultJobTimeout),
m_url(Json::getString(object, kUrl))
{
if (!m_url.isValid()) {
@@ -123,6 +127,7 @@ xmrig::Pool::Pool(const rapidjson::Value &object) :
m_rigId = Json::getString(object, kRigId);
m_fingerprint = Json::getString(object, kFingerprint);
m_pollInterval = Json::getUint64(object, kDaemonPollInterval, kDefaultPollInterval);
m_jobTimeout = Json::getUint64(object, kDaemonJobTimeout, kDefaultJobTimeout);
m_algorithm = Json::getString(object, kAlgo);
m_coin = Json::getString(object, kCoin);
m_daemon = Json::getString(object, kSelfSelect);
@@ -207,6 +212,7 @@ bool xmrig::Pool::isEqual(const Pool &other) const
&& m_url == other.m_url
&& m_user == other.m_user
&& m_pollInterval == other.m_pollInterval
&& m_jobTimeout == other.m_jobTimeout
&& m_daemon == other.m_daemon
&& m_proxy == other.m_proxy
);
@@ -299,6 +305,7 @@ rapidjson::Value xmrig::Pool::toJSON(rapidjson::Document &doc) const
if (m_mode == MODE_DAEMON) {
obj.AddMember(StringRef(kDaemonPollInterval), m_pollInterval, allocator);
obj.AddMember(StringRef(kDaemonJobTimeout), m_jobTimeout, allocator);
obj.AddMember(StringRef(kDaemonZMQPort), m_zmqPort, allocator);
}
else {

View File

@@ -59,6 +59,7 @@ public:
static const char *kCoin;
static const char *kDaemon;
static const char *kDaemonPollInterval;
static const char* kDaemonJobTimeout;
static const char *kEnabled;
static const char *kFingerprint;
static const char *kKeepalive;
@@ -78,6 +79,7 @@ public:
constexpr static int kKeepAliveTimeout = 60;
constexpr static uint16_t kDefaultPort = 3333;
constexpr static uint64_t kDefaultPollInterval = 1000;
constexpr static uint64_t kDefaultJobTimeout = 15000;
Pool() = default;
Pool(const char *host, uint16_t port, const char *user, const char *password, const char* spendSecretKey, int keepAlive, bool nicehash, bool tls, Mode mode);
@@ -110,6 +112,7 @@ public:
inline uint16_t port() const { return m_url.port(); }
inline int zmq_port() const { return m_zmqPort; }
inline uint64_t pollInterval() const { return m_pollInterval; }
inline uint64_t jobTimeout() const { return m_jobTimeout; }
inline void setAlgo(const Algorithm &algorithm) { m_algorithm = algorithm; }
inline void setUrl(const char *url) { m_url = Url(url); }
inline void setPassword(const String &password) { m_password = password; }
@@ -156,6 +159,7 @@ private:
String m_user;
String m_spendSecretKey;
uint64_t m_pollInterval = kDefaultPollInterval;
uint64_t m_jobTimeout = kDefaultJobTimeout;
Url m_daemon;
Url m_url;
int m_zmqPort = -1;

View File

@@ -1,7 +1,7 @@
/* XMRig
* Copyright (c) 2018 Lee Clagett <https://github.com/vtnerd>
* Copyright (c) 2018-2021 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2021 XMRig <https://github.com/xmrig>, <support@xmrig.com>
* Copyright (c) 2018-2023 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2023 XMRig <https://github.com/xmrig>, <support@xmrig.com>
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -45,6 +45,7 @@ namespace xmrig {
// https://wiki.openssl.org/index.php/Diffie-Hellman_parameters
#if OPENSSL_VERSION_NUMBER < 0x30000000L || defined(LIBRESSL_VERSION_NUMBER)
static DH *get_dh2048()
{
static unsigned char dhp_2048[] = {
@@ -96,6 +97,8 @@ static DH *get_dh2048()
return dh;
}
#endif
} // namespace xmrig
@@ -191,6 +194,7 @@ bool xmrig::TlsContext::setCipherSuites(const char *ciphersuites)
bool xmrig::TlsContext::setDH(const char *dhparam)
{
# if OPENSSL_VERSION_NUMBER < 0x30000000L || defined(LIBRESSL_VERSION_NUMBER)
DH *dh = nullptr;
if (dhparam != nullptr) {
@@ -225,6 +229,34 @@ bool xmrig::TlsContext::setDH(const char *dhparam)
return false;
}
# else
if (dhparam != nullptr) {
EVP_PKEY *dh = nullptr;
BIO *bio = BIO_new_file(Env::expand(dhparam), "r");
if (bio) {
dh = PEM_read_bio_Parameters(bio, nullptr);
BIO_free(bio);
}
if (!dh) {
LOG_ERR("PEM_read_bio_Parameters(\"%s\") failed.", dhparam);
return false;
}
if (SSL_CTX_set0_tmp_dh_pkey(m_ctx, dh) != 1) {
EVP_PKEY_free(dh);
LOG_ERR("SSL_CTX_set0_tmp_dh_pkey(\"%s\") failed.", dhparam);
return false;
}
}
else {
SSL_CTX_set_dh_auto(m_ctx, 1);
}
# endif
return true;
}

View File

@@ -1,7 +1,7 @@
/* XMRig
* Copyright (c) 2018 Lee Clagett <https://github.com/vtnerd>
* Copyright (c) 2018-2021 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2021 XMRig <https://github.com/xmrig>, <support@xmrig.com>
* Copyright (c) 2018-2023 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2023 XMRig <https://github.com/xmrig>, <support@xmrig.com>
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -24,9 +24,6 @@
#include "base/tools/Object.h"
#include <cstdint>
using SSL_CTX = struct ssl_ctx_st;
@@ -60,6 +57,7 @@ private:
};
} /* namespace xmrig */
} // namespace xmrig
#endif /* XMRIG_TLSCONTEXT_H */
#endif // XMRIG_TLSCONTEXT_H

View File

@@ -1,6 +1,6 @@
/* XMRig
* Copyright (c) 2018-2021 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2021 XMRig <https://github.com/xmrig>, <support@xmrig.com>
* Copyright (c) 2018-2023 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2023 XMRig <https://github.com/xmrig>, <support@xmrig.com>
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -33,6 +33,7 @@ static const char *kLocalhost = "localhost";
static EVP_PKEY *generate_pkey()
{
# if OPENSSL_VERSION_NUMBER < 0x30000000L || defined(LIBRESSL_VERSION_NUMBER)
auto pkey = EVP_PKEY_new();
if (!pkey) {
return nullptr;
@@ -53,6 +54,9 @@ static EVP_PKEY *generate_pkey()
BN_free(exponent);
return pkey;
# else
return EVP_RSA_gen(2048);
# endif
}

View File

@@ -1,6 +1,6 @@
/* XMRig
* Copyright (c) 2018-2021 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2021 XMRig <https://github.com/xmrig>, <support@xmrig.com>
* Copyright (c) 2018-2023 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2023 XMRig <https://github.com/xmrig>, <support@xmrig.com>
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -55,7 +55,7 @@ private:
};
} /* namespace xmrig */
} // namespace xmrig
#endif /* XMRIG_TLSGEN_H */
#endif // XMRIG_TLSGEN_H

View File

@@ -1,6 +1,6 @@
/* XMRig
* Copyright 2018-2020 SChernykh <https://github.com/SChernykh>
* Copyright 2016-2020 XMRig <https://github.com/xmrig>, <support@xmrig.com>
* Copyright 2018-2023 SChernykh <https://github.com/SChernykh>
* Copyright 2016-2023 XMRig <https://github.com/xmrig>, <support@xmrig.com>
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -42,7 +42,7 @@ public:
}
inline void *ptr(uintptr_t id) { return reinterpret_cast<void *>(id); }
inline TYPE *ptr(uintptr_t id) { return reinterpret_cast<TYPE *>(id); }
inline TYPE *get(const void *id) const { return get(reinterpret_cast<uintptr_t>(id)); }
@@ -56,6 +56,9 @@ public:
return m_data.at(id);
}
inline bool isEmpty() const { return m_data.empty(); }
inline size_t size() const { return m_data.size(); }
inline void remove(const void *id) { delete release(reinterpret_cast<uintptr_t>(id)); }
inline void remove(uintptr_t id) { delete release(id); }

View File

@@ -1,6 +1,6 @@
/* XMRig
* Copyright (c) 2018-2021 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2021 XMRig <https://github.com/xmrig>, <support@xmrig.com>
* Copyright (c) 2018-2023 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2023 XMRig <https://github.com/xmrig>, <support@xmrig.com>
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -20,7 +20,9 @@
#define XMRIG_OBJECT_H
#include <chrono>
#include <cstddef>
#include <cstdint>
#include <memory>
namespace xmrig {
@@ -41,6 +43,7 @@ namespace xmrig {
X &operator=(X &&other) = delete;
} /* namespace xmrig */
} // namespace xmrig
#endif /* XMRIG_OBJECT_H */
#endif // XMRIG_OBJECT_H

View File

@@ -561,6 +561,12 @@ void xmrig::Miner::setJob(const Job &job, bool donate)
const uint8_t index = donate ? 1 : 0;
d_ptr->reset = !(d_ptr->job.index() == 1 && index == 0 && d_ptr->userJobId == job.id());
// Don't reset nonce if pool sends the same hashing blob again, but with different difficulty (for example)
if (d_ptr->job.isEqualBlob(job)) {
d_ptr->reset = false;
}
d_ptr->job = job;
d_ptr->job.setIndex(index);

View File

@@ -50,6 +50,7 @@ static const option options[] = {
{ "http-no-restricted", 0, nullptr, IConfig::HttpRestrictedKey },
{ "daemon", 0, nullptr, IConfig::DaemonKey },
{ "daemon-poll-interval", 1, nullptr, IConfig::DaemonPollKey },
{ "daemon-job-timeout", 1, nullptr, IConfig::DaemonJobTimeoutKey },
{ "self-select", 1, nullptr, IConfig::SelfSelectKey },
{ "submit-to-origin", 0, nullptr, IConfig::SubmitToOriginKey },
{ "daemon-zmq-port", 1, nullptr, IConfig::DaemonZMQPortKey },

View File

@@ -64,7 +64,9 @@ static inline const std::string &usage()
# ifdef XMRIG_FEATURE_HTTP
u += " --daemon use daemon RPC instead of pool for solo mining\n";
u += " --daemon-zmq-port daemon's zmq-pub port number (only use it if daemon has it enabled)\n";
u += " --daemon-poll-interval=N daemon poll interval in milliseconds (default: 1000)\n";
u += " --daemon-job-timeout=N daemon job timeout in milliseconds (default: 15000)\n";
u += " --self-select=URL self-select block templates from URL\n";
u += " --submit-to-origin also submit solution back to self-select URL\n";
# endif

View File

@@ -407,8 +407,12 @@ xmrig::cn_hash_fun xmrig::CnHash::fn(const Algorithm &algorithm, AlgoVariant av,
}
# ifdef XMRIG_ALGO_CN_HEAVY
// cn-heavy optimization for Zen3 CPUs
if ((av == AV_SINGLE) && (assembly != Assembly::NONE) && (Cpu::info()->arch() == ICpuInfo::ARCH_ZEN3) && (Cpu::info()->model() == 0x21)) {
// cn-heavy optimization for Zen3/Zen4 CPUs
const auto arch = Cpu::info()->arch();
const uint32_t model = Cpu::info()->model();
const bool is_vermeer = (arch == ICpuInfo::ARCH_ZEN3) && (model == 0x21);
const bool is_raphael = (arch == ICpuInfo::ARCH_ZEN4) && (model == 0x61);
if ((av == AV_SINGLE) && (assembly != Assembly::NONE) && (is_vermeer || is_raphael)) {
switch (algorithm.id()) {
case Algorithm::CN_HEAVY_0:
return cryptonight_single_hash<Algorithm::CN_HEAVY_0, false, 3>;

View File

@@ -80,7 +80,7 @@ static inline void do_skein_hash(const uint8_t *input, size_t len, uint8_t *outp
void (* const extra_hashes[4])(const uint8_t *, size_t, uint8_t *) = {do_blake_hash, do_groestl_hash, do_jh_hash, do_skein_hash};
#if defined(__i386__) || defined(_M_IX86)
#if (defined(__i386__) || defined(_M_IX86)) && !(defined(__clang__) && defined(__clang_major__) && (__clang_major__ >= 15))
static inline int64_t _mm_cvtsi128_si64(__m128i a)
{
return ((uint64_t)(uint32_t)_mm_cvtsi128_si32(a) | ((uint64_t)(uint32_t)_mm_cvtsi128_si32(_mm_srli_si128(a, 4)) << 32));

File diff suppressed because it is too large Load Diff

View File

@@ -57,6 +57,15 @@
# define MAP_HUGE_MASK 0x3f
#endif
#ifdef XMRIG_OS_FREEBSD
# ifndef MAP_ALIGNED_SUPER
# define MAP_ALIGNED_SUPER 0
# endif
# ifndef MAP_PREFAULT_READ
# define MAP_PREFAULT_READ 0
# endif
#endif
#ifdef XMRIG_SECURE_JIT
# define SECURE_PROT_EXEC 0
@@ -65,7 +74,7 @@
#endif
#if defined(XMRIG_OS_LINUX) || (!defined(XMRIG_OS_APPLE) && !defined(__FreeBSD__))
#if defined(XMRIG_OS_LINUX) || (!defined(XMRIG_OS_APPLE) && !defined(XMRIG_OS_FREEBSD))
static inline int hugePagesFlag(size_t size)
{
return (static_cast<int>(log2(size)) & MAP_HUGE_MASK) << MAP_HUGE_SHIFT;
@@ -112,13 +121,19 @@ bool xmrig::VirtualMemory::protectRWX(void *p, size_t size)
bool xmrig::VirtualMemory::protectRX(void *p, size_t size)
{
bool result = true;
# if defined(XMRIG_OS_APPLE) && defined(XMRIG_ARM)
pthread_jit_write_protect_np(true);
flushInstructionCache(p, size);
return true;
# else
return mprotect(p, size, PROT_READ | PROT_EXEC) == 0;
result = (mprotect(p, size, PROT_READ | PROT_EXEC) == 0);
# endif
# if defined(XMRIG_ARM)
flushInstructionCache(p, size);
# endif
return result;
}
@@ -129,7 +144,7 @@ void *xmrig::VirtualMemory::allocateExecutableMemory(size_t size, bool hugePages
# ifdef XMRIG_ARM
pthread_jit_write_protect_np(false);
# endif
# elif defined(__FreeBSD__)
# elif defined(XMRIG_OS_FREEBSD)
void *mem = nullptr;
if (hugePages) {
@@ -162,7 +177,7 @@ void *xmrig::VirtualMemory::allocateLargePagesMemory(size_t size)
{
# if defined(XMRIG_OS_APPLE)
void *mem = mmap(0, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANON, VM_FLAGS_SUPERPAGE_SIZE_2MB, 0);
# elif defined(__FreeBSD__)
# elif defined(XMRIG_OS_FREEBSD)
void *mem = mmap(0, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_ALIGNED_SUPER | MAP_PREFAULT_READ, -1, 0);
# else
void *mem = mmap(0, size, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB | MAP_POPULATE | hugePagesFlag(hugePageSize()), 0, 0);

View File

@@ -1,4 +1,4 @@
cmake_minimum_required(VERSION 2.8.12)
cmake_minimum_required(VERSION 3.1)
project(GhostRider)
set(HEADERS

View File

@@ -1,6 +1,6 @@
/* XMRig
* Copyright 2018-2021 SChernykh <https://github.com/SChernykh>
* Copyright 2016-2021 XMRig <https://github.com/xmrig>, <support@xmrig.com>
* Copyright 2018-2023 SChernykh <https://github.com/SChernykh>
* Copyright 2016-2023 XMRig <https://github.com/xmrig>, <support@xmrig.com>
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -16,7 +16,6 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include "ghostrider.h"
#include "sph_blake.h"
#include "sph_bmw.h"

View File

@@ -262,6 +262,10 @@ namespace randomx {
// AVX2 init is faster on Zen3
initDatasetAVX2 = true;
break;
case xmrig::ICpuInfo::ARCH_ZEN4:
// AVX2 init is slower on Zen4
initDatasetAVX2 = false;
break;
}
}
}
@@ -424,7 +428,8 @@ namespace randomx {
memcpy(imul_rcp_storage - 34, &pcfg.eMask, sizeof(pcfg.eMask));
codePos = codePosFirst;
prevCFROUND = 0;
prevCFROUND = -1;
prevFPOperation = -1;
//mark all registers as used
uint64_t* r = (uint64_t*)registerUsage;
@@ -1160,7 +1165,7 @@ namespace randomx {
uint8_t* const p = code;
uint32_t pos = codePos;
prevCFROUND = 0;
prevFPOperation = pos;
const uint64_t dst = instr.dst % RegisterCountFlt;
const uint64_t src = instr.src % RegisterCountFlt;
@@ -1175,7 +1180,7 @@ namespace randomx {
uint8_t* const p = code;
uint32_t pos = codePos;
prevCFROUND = 0;
prevFPOperation = pos;
const uint32_t src = instr.src % RegistersCount;
const uint32_t dst = instr.dst % RegisterCountFlt;
@@ -1192,7 +1197,7 @@ namespace randomx {
uint8_t* const p = code;
uint32_t pos = codePos;
prevCFROUND = 0;
prevFPOperation = pos;
const uint64_t dst = instr.dst % RegisterCountFlt;
const uint64_t src = instr.src % RegisterCountFlt;
@@ -1207,7 +1212,7 @@ namespace randomx {
uint8_t* const p = code;
uint32_t pos = codePos;
prevCFROUND = 0;
prevFPOperation = pos;
const uint32_t src = instr.src % RegistersCount;
const uint32_t dst = instr.dst % RegisterCountFlt;
@@ -1235,7 +1240,7 @@ namespace randomx {
uint8_t* const p = code;
uint32_t pos = codePos;
prevCFROUND = 0;
prevFPOperation = pos;
const uint64_t dst = instr.dst % RegisterCountFlt;
const uint64_t src = instr.src % RegisterCountFlt;
@@ -1250,7 +1255,7 @@ namespace randomx {
uint8_t* const p = code;
uint32_t pos = codePos;
prevCFROUND = 0;
prevFPOperation = pos;
const uint32_t src = instr.src % RegistersCount;
const uint64_t dst = instr.dst % RegisterCountFlt;
@@ -1277,7 +1282,7 @@ namespace randomx {
uint8_t* const p = code;
uint32_t pos = codePos;
prevCFROUND = 0;
prevFPOperation = pos;
const uint32_t dst = instr.dst % RegisterCountFlt;
@@ -1288,18 +1293,18 @@ namespace randomx {
void JitCompilerX86::h_CFROUND(const Instruction& instr) {
uint8_t* const p = code;
uint32_t pos = prevCFROUND;
int32_t t = prevCFROUND;
if (pos) {
if (t > prevFPOperation) {
if (vm_flags & RANDOMX_FLAG_AMD) {
memcpy(p + pos, NOP26, 26);
memcpy(p + t, NOP26, 26);
}
else {
memcpy(p + pos, NOP14, 14);
memcpy(p + t, NOP14, 14);
}
}
pos = codePos;
uint32_t pos = codePos;
prevCFROUND = pos;
const uint32_t src = instr.src % RegistersCount;
@@ -1324,18 +1329,18 @@ namespace randomx {
void JitCompilerX86::h_CFROUND_BMI2(const Instruction& instr) {
uint8_t* const p = code;
uint32_t pos = prevCFROUND;
int32_t t = prevCFROUND;
if (pos) {
if (t > prevFPOperation) {
if (vm_flags & RANDOMX_FLAG_AMD) {
memcpy(p + pos, NOP25, 25);
memcpy(p + t, NOP25, 25);
}
else {
memcpy(p + pos, NOP13, 13);
memcpy(p + t, NOP13, 13);
}
}
pos = codePos;
uint32_t pos = codePos;
prevCFROUND = pos;
const uint64_t src = instr.src % RegistersCount;
@@ -1365,10 +1370,9 @@ namespace randomx {
const int reg = instr.dst % RegistersCount;
int32_t jmp_offset = registerUsage[reg];
// if it jumps over the previous CFROUND, it can't be safely eliminated
const uint32_t t = prevCFROUND;
if (t && (jmp_offset < t)) {
prevCFROUND = 0;
// if it jumps over the previous FP instruction that uses rounding, treat it as if FP instruction happened now
if (jmp_offset <= prevFPOperation) {
prevFPOperation = pos;
}
jmp_offset -= pos + 16;

View File

@@ -89,7 +89,8 @@ namespace randomx {
uint32_t codePos = 0;
uint32_t codePosFirst = 0;
uint32_t vm_flags = 0;
uint32_t prevCFROUND = 0;
int32_t prevCFROUND = -1;
int32_t prevFPOperation = -1;
# ifdef XMRIG_FIX_RYZEN
std::pair<const void*, const void*> mainLoopBounds;

View File

@@ -58,12 +58,13 @@ static const std::array<const char *, RxConfig::ModeMax> modeNames = { "auto", "
#ifdef XMRIG_FEATURE_MSR
constexpr size_t kMsrArraySize = 5;
constexpr size_t kMsrArraySize = 6;
static const std::array<MsrItems, kMsrArraySize> msrPresets = {
MsrItems(),
MsrItems{{ 0xC0011020, 0ULL }, { 0xC0011021, 0x40ULL, ~0x20ULL }, { 0xC0011022, 0x1510000ULL }, { 0xC001102b, 0x2000cc16ULL }},
MsrItems{{ 0xC0011020, 0x0004480000000000ULL }, { 0xC0011021, 0x001c000200000040ULL, ~0x20ULL }, { 0xC0011022, 0xc000000401500000ULL }, { 0xC001102b, 0x2000cc14ULL }},
MsrItems{{ 0xC0011020, 0x0004480000000000ULL }, { 0xC0011021, 0x001c000200000040ULL, ~0x20ULL }, { 0xC0011022, 0xc000000401570000ULL }, { 0xC001102b, 0x2000cc10ULL }},
MsrItems{{ 0xC0011020, 0x0004400000000000ULL }, { 0xC0011021, 0x0004000000000040ULL, ~0x20ULL }, { 0xC0011022, 0x8680000401570000ULL }, { 0xC001102b, 0x2040cc10ULL }},
MsrItems{{ 0x1a4, 0xf }},
MsrItems()
};
@@ -255,10 +256,12 @@ void xmrig::RxConfig::readMSR(const rapidjson::Value &value)
return;
}
if (value.IsInt() && Cpu::info()->vendor() == ICpuInfo::VENDOR_INTEL) {
if (value.IsInt()) {
const int i = std::min(value.GetInt(), 15);
if (i >= 0) {
m_msrPreset.emplace_back(0x1a4, i);
if (Cpu::info()->vendor() == ICpuInfo::VENDOR_INTEL) {
m_msrPreset.emplace_back(0x1a4, i);
}
}
else {
m_wrmsr = false;

View File

@@ -1,6 +1,6 @@
/* XMRig
* Copyright (c) 2018-2021 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2021 XMRig <https://github.com/xmrig>, <support@xmrig.com>
* Copyright (c) 2018-2022 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2022 XMRig <https://github.com/xmrig>, <support@xmrig.com>
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -23,22 +23,22 @@
/*
* Dev donation.
*
* Percentage of your hashing power that you want to donate to the developer, can be 0 if you don't want to do that.
* Percentage of your hashing power that you want to donate to the developer can be 0% but supports XMRig Development.
*
* Example of how it works for the setting of 1%:
* You miner will mine into your usual pool for random time (in range from 49.5 to 148.5 minutes),
* Your miner will mine into your usual pool for a random time (in a range from 49.5 to 148.5 minutes),
* then switch to the developer's pool for 1 minute, then switch again to your pool for 99 minutes
* and then switch again to developer's pool for 1 minute, these rounds will continue until miner working.
* and then switch again to developer's pool for 1 minute; these rounds will continue until the miner stops.
*
* Randomised only first round, to prevent waves on the donation pool.
* Randomised only on the first round to prevent waves on the donation pool.
*
* Switching is instant, and only happens after a successful connection, so you never loose any hashes.
* Switching is instant and only happens after a successful connection, so you never lose any hashes.
*
* If you plan on changing this setting to 0 please consider making a one off donation to my wallet:
* If you plan on changing donations to 0%, please consider making a one-off donation to my wallet:
* XMR: 48edfHu7V9Z84YzzMa6fUueoELZ9ZRXq9VetWzYGzKt52XU5xvqgzYnDK9URnRoJMk1j8nLwEVsaSWJ4fhdUyZijBGUicoD
*/
constexpr const int kDefaultDonateLevel = 1;
constexpr const int kMinimumDonateLevel = 1;
#endif /* XMRIG_DONATE_H */
#endif // XMRIG_DONATE_H

View File

@@ -1,7 +1,7 @@
/* XMRig
* Copyright (c) 2002-2006 Hugo Weber <address@hidden>
* Copyright (c) 2018-2021 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2021 XMRig <https://github.com/xmrig>, <support@xmrig.com>
* Copyright (c) 2018-2023 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2023 XMRig <https://github.com/xmrig>, <support@xmrig.com>
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -17,7 +17,6 @@
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
#include "hw/dmi/DmiReader.h"
#include "hw/dmi/DmiTools.h"
@@ -91,12 +90,12 @@ bool xmrig::DmiReader::read()
}
CFDataRef data = reinterpret_cast<CFDataRef>(IORegistryEntryCreateCFProperty(service, CFSTR("SMBIOS-EPS"), kCFAllocatorDefault, kNilOptions));
if (!data) {
if (!data || CFDataGetLength(data) < 0x1f) {
return false;
}
uint8_t buf[0x20]{};
CFDataGetBytes(data, CFRangeMake(0, sizeof(buf)), buf);
CFDataGetBytes(data, CFRangeMake(0, sizeof(buf) - 1), buf);
CFRelease(data);
auto smb = smbios_decode(buf, m_size, m_version, service);

View File

@@ -31,7 +31,7 @@
#include <unistd.h>
#include <cstdio>
#ifdef __FreeBSD__
#ifdef XMRIG_OS_FREEBSD
# include <kenv.h>
#endif
@@ -288,7 +288,7 @@ static off_t address_from_efi()
const char *filename;
char linebuf[64];
off_t address = 0;
# elif defined(__FreeBSD__)
# elif defined(XMRIG_OS_FREEBSD)
char addrstr[KENV_MVALLEN + 1];
# endif
@@ -310,7 +310,7 @@ static off_t address_from_efi()
fclose(efi_systab);
return address;
# elif defined(__FreeBSD__)
# elif defined(XMRIG_OS_FREEBSD)
if (kenv(KENV_GET, "hint.smbios.0.mem", addrstr, sizeof(addrstr)) == -1) {
return EFI_NOT_FOUND;
}

View File

@@ -1,6 +1,6 @@
/* XMRig
* Copyright (c) 2018-2022 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2022 XMRig <https://github.com/xmrig>, <support@xmrig.com>
* Copyright (c) 2018-2023 SChernykh <https://github.com/SChernykh>
* Copyright (c) 2016-2023 XMRig <https://github.com/xmrig>, <support@xmrig.com>
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
@@ -22,14 +22,14 @@
#define APP_ID "xmrig"
#define APP_NAME "XMRig"
#define APP_DESC "XMRig miner"
#define APP_VERSION "6.18.1-dev"
#define APP_VERSION "6.19.1"
#define APP_DOMAIN "xmrig.com"
#define APP_SITE "www.xmrig.com"
#define APP_COPYRIGHT "Copyright (C) 2016-2022 xmrig.com"
#define APP_COPYRIGHT "Copyright (C) 2016-2023 xmrig.com"
#define APP_KIND "miner"
#define APP_VER_MAJOR 6
#define APP_VER_MINOR 18
#define APP_VER_MINOR 19
#define APP_VER_PATCH 1
#ifdef _MSC_VER
@@ -52,4 +52,4 @@
# endif
#endif
#endif /* XMRIG_VERSION_H */
#endif // XMRIG_VERSION_H