v6.18.1

Added Zen4 to randomx_boost.sh

CHANGELOG.md

@@ -1,12 +1,68 @@
+# v6.18.1
+- [#3129](https://github.com/xmrig/xmrig/pull/3129) Fix: protectRX flushed CPU cache only on MacOS/iOS.
+- [#3126](https://github.com/xmrig/xmrig/pull/3126) Don't reset when pool sends the same job blob.
+- [#3120](https://github.com/xmrig/xmrig/pull/3120) RandomX: optimized `CFROUND` elimination.
+- [#3109](https://github.com/xmrig/xmrig/pull/3109) RandomX: added Blake2 AVX2 version.
+- [#3082](https://github.com/xmrig/xmrig/pull/3082) Fixed GCC 12 warnings.
+- [#3075](https://github.com/xmrig/xmrig/pull/3075) Recognize `armv7ve` as valid ARMv7 target.
+- [#3132](https://github.com/xmrig/xmrig/pull/3132) RandomX: added MSR mod for Zen 4.
+- [#3134](https://github.com/xmrig/xmrig/pull/3134) Added Zen4 to `randomx_boost.sh`.
+
+# v6.18.0
+- [#3067](https://github.com/xmrig/xmrig/pull/3067) Monero v15 network upgrade support and more house keeping.
+  - Removed deprecated AstroBWTv1 and v2.
+  - Fixed debug GhostRider build.
+  - Monero v15 network upgrade support.
+  - Fixed ZMQ debug log.
+  - Improved daemon ZMQ mining stability.
+- [#3054](https://github.com/xmrig/xmrig/pull/3054) Fixes for 32-bit ARM.
+- [#3042](https://github.com/xmrig/xmrig/pull/3042) Fixed being unable to resume from `pause-on-battery`.
+- [#3031](https://github.com/xmrig/xmrig/pull/3031) Fixed `--cpu-priority` not working sometimes.
+- [#3020](https://github.com/xmrig/xmrig/pull/3020) Removed old AstroBWT algorithm.
+
+# v6.17.0
+- [#2954](https://github.com/xmrig/xmrig/pull/2954) **Dero HE fork support (`astrobwt/v2` algorithm).**
+  - [#2961](https://github.com/xmrig/xmrig/pull/2961) Dero HE (`astrobwt/v2`) CUDA config generator.
+  - [#2969](https://github.com/xmrig/xmrig/pull/2969) Dero HE (`astrobwt/v2`) OpenCL support.
+- Fixed displayed DMI memory information for empty slots.
+- [#2932](https://github.com/xmrig/xmrig/pull/2932) Fixed GhostRider with hwloc disabled.
+
+# v6.16.4
+- [#2904](https://github.com/xmrig/xmrig/pull/2904) Fixed unaligned memory accesses.
+- [#2908](https://github.com/xmrig/xmrig/pull/2908) Added MSVC/2022 to `version.h`.
+- [#2910](https://github.com/xmrig/xmrig/issues/2910) Fixed donation for GhostRider/RTM.
+
+# v6.16.3
+- [#2778](https://github.com/xmrig/xmrig/pull/2778) Fixed `READY threads X/X` display after algorithm switching.
+- [#2782](https://github.com/xmrig/xmrig/pull/2782) Updated GhostRider documentation.
+- [#2815](https://github.com/xmrig/xmrig/pull/2815) Fixed `cn-heavy` in 32-bit builds.
+- [#2827](https://github.com/xmrig/xmrig/pull/2827) GhostRider: set correct priority for helper threads.
+- [#2837](https://github.com/xmrig/xmrig/pull/2837) RandomX: don't restart mining threads when the seed changes.
+- [#2848](https://github.com/xmrig/xmrig/pull/2848) GhostRider: added support for `client.reconnect` method.
+- [#2856](https://github.com/xmrig/xmrig/pull/2856) Fix for short responses from some Raptoreum pools.
+- [#2873](https://github.com/xmrig/xmrig/pull/2873) Fixed GhostRider benchmark on single-core systems.
+- [#2882](https://github.com/xmrig/xmrig/pull/2882) Fixed ARMv7 compilation.
+- [#2893](https://github.com/xmrig/xmrig/pull/2893) KawPow OpenCL: use separate UV loop for building programs.
+
+# v6.16.2
+- [#2751](https://github.com/xmrig/xmrig/pull/2751) Fixed crash on CPUs supporting VAES and running GCC-compiled xmrig.
+- [#2761](https://github.com/xmrig/xmrig/pull/2761) Fixed broken auto-tuning in GCC Windows build.
+- [#2771](https://github.com/xmrig/xmrig/issues/2771) Fixed environment variables support for GhostRider and KawPow. 
+- [#2769](https://github.com/xmrig/xmrig/pull/2769) Performance fixes:
+  - Fixed several performance bottlenecks introduced in v6.16.1.
+  - Fixed overall GCC-compiled build performance, it's the same speed as MSVC build now.
+  - **Linux builds are up to 10% faster now compared to v6.16.0 GCC build.**
+  - **Windows builds are up to 5% faster now compared to v6.16.0 MSVC build.**
+
 # v6.16.1
 - [#2729](https://github.com/xmrig/xmrig/pull/2729) GhostRider fixes:
-  - Added average hashrate display
-  - Fixed the number of threads shown at startup
-  - Fixed `--threads` or `-t` command line option (but `--cpu-max-threads-hint` is recommended to use)
+  - Added average hashrate display.
+  - Fixed the number of threads shown at startup.
+  - Fixed `--threads` or `-t` command line option (but `--cpu-max-threads-hint` is recommended to use).
 - [#2738](https://github.com/xmrig/xmrig/pull/2738) GhostRider fixes:
-  - Fixed "difficulty is not a number" error when diff is high on some pools
-  - Fixed GhostRider compilation when WITH_KAWPOW=OFF
-- [#2740](https://github.com/xmrig/xmrig/pull/2740) Added VAES support for Cryptonight variants **+4% speedup on Zen3**
+  - Fixed "difficulty is not a number" error when diff is high on some pools.
+  - Fixed GhostRider compilation when `WITH_KAWPOW=OFF`.
+- [#2740](https://github.com/xmrig/xmrig/pull/2740) Added VAES support for Cryptonight variants **+4% speedup on Zen3**.
   - VAES instructions are available on Intel Ice Lake/AMD Zen3 and newer CPUs.
   - +4% speedup on Ryzen 5 5600X.
 

CMakeLists.txt

@@ -8,7 +8,6 @@ option(WITH_CN_PICO         "Enable CryptoNight-Pico algorithm" ON)
 option(WITH_CN_FEMTO        "Enable CryptoNight-UPX2 algorithm" ON)
 option(WITH_RANDOMX         "Enable RandomX algorithms family" ON)
 option(WITH_ARGON2          "Enable Argon2 algorithms family" ON)
-option(WITH_ASTROBWT        "Enable AstroBWT algorithms family" ON)
 option(WITH_KAWPOW          "Enable KawPow algorithms family" ON)
 option(WITH_GHOSTRIDER      "Enable GhostRider algorithm" ON)
 option(WITH_HTTP            "Enable HTTP protocol support (client/server)" ON)
@@ -28,6 +27,7 @@ option(WITH_STRICT_CACHE    "Enable strict checks for OpenCL cache" ON)
 option(WITH_INTERLEAVE_DEBUG_LOG "Enable debug log for threads interleave" OFF)
 option(WITH_PROFILING       "Enable profiling for developers" OFF)
 option(WITH_SSE4_1          "Enable SSE 4.1 for Blake2" ON)
+option(WITH_AVX2            "Enable AVX2 for Blake2" ON)
 option(WITH_VAES            "Enable VAES instructions for Cryptonight" ON)
 option(WITH_BENCHMARK       "Enable builtin RandomX benchmark and stress test" ON)
 option(WITH_SECURE_JIT      "Enable secure access to JIT memory" OFF)
@@ -199,7 +199,6 @@ find_package(UV REQUIRED)
 include(cmake/flags.cmake)
 include(cmake/randomx.cmake)
 include(cmake/argon2.cmake)
-include(cmake/astrobwt.cmake)
 include(cmake/kawpow.cmake)
 include(cmake/ghostrider.cmake)
 include(cmake/OpenSSL.cmake)

README.md

@@ -7,10 +7,10 @@
 [![GitHub stars](https://img.shields.io/github/stars/xmrig/xmrig.svg)](https://github.com/xmrig/xmrig/stargazers)
 [![GitHub forks](https://img.shields.io/github/forks/xmrig/xmrig.svg)](https://github.com/xmrig/xmrig/network)
 
-XMRig is a high performance, open source, cross platform RandomX, KawPow, CryptoNight and AstroBWT unified CPU/GPU miner and [RandomX benchmark](https://xmrig.com/benchmark). Official binaries are available for Windows, Linux, macOS and FreeBSD.
+XMRig is a high performance, open source, cross platform RandomX, KawPow, CryptoNight and [GhostRider](https://github.com/xmrig/xmrig/tree/master/src/crypto/ghostrider#readme) unified CPU/GPU miner and [RandomX benchmark](https://xmrig.com/benchmark). Official binaries are available for Windows, Linux, macOS and FreeBSD.
 
 ## Mining backends
-- **CPU** (x64/ARMv8)
+- **CPU** (x64/ARMv7/ARMv8)
 - **OpenCL** for AMD GPUs.
 - **CUDA** for NVIDIA GPUs via external [CUDA plugin](https://github.com/xmrig/xmrig-cuda).
 

cmake/astrobwt.cmake

@@ -1,51 +0,0 @@
-if (WITH_ASTROBWT)
-    add_definitions(/DXMRIG_ALGO_ASTROBWT)
-
-    list(APPEND HEADERS_CRYPTO
-        src/crypto/astrobwt/AstroBWT.h
-    )
-
-    list(APPEND SOURCES_CRYPTO
-        src/crypto/astrobwt/AstroBWT.cpp
-    )
-
-    if (XMRIG_ARM)
-        list(APPEND HEADERS_CRYPTO
-            src/crypto/astrobwt/salsa20_ref/ecrypt-config.h
-            src/crypto/astrobwt/salsa20_ref/ecrypt-machine.h
-            src/crypto/astrobwt/salsa20_ref/ecrypt-portable.h
-            src/crypto/astrobwt/salsa20_ref/ecrypt-sync.h
-        )
-
-        list(APPEND SOURCES_CRYPTO
-            src/crypto/astrobwt/salsa20_ref/salsa20.c
-        )
-    else()
-        if (CMAKE_SIZEOF_VOID_P EQUAL 8)
-            add_definitions(/DASTROBWT_AVX2)
-            list(APPEND SOURCES_CRYPTO src/crypto/astrobwt/xmm6int/salsa20_xmm6int-avx2.c)
-
-            if (CMAKE_C_COMPILER_ID MATCHES GNU OR CMAKE_C_COMPILER_ID MATCHES Clang)
-                set_source_files_properties(src/crypto/astrobwt/xmm6int/salsa20_xmm6int-avx2.c PROPERTIES COMPILE_FLAGS -mavx2)
-            endif()
-
-            if (CMAKE_C_COMPILER_ID MATCHES MSVC)
-                enable_language(ASM_MASM)
-                list(APPEND SOURCES_CRYPTO src/crypto/astrobwt/sha3_256_avx2.asm)
-            else()
-                enable_language(ASM)
-                list(APPEND SOURCES_CRYPTO src/crypto/astrobwt/sha3_256_avx2.S)
-            endif()
-        endif()
-
-        list(APPEND HEADERS_CRYPTO
-            src/crypto/astrobwt/Salsa20.hpp
-        )
-
-        list(APPEND SOURCES_CRYPTO
-            src/crypto/astrobwt/Salsa20.cpp
-        )
-    endif()
-else()
-    remove_definitions(/DXMRIG_ALGO_ASTROBWT)
-endif()

cmake/cpu.cmake

@@ -25,13 +25,14 @@ if (XMRIG_64_BIT AND CMAKE_SYSTEM_PROCESSOR MATCHES "^(x86_64|AMD64)$")
     add_definitions(-DRAPIDJSON_SSE2)
 else()
     set(WITH_SSE4_1 OFF)
+    set(WITH_AVX2 OFF)
     set(WITH_VAES OFF)
 endif()
 
 if (NOT ARM_TARGET)
     if (CMAKE_SYSTEM_PROCESSOR MATCHES "^(aarch64|arm64|armv8-a)$")
         set(ARM_TARGET 8)
-    elseif (CMAKE_SYSTEM_PROCESSOR MATCHES "^(armv7|armv7f|armv7s|armv7k|armv7-a|armv7l)$")
+    elseif (CMAKE_SYSTEM_PROCESSOR MATCHES "^(armv7|armv7f|armv7s|armv7k|armv7-a|armv7l|armv7ve)$")
         set(ARM_TARGET 7)
     endif()
 endif()
@@ -57,3 +58,7 @@ endif()
 if (WITH_SSE4_1)
     add_definitions(-DXMRIG_FEATURE_SSE4_1)
 endif()
+
+if (WITH_AVX2)
+    add_definitions(-DXMRIG_FEATURE_AVX2)
+endif()

cmake/flags.cmake

@@ -26,8 +26,8 @@ if (CMAKE_CXX_COMPILER_ID MATCHES GNU)
         set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} ${ARM8_CXX_FLAGS}")
         set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} ${ARM8_CXX_FLAGS} -flax-vector-conversions")
     elseif (ARM_TARGET EQUAL 7)
-        set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -mfpu=neon")
-        set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -mfpu=neon -flax-vector-conversions")
+        set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -march=armv7-a -mfpu=neon")
+        set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -march=armv7-a -mfpu=neon -flax-vector-conversions")
     else()
         set(CMAKE_C_FLAGS "${CMAKE_C_FLAGS} -maes")
         set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -maes")

cmake/randomx.cmake

@@ -76,7 +76,15 @@ if (WITH_RANDOMX)
         list(APPEND SOURCES_CRYPTO src/crypto/randomx/blake2/blake2b_sse41.c)
 
         if (CMAKE_C_COMPILER_ID MATCHES GNU OR CMAKE_C_COMPILER_ID MATCHES Clang)
-            set_source_files_properties(src/crypto/randomx/blake2/blake2b_sse41.c PROPERTIES COMPILE_FLAGS -msse4.1)
+            set_source_files_properties(src/crypto/randomx/blake2/blake2b_sse41.c PROPERTIES COMPILE_FLAGS "-Ofast -msse4.1")
+        endif()
+    endif()
+
+    if (WITH_AVX2)
+        list(APPEND SOURCES_CRYPTO src/crypto/randomx/blake2/avx2/blake2b_avx2.c)
+
+        if (CMAKE_C_COMPILER_ID MATCHES GNU OR CMAKE_C_COMPILER_ID MATCHES Clang)
+            set_source_files_properties(src/crypto/randomx/blake2/avx2/blake2b_avx2.c PROPERTIES COMPILE_FLAGS "-Ofast -mavx2")
         endif()
     endif()
 

scripts/build.hwloc.sh

@@ -1,6 +1,10 @@
 #!/bin/bash -e
 
-HWLOC_VERSION="2.5.0"
+HWLOC_VERSION_MAJOR="2"
+HWLOC_VERSION_MINOR="7"
+HWLOC_VERSION_PATCH="1"
+
+HWLOC_VERSION="${HWLOC_VERSION_MAJOR}.${HWLOC_VERSION_MINOR}.${HWLOC_VERSION_PATCH}"
 
 mkdir -p deps
 mkdir -p deps/include
@@ -8,7 +12,7 @@ mkdir -p deps/lib
 
 mkdir -p build && cd build
 
-wget https://download.open-mpi.org/release/hwloc/v2.5/hwloc-${HWLOC_VERSION}.tar.gz -O hwloc-${HWLOC_VERSION}.tar.gz
+wget https://download.open-mpi.org/release/hwloc/v${HWLOC_VERSION_MAJOR}.${HWLOC_VERSION_MINOR}/hwloc-${HWLOC_VERSION}.tar.gz -O hwloc-${HWLOC_VERSION}.tar.gz
 tar -xzf hwloc-${HWLOC_VERSION}.tar.gz
 
 cd hwloc-${HWLOC_VERSION}

scripts/build.libressl.sh

@@ -1,6 +1,6 @@
 #!/bin/bash -e
 
-LIBRESSL_VERSION="3.0.2"
+LIBRESSL_VERSION="3.5.2"
 
 mkdir -p deps
 mkdir -p deps/include

scripts/build.openssl.sh

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

scripts/build.openssl3.sh

@@ -0,0 +1,20 @@
+#!/bin/bash -e
+
+OPENSSL_VERSION="3.0.3"
+
+mkdir -p deps
+mkdir -p deps/include
+mkdir -p deps/lib
+
+mkdir -p build && cd build
+
+wget https://www.openssl.org/source/openssl-${OPENSSL_VERSION}.tar.gz -O openssl-${OPENSSL_VERSION}.tar.gz
+tar -xzf openssl-${OPENSSL_VERSION}.tar.gz
+
+cd openssl-${OPENSSL_VERSION}
+./config -no-shared -no-asm -no-zlib -no-comp -no-dgram -no-filenames -no-cms
+make -j$(nproc || sysctl -n hw.ncpu || sysctl -n hw.logicalcpu)
+cp -fr include ../../deps
+cp libcrypto.a ../../deps/lib
+cp libssl.a ../../deps/lib
+cd ..

scripts/build.uv.sh

@@ -1,6 +1,6 @@
 #!/bin/bash -e
 
-UV_VERSION="1.42.0"
+UV_VERSION="1.44.1"
 
 mkdir -p deps
 mkdir -p deps/include

scripts/generate_cl.js

@@ -67,15 +67,6 @@ function rx()
 }
 
 
-function astrobwt()
-{
-    const astrobwt = opencl_minify(addIncludes('astrobwt.cl', [ 'BWT.cl', 'salsa20.cl', 'sha3.cl' ]));
-
-    // fs.writeFileSync('astrobwt_gen.cl', astrobwt);
-    fs.writeFileSync('astrobwt_cl.h', text2h(astrobwt, 'xmrig', 'astrobwt_cl'));
-}
-
-
 function kawpow()
 {
     const kawpow = opencl_minify(addIncludes('kawpow.cl', [ 'defs.h' ]));
@@ -97,11 +88,6 @@ process.chdir(path.resolve('src/backend/opencl/cl/rx'));
 
 rx();
 
-process.chdir(cwd);
-process.chdir(path.resolve('src/backend/opencl/cl/astrobwt'));
-
-astrobwt();
-
 process.chdir(cwd);
 process.chdir(path.resolve('src/backend/opencl/cl/kawpow'));
 

scripts/randomx_boost.sh

@@ -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
+			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 0xc000000401500000
 					wrmsr -a 0xc001102b 0x2000cc14
 					echo "MSR register values for Zen3 applied"
+				fi
 		else
 			echo "Detected Zen1/Zen2 CPU"
 			wrmsr -a 0xc0011020 0

scripts/rtm_ghostrider_example.cmd

@@ -16,5 +16,8 @@
 :: Smaller pools also often have smaller fees/payout limits.
 
 cd %~dp0
+:: Use this command line to connect to non-SSL port
 xmrig.exe -a gr -o raptoreumemporium.com:3008 -u WALLET_ADDRESS -p x
+:: Or use this command line to connect to an SSL port
+:: xmrig.exe -a gr -o rtm.suprnova.cc:4273 --tls -u WALLET_ADDRESS -p x
 pause

src/3rdparty/hwloc/NEWS

@@ -1,5 +1,5 @@
 Copyright © 2009 CNRS
-Copyright © 2009-2021 Inria.  All rights reserved.
+Copyright © 2009-2022 Inria.  All rights reserved.
 Copyright © 2009-2013 Université Bordeaux
 Copyright © 2009-2011 Cisco Systems, Inc.  All rights reserved.
 Copyright © 2020 Hewlett Packard Enterprise.  All rights reserved.
@@ -17,6 +17,88 @@ bug fixes (and other actions) for each version of hwloc since version
 0.9.
 
 
+Version 2.7.1
+-------------
+* Workaround crashes when virtual machines report incoherent x86 CPUID
+  information about numbers of cores and threads.
+  Thanks to Peter Bense for the report.
+* Use setenv() instead of putenv() when trying to force enable oneAPI L0
+  support, to avoid issues with applications that touch the environment,
+  thanks to Josh Hursey for the patch.
+* Add some warnings at the end of configure when GPU libraries are
+  missing on the system or their path is missing in the environment.
+
+
+Version 2.7.0
+-------------
+* Backends
+  + Add support for NUMA nodes and caches with more than 64 PUs across
+    multiple processor groups on Windows 11 and Windows Server 2022.
+  + Group objects are not created for Windows processor groups anymore,
+    except if HWLOC_WINDOWS_PROCESSOR_GROUP_OBJS=1 in the environment.
+  + Expose "Cluster" group objects on Linux kernel 5.16+ for CPUs
+    that share some internal cache or bus. This can be equivalent
+    to the L2 Cache level on some platforms (e.g. x86) or a specific
+    level between L2 and L3 on others (e.g. ARM Kungpeng 920).
+    Thanks to Jonathan Cameron for the help.
+    - HWLOC_DONT_MERGE_CLUSTER_GROUPS=1 may be set in the environment
+      to prevent these groups from being merged with identical caches, etc.
+  + Improve the oneAPI LevelZero backend:
+    - Expose subdevices such as "ze0.1" inside root OS devices ("ze0")
+      when the hardware contains multiple subdevices.
+    - Add many new attributes to describe device type, and the
+      numbers of slices, subslices, execution units and threads.
+    - Expose the memory information as LevelZeroHBM/DDR/MemorySize infos.
+  + Ignore the max frequencies of cores in Linux cpukinds when the
+    base frequencies are available (to avoid exposing hybrid CPUs
+    when Intel Turbo Boost Max 3.0 gives slightly different max
+    frequencies to CPU cores).
+    - May be reverted by setting HWLOC_CPUKINDS_MAXFREQ=1 in the environment.
+* Tools
+  + Add --grey and --palette options to switch lstopo to greyscale or
+    white-background-only graphics, or to tune individual colors.
+* Build
+  + Windows CMake builds now support non-MSVC compilers, detect several
+    features at build time, can build/run tests, etc.
+    Thanks to Michael Hirsch and Alexander Neumann .
+
+
+Version 2.6.0
+-------------
+* Backends
+  + Expose two cpukinds for energy-efficient cores (icestorm) and
+    high-performance cores (firestorm) on Apple M1 on Mac OS X.
+  + Use sysfs CPU "capacity" to rank hybrid cores by efficiency
+    on Linux when available (mostly on recent ARM platforms for now).
+  + Improve HWLOC_MEMBIND_BIND (without the STRICT flag) on Linux kernel
+    >= 5.15: If more than one node is given, the kernel may now use all
+    of them instead of only the first one before falling back to others.
+  + Expose cache os_index when available on Linux, it may be needed
+    when using resctrl to configure cache partitioning, memory bandwidth
+    monitoring, etc.
+  + Add a "XGMIHops" distances matrix in the RSMI backend for AMD GPU
+    interconnected through XGMI links.
+  + Expose AMD GPU memory information (VRAM and GTT) in the RSMI backend.
+  + Add OS devices such as "bxi0" for Atos/Bull BXI HCAs on Linux.
+* Tools
+  + lstopo has a better placement algorithm with respect to I/O
+    objects, see --children-order in the manpage for details.
+  + hwloc-annotate may now change object subtypes and cache or memory
+    sizes.
+* Build
+  + Allow to specify the ROCm installation for building the RSMI backend:
+    - Use a custom installation path if specified with --with-rocm=<dir>.
+    - Use /opt/rocm-<version> if specified with --with-rocm-version=<version>
+      or the ROCM_VERSION environment variable.
+    - Try /opt/rocm if it exists.
+    - See "How do I enable ROCm SMI and select which version to use?"
+      in the FAQ for details.
+  + Add a CMakeLists for Windows under contrib/windows-cmake/ .
+* Documentation
+  + Add FAQ entry "How do I create a custom heterogeneous and
+     asymmetric topology?"
+
+
 Version 2.5.0
 -------------
 * API

src/3rdparty/hwloc/VERSION

@@ -8,8 +8,8 @@
 # Please update HWLOC_VERSION* in contrib/windows/hwloc_config.h too.
 
 major=2
-minor=5
-release=0
+minor=7
+release=1
 
 # 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="Jun 14, 2021"
+date="Mar 20, 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=20:0:5
+libhwloc_so_version=20:3:5
 libnetloc_so_version=0:0:0
 
 # Please also update the <TargetName> lines in contrib/windows/libhwloc.vcxproj

src/3rdparty/hwloc/include/hwloc.h

@@ -29,7 +29,7 @@
  * THAT IS IN THE PDF/HTML THAT IS ***NOT*** IN hwloc.h!
  *
  * There are entire paragraph-length descriptions, discussions, and
- * pretty prictures to explain subtle corner cases, provide concrete
+ * pretty pictures to explain subtle corner cases, provide concrete
  * examples, etc.
  *
  * Please, go read the documentation.  :-)
@@ -346,7 +346,8 @@ typedef enum hwloc_obj_osdev_type_e {
 				  * For instance the "eth0" interface on Linux. */
   HWLOC_OBJ_OSDEV_OPENFABRICS,	/**< \brief Operating system openfabrics device.
 				  * For instance the "mlx4_0" InfiniBand HCA,
-				  * or "hfi1_0" Omni-Path interface on Linux. */
+				  * "hfi1_0" Omni-Path interface,
+				  * or "bxi0" Atos/Bull BXI HCA on Linux. */
   HWLOC_OBJ_OSDEV_DMA,		/**< \brief Operating system dma engine device.
 				  * For instance the "dma0chan0" DMA channel on Linux. */
   HWLOC_OBJ_OSDEV_COPROC	/**< \brief Operating system co-processor device.
@@ -516,7 +517,7 @@ struct hwloc_obj {
                                           * objects).
                                           *
                                           * If the ::HWLOC_TOPOLOGY_FLAG_INCLUDE_DISALLOWED configuration flag is set,
-                                          * some of these CPUs may not be allowed for binding,
+                                          * some of these CPUs may be online but not allowed for binding,
                                           * see hwloc_topology_get_allowed_cpuset().
                                           *
 					  * \note All objects have non-NULL CPU and node sets except Misc and I/O objects.
@@ -548,7 +549,7 @@ struct hwloc_obj {
                                           * nodes more precisely.
                                           *
                                           * If the ::HWLOC_TOPOLOGY_FLAG_INCLUDE_DISALLOWED configuration flag is set,
-                                          * some of these nodes may not be allowed for allocation,
+                                          * some of these nodes may be online but not allowed for allocation,
                                           * see hwloc_topology_get_allowed_nodeset().
                                           *
                                           * If there are no NUMA nodes in the machine, all the memory is close to this
@@ -641,7 +642,7 @@ union hwloc_obj_attr_u {
     unsigned char revision;
     float linkspeed; /* in GB/s */
   } pcidev;
-  /** \brief Bridge specific Object Attribues */
+  /** \brief Bridge specific Object Attributes */
   struct hwloc_bridge_attr_s {
     union {
       struct hwloc_pcidev_attr_s pci;
@@ -1088,7 +1089,7 @@ HWLOC_DECLSPEC int hwloc_obj_add_info(hwloc_obj_t obj, const char *name, const c
  *
  * Some operating systems only support binding threads or processes to a single PU.
  * Others allow binding to larger sets such as entire Cores or Packages or
- * even random sets of invididual PUs. In such operating system, the scheduler
+ * even random sets of individual PUs. In such operating system, the scheduler
  * is free to run the task on one of these PU, then migrate it to another PU, etc.
  * It is often useful to call hwloc_bitmap_singlify() on the target CPU set before
  * passing it to the binding function to avoid these expensive migrations.
@@ -1166,7 +1167,7 @@ typedef enum {
    * CPUs are idle, operating systems may execute the thread/process
    * on those other CPUs instead of the designated CPUs, to let them
    * progress anyway.  Strict binding means that the thread/process
-   * will _never_ execute on other cpus than the designated CPUs, even
+   * will _never_ execute on other CPUs than the designated CPUs, even
    * when those are busy with other tasks and other CPUs are idle.
    *
    * \note Depending on the operating system, strict binding may not
@@ -1203,7 +1204,7 @@ typedef enum {
   HWLOC_CPUBIND_NOMEMBIND = (1<<3)
 } hwloc_cpubind_flags_t;
 
-/** \brief Bind current process or thread on cpus given in physical bitmap \p set.
+/** \brief Bind current process or thread on CPUs given in physical bitmap \p set.
  *
  * \return -1 with errno set to ENOSYS if the action is not supported
  * \return -1 with errno set to EXDEV if the binding cannot be enforced
@@ -1212,12 +1213,13 @@ HWLOC_DECLSPEC int hwloc_set_cpubind(hwloc_topology_t topology, hwloc_const_cpus
 
 /** \brief Get current process or thread binding.
  *
- * Writes into \p set the physical cpuset which the process or thread (according to \e
- * flags) was last bound to.
+ * The CPU-set \p set (previously allocated by the caller)
+ * is filled with the list of PUs which the process or
+ * thread (according to \e flags) was last bound to.
  */
 HWLOC_DECLSPEC int hwloc_get_cpubind(hwloc_topology_t topology, hwloc_cpuset_t set, int flags);
 
-/** \brief Bind a process \p pid on cpus given in physical bitmap \p set.
+/** \brief Bind a process \p pid on CPUs given in physical bitmap \p set.
  *
  * \note \p hwloc_pid_t is \p pid_t on Unix platforms,
  * and \p HANDLE on native Windows platforms.
@@ -1231,6 +1233,10 @@ HWLOC_DECLSPEC int hwloc_get_cpubind(hwloc_topology_t topology, hwloc_cpuset_t s
 HWLOC_DECLSPEC int hwloc_set_proc_cpubind(hwloc_topology_t topology, hwloc_pid_t pid, hwloc_const_cpuset_t set, int flags);
 
 /** \brief Get the current physical binding of process \p pid.
+ *
+ * The CPU-set \p set (previously allocated by the caller)
+ * is filled with the list of PUs which the process
+ * was last bound to.
  *
  * \note \p hwloc_pid_t is \p pid_t on Unix platforms,
  * and \p HANDLE on native Windows platforms.
@@ -1244,7 +1250,7 @@ HWLOC_DECLSPEC int hwloc_set_proc_cpubind(hwloc_topology_t topology, hwloc_pid_t
 HWLOC_DECLSPEC int hwloc_get_proc_cpubind(hwloc_topology_t topology, hwloc_pid_t pid, hwloc_cpuset_t set, int flags);
 
 #ifdef hwloc_thread_t
-/** \brief Bind a thread \p thread on cpus given in physical bitmap \p set.
+/** \brief Bind a thread \p thread on CPUs given in physical bitmap \p set.
  *
  * \note \p hwloc_thread_t is \p pthread_t on Unix platforms,
  * and \p HANDLE on native Windows platforms.
@@ -1256,6 +1262,10 @@ HWLOC_DECLSPEC int hwloc_set_thread_cpubind(hwloc_topology_t topology, hwloc_thr
 
 #ifdef hwloc_thread_t
 /** \brief Get the current physical binding of thread \p tid.
+ *
+ * The CPU-set \p set (previously allocated by the caller)
+ * is filled with the list of PUs which the thread
+ * was last bound to.
  *
  * \note \p hwloc_thread_t is \p pthread_t on Unix platforms,
  * and \p HANDLE on native Windows platforms.
@@ -1266,6 +1276,10 @@ HWLOC_DECLSPEC int hwloc_get_thread_cpubind(hwloc_topology_t topology, hwloc_thr
 #endif
 
 /** \brief Get the last physical CPU where the current process or thread ran.
+ *
+ * The CPU-set \p set (previously allocated by the caller)
+ * is filled with the list of PUs which the process or
+ * thread (according to \e flags) last ran on.
  *
  * The operating system may move some tasks from one processor
  * to another at any time according to their binding,
@@ -1281,6 +1295,10 @@ HWLOC_DECLSPEC int hwloc_get_thread_cpubind(hwloc_topology_t topology, hwloc_thr
 HWLOC_DECLSPEC int hwloc_get_last_cpu_location(hwloc_topology_t topology, hwloc_cpuset_t set, int flags);
 
 /** \brief Get the last physical CPU where a process ran.
+ *
+ * The CPU-set \p set (previously allocated by the caller)
+ * is filled with the list of PUs which the process
+ * last ran on.
  *
  * The operating system may move some tasks from one processor
  * to another at any time according to their binding,
@@ -1511,6 +1529,9 @@ HWLOC_DECLSPEC int hwloc_set_membind(hwloc_topology_t topology, hwloc_const_bitm
 /** \brief Query the default memory binding policy and physical locality of the
  * current process or thread.
  *
+ * The bitmap \p set (previously allocated by the caller)
+ * is filled with the process or thread memory binding.
+ *
  * This function has two output parameters: \p set and \p policy.
  * The values returned in these parameters depend on both the \p flags
  * passed in and the current memory binding policies and nodesets in
@@ -1571,6 +1592,9 @@ HWLOC_DECLSPEC int hwloc_set_proc_membind(hwloc_topology_t topology, hwloc_pid_t
 /** \brief Query the default memory binding policy and physical locality of the
  * specified process.
  *
+ * The bitmap \p set (previously allocated by the caller)
+ * is filled with the process memory binding.
+ *
  * This function has two output parameters: \p set and \p policy.
  * The values returned in these parameters depend on both the \p flags
  * passed in and the current memory binding policies and nodesets in
@@ -1624,6 +1648,9 @@ HWLOC_DECLSPEC int hwloc_set_area_membind(hwloc_topology_t topology, const void
 /** \brief Query the CPUs near the physical NUMA node(s) and binding policy of
  * the memory identified by (\p addr, \p len ).
  *
+ * The bitmap \p set (previously allocated by the caller)
+ * is filled with the memory area binding.
+ *
  * This function has two output parameters: \p set and \p policy.
  * The values returned in these parameters depend on both the \p flags
  * passed in and the memory binding policies and nodesets of the pages
@@ -1652,7 +1679,8 @@ HWLOC_DECLSPEC int hwloc_get_area_membind(hwloc_topology_t topology, const void
 
 /** \brief Get the NUMA nodes where memory identified by (\p addr, \p len ) is physically allocated.
  *
- * Fills \p set according to the NUMA nodes where the memory area pages
+ * The bitmap \p set (previously allocated by the caller)
+ * is filled according to the NUMA nodes where the memory area pages
  * are physically allocated. If no page is actually allocated yet,
  * \p set may be empty.
  *
@@ -1698,9 +1726,12 @@ HWLOC_DECLSPEC void *hwloc_alloc_membind(hwloc_topology_t topology, size_t len,
 
 /** \brief Allocate some memory on NUMA memory nodes specified by \p set
  *
- * This is similar to hwloc_alloc_membind_nodeset() except that it is allowed to change
- * the current memory binding policy, thus providing more binding support, at
- * the expense of changing the current state.
+ * First, try to allocate properly with hwloc_alloc_membind().
+ * On failure, the current process or thread memory binding policy
+ * is changed with hwloc_set_membind() before allocating memory.
+ * Thus this function works in more cases, at the expense of changing
+ * the current state (possibly affecting future allocations that
+ * would not specify any policy).
  *
  * If ::HWLOC_MEMBIND_BYNODESET is specified, set is considered a nodeset.
  * Otherwise it's a cpuset.
@@ -1883,8 +1914,9 @@ HWLOC_DECLSPEC int hwloc_topology_set_components(hwloc_topology_t __hwloc_restri
 enum hwloc_topology_flags_e {
  /** \brief Detect the whole system, ignore reservations, include disallowed objects.
    *
-   * Gather all resources, even if some were disabled by the administrator.
+   * Gather all online resources, even if some were disabled by the administrator.
    * For instance, ignore Linux Cgroup/Cpusets and gather all processors and memory nodes.
+   * However offline PUs and NUMA nodes are still ignored.
    *
    * When this flag is not set, PUs and NUMA nodes that are disallowed are not added to the topology.
    * Parent objects (package, core, cache, etc.) are added only if some of their children are allowed.
@@ -2035,10 +2067,12 @@ enum hwloc_topology_flags_e {
  *
  * Set a OR'ed set of ::hwloc_topology_flags_e onto a topology that was not yet loaded.
  *
- * If this function is called multiple times, the last invokation will erase
+ * If this function is called multiple times, the last invocation will erase
  * and replace the set of flags that was previously set.
  *
- * The flags set in a topology may be retrieved with hwloc_topology_get_flags()
+ * By default, no flags are set (\c 0).
+ *
+ * The flags set in a topology may be retrieved with hwloc_topology_get_flags().
  */
 HWLOC_DECLSPEC int hwloc_topology_set_flags (hwloc_topology_t topology, unsigned long flags);
 
@@ -2046,6 +2080,9 @@ HWLOC_DECLSPEC int hwloc_topology_set_flags (hwloc_topology_t topology, unsigned
  *
  * Get the OR'ed set of ::hwloc_topology_flags_e of a topology.
  *
+ * If hwloc_topology_set_flags() was not called earlier,
+ * no flags are set (\c 0 is returned).
+ *
  * \return the flags previously set with hwloc_topology_set_flags().
  */
 HWLOC_DECLSPEC unsigned long hwloc_topology_get_flags (hwloc_topology_t topology);

src/3rdparty/hwloc/include/hwloc/autogen/config.h

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009 CNRS
- * Copyright © 2009-2020 Inria.  All rights reserved.
+ * Copyright © 2009-2021 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 "2.5.0"
+#define HWLOC_VERSION "2.7.1"
 #define HWLOC_VERSION_MAJOR 2
-#define HWLOC_VERSION_MINOR 5
-#define HWLOC_VERSION_RELEASE 0
+#define HWLOC_VERSION_MINOR 7
+#define HWLOC_VERSION_RELEASE 1
 #define HWLOC_VERSION_GREEK ""
 
 #define __hwloc_restrict

src/3rdparty/hwloc/include/hwloc/cpukinds.h

@@ -1,5 +1,5 @@
 /*
- * Copyright © 2020 Inria.  All rights reserved.
+ * Copyright © 2020-2021 Inria.  All rights reserved.
  * See COPYING in top-level directory.
  */
 
@@ -42,18 +42,23 @@ extern "C" {
  * (for instance the "CoreType" and "FrequencyMaxMHz",
  *  see \ref topoattrs_cpukinds).
  *
- * A higher efficiency value means intrinsic greater performance
+ * A higher efficiency value means greater intrinsic performance
  * (and possibly less performance/power efficiency).
- * Kinds with lower efficiency are ranked first:
+ * Kinds with lower efficiency values are ranked first:
  * Passing 0 as \p kind_index to hwloc_cpukinds_get_info() will
- * return information about the less efficient CPU kind.
+ * return information about the CPU kind with lower performance
+ * but higher energy-efficiency.
+ * Higher \p kind_index values would rather return information
+ * about power-hungry high-performance cores.
  *
- * When available, efficiency values are gathered from the operating
- * system (when \p cpukind_efficiency is set in the
- * struct hwloc_topology_discovery_support array, only on Windows 10 for now).
- * Otherwise hwloc tries to compute efficiencies
- * by comparing CPU kinds using frequencies (on ARM),
- * or core types and frequencies (on other architectures).
+ * When available, efficiency values are gathered from the operating system.
+ * If so, \p cpukind_efficiency is set in the struct hwloc_topology_discovery_support array.
+ * This is currently available on Windows 10, Mac OS X (Darwin),
+ * and on some Linux platforms where core "capacity" is exposed in sysfs.
+ *
+ * If the operating system does not expose core efficiencies natively,
+ * hwloc tries to compute efficiencies by comparing CPU kinds using
+ * frequencies (on ARM), or core types and frequencies (on other architectures).
  * The environment variable HWLOC_CPUKINDS_RANKING may be used
  * to change this heuristics, see \ref envvar.
  *

src/3rdparty/hwloc/include/hwloc/distances.h

@@ -35,7 +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" and "NVLinkBandwidth".
+ * Others distance structures include and "XGMIBandwidth", "XGMIHops"
+ * 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.
@@ -159,7 +160,7 @@ 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" and "NVLinkBandwidth".
+ * Others include "XGMIBandwidth", "XGMIHops" and "NVLinkBandwidth".
  */
 HWLOC_DECLSPEC int
 hwloc_distances_get_by_name(hwloc_topology_t topology, const char *name,

src/3rdparty/hwloc/include/hwloc/linux.h

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

src/3rdparty/hwloc/include/hwloc/memattrs.h

@@ -1,5 +1,5 @@
 /*
- * Copyright © 2019-2020 Inria.  All rights reserved.
+ * Copyright © 2019-2022 Inria.  All rights reserved.
  * See COPYING in top-level directory.
  */
 
@@ -354,7 +354,7 @@ hwloc_memattr_register(hwloc_topology_t topology,
  * \p flags must be \c 0 for now.
  *
  * \note The initiator \p initiator should be of type ::HWLOC_LOCATION_TYPE_CPUSET
- * when refering to accesses performed by CPU cores.
+ * when referring to accesses performed by CPU cores.
  * ::HWLOC_LOCATION_TYPE_OBJECT is currently unused internally by hwloc,
  * but users may for instance use it to provide custom information about
  * host memory accesses performed by GPUs.
@@ -398,7 +398,7 @@ hwloc_memattr_set_value(hwloc_topology_t topology,
  * values.
  *
  * \note The initiator \p initiator should be of type ::HWLOC_LOCATION_TYPE_CPUSET
- * when refering to accesses performed by CPU cores.
+ * when referring to accesses performed by CPU cores.
  * ::HWLOC_LOCATION_TYPE_OBJECT is currently unused internally by hwloc,
  * but users may for instance use it to provide custom information about
  * host memory accesses performed by GPUs.
@@ -408,7 +408,7 @@ hwloc_memattr_get_targets(hwloc_topology_t topology,
                           hwloc_memattr_id_t attribute,
                           struct hwloc_location *initiator,
                           unsigned long flags,
-                          unsigned *nrp, hwloc_obj_t *targets, hwloc_uint64_t *values);
+                          unsigned *nr, hwloc_obj_t *targets, hwloc_uint64_t *values);
 
 /** \brief Return the initiators that have values for a given attribute for a specific target NUMA node.
  *

src/3rdparty/hwloc/include/hwloc/plugins.h

@@ -497,6 +497,7 @@ hwloc_filter_check_pcidev_subtype_important(unsigned classid)
   return (baseclass == 0x03 /* PCI_BASE_CLASS_DISPLAY */
 	  || baseclass == 0x02 /* PCI_BASE_CLASS_NETWORK */
 	  || baseclass == 0x01 /* PCI_BASE_CLASS_STORAGE */
+	  || baseclass == 0x00 /* Unclassified, for Atos/Bull BXI */
 	  || baseclass == 0x0b /* PCI_BASE_CLASS_PROCESSOR */
 	  || classid == 0x0c04 /* PCI_CLASS_SERIAL_FIBER */
 	  || classid == 0x0c06 /* PCI_CLASS_SERIAL_INFINIBAND */

src/3rdparty/hwloc/include/private/autogen/config.h

@@ -1,6 +1,6 @@
 /*
  * Copyright © 2009, 2011, 2012 CNRS.  All rights reserved.
- * Copyright © 2009-2020 Inria.  All rights reserved.
+ * Copyright © 2009-2021 Inria.  All rights reserved.
  * Copyright © 2009, 2011, 2012, 2015 Université Bordeaux.  All rights reserved.
  * Copyright © 2009-2020 Cisco Systems, Inc.  All rights reserved.
  * $COPYRIGHT$
@@ -290,10 +290,6 @@
 /* Define to '1' if sysctlbyname is present and usable */
 /* #undef HAVE_SYSCTLBYNAME */
 
-/* Define to 1 if the system has the type
-   `SYSTEM_LOGICAL_PROCESSOR_INFORMATION'. */
-#define HAVE_SYSTEM_LOGICAL_PROCESSOR_INFORMATION 1
-
 /* Define to 1 if the system has the type
    `SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX'. */
 #define HAVE_SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX 1

src/3rdparty/hwloc/include/private/misc.h

@@ -504,7 +504,7 @@ hwloc__obj_type_is_icache(hwloc_obj_type_t type)
   }                                    \
 } while(0)
 #else /* HAVE_USELOCALE */
-#if __HWLOC_HAVE_ATTRIBUTE_UNUSED
+#if HWLOC_HAVE_ATTRIBUTE_UNUSED
 #define hwloc_localeswitch_declare int __dummy_nolocale __hwloc_attribute_unused
 #define hwloc_localeswitch_init()
 #else

src/3rdparty/hwloc/include/private/private.h

@@ -480,6 +480,7 @@ extern char * hwloc_progname(struct hwloc_topology *topology);
 #define HWLOC_GROUP_KIND_AIX_SDL_UNKNOWN		210	/* subkind is SDL level */
 #define HWLOC_GROUP_KIND_WINDOWS_PROCESSOR_GROUP	220	/* no subkind */
 #define HWLOC_GROUP_KIND_WINDOWS_RELATIONSHIP_UNKNOWN	221	/* no subkind */
+#define HWLOC_GROUP_KIND_LINUX_CLUSTER                  222     /* no subkind */
 /* distance groups */
 #define HWLOC_GROUP_KIND_DISTANCE			900	/* subkind is round of adding these groups during distance based grouping */
 /* finally, hwloc-specific groups required to insert something else, should disappear as soon as possible */

src/3rdparty/hwloc/include/private/windows.h

@@ -0,0 +1,21 @@
+/*
+ * Copyright © 2009 Université Bordeaux
+ * Copyright © 2020 Inria.  All rights reserved.
+ *
+ * See COPYING in top-level directory.
+ */
+
+#ifndef HWLOC_PRIVATE_WINDOWS_H
+#define HWLOC_PRIVATE_WINDOWS_H
+
+#ifdef __GNUC__
+#define _ANONYMOUS_UNION __extension__
+#define _ANONYMOUS_STRUCT __extension__
+#else
+#define _ANONYMOUS_UNION
+#define _ANONYMOUS_STRUCT
+#endif /* __GNUC__ */
+#define DUMMYUNIONNAME
+#define DUMMYSTRUCTNAME
+
+#endif /* HWLOC_PRIVATE_WINDOWS_H */

src/3rdparty/hwloc/src/cpukinds.c

@@ -42,6 +42,9 @@ hwloc_internal_cpukinds_dup(hwloc_topology_t new, hwloc_topology_t old)
   struct hwloc_internal_cpukind_s *kinds;
   unsigned i;
 
+  if (!old->nr_cpukinds)
+    return 0;
+
   kinds = hwloc_tma_malloc(tma, old->nr_cpukinds * sizeof(*kinds));
   if (!kinds)
     return -1;
@@ -445,7 +448,9 @@ static int hwloc__cpukinds_compare_ranking_values(const void *_a, const void *_b
 {
   const struct hwloc_internal_cpukind_s *a = _a;
   const struct hwloc_internal_cpukind_s *b = _b;
-  return a->ranking_value - b->ranking_value;
+  uint64_t arv = a->ranking_value;
+  uint64_t brv = b->ranking_value;
+  return arv < brv ? -1 : arv > brv ? 1 : 0;
 }
 
 /* this function requires ranking values to be unique */

src/3rdparty/hwloc/src/memattrs.c

@@ -1,5 +1,5 @@
 /*
- * Copyright © 2020 Inria.  All rights reserved.
+ * Copyright © 2020-2021 Inria.  All rights reserved.
  * See COPYING in top-level directory.
  */
 
@@ -127,6 +127,8 @@ hwloc_internal_memattrs_dup(struct hwloc_topology *new, struct hwloc_topology *o
   struct hwloc_internal_memattr_s *imattrs;
   hwloc_memattr_id_t id;
 
+  /* old->nr_memattrs is always > 0 thanks to default memattrs */
+
   imattrs = hwloc_tma_malloc(tma, old->nr_memattrs * sizeof(*imattrs));
   if (!imattrs)
     return -1;

src/3rdparty/hwloc/src/pci-common.c

@@ -810,13 +810,14 @@ hwloc_pcidisc_find_linkspeed(const unsigned char *config,
    * 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
    */
 
   /* lanespeed in Gbit/s */
   if (speed <= 2)
     lanespeed = 2.5f * speed * 0.8f;
   else
-    lanespeed = 8.0f * (1<<(speed-3)) * 128/130; /* assume Gen6 will be 64 GT/s and so on */
+    lanespeed = 8.0f * (1<<(speed-3)) * 128/130; /* assume Gen7 will be 128 GT/s and so on */
 
   /* linkspeed in GB/s */
   *linkspeed = lanespeed * width / 8;

src/3rdparty/hwloc/src/topology-windows.c

@@ -13,6 +13,7 @@
 #include "hwloc.h"
 #include "hwloc/windows.h"
 #include "private/private.h"
+#include "private/windows.h" /* must be before windows.h */
 #include "private/debug.h"
 
 #include <windows.h>
@@ -65,26 +66,6 @@ typedef enum _LOGICAL_PROCESSOR_RELATIONSHIP {
 #  endif /* HAVE_RELATIONPROCESSORPACKAGE */
 #endif /* HAVE_LOGICAL_PROCESSOR_RELATIONSHIP */
 
-#ifndef HAVE_SYSTEM_LOGICAL_PROCESSOR_INFORMATION
-typedef struct _SYSTEM_LOGICAL_PROCESSOR_INFORMATION {
-  ULONG_PTR ProcessorMask;
-  LOGICAL_PROCESSOR_RELATIONSHIP Relationship;
-  _ANONYMOUS_UNION
-  union {
-    struct {
-      BYTE flags;
-    } ProcessorCore;
-    struct {
-      DWORD NodeNumber;
-    } NumaNode;
-    CACHE_DESCRIPTOR Cache;
-    ULONGLONG Reserved[2];
-  } DUMMYUNIONNAME;
-} SYSTEM_LOGICAL_PROCESSOR_INFORMATION, *PSYSTEM_LOGICAL_PROCESSOR_INFORMATION;
-#endif
-
-/* Extended interface, for group support */
-
 #ifndef HAVE_GROUP_AFFINITY
 typedef struct _GROUP_AFFINITY {
   KAFFINITY Mask;
@@ -93,35 +74,40 @@ typedef struct _GROUP_AFFINITY {
 } GROUP_AFFINITY, *PGROUP_AFFINITY;
 #endif
 
-#ifndef HAVE_PROCESSOR_RELATIONSHIP
+/* always use our own structure because the EfficiencyClass field didn't exist before Win10 */
 typedef struct HWLOC_PROCESSOR_RELATIONSHIP {
   BYTE Flags;
-  BYTE EfficiencyClass; /* for RelationProcessorCore, higher means greater performance but less efficiency, only available in Win10+ */
+  BYTE EfficiencyClass; /* for RelationProcessorCore, higher means greater performance but less efficiency */
   BYTE Reserved[20];
   WORD GroupCount;
   GROUP_AFFINITY GroupMask[ANYSIZE_ARRAY];
-} PROCESSOR_RELATIONSHIP, *PPROCESSOR_RELATIONSHIP;
-#endif
+} HWLOC_PROCESSOR_RELATIONSHIP;
 
-#ifndef HAVE_NUMA_NODE_RELATIONSHIP
-typedef struct _NUMA_NODE_RELATIONSHIP {
+/* always use our own structure because the GroupCount and GroupMasks fields didn't exist in some Win10 */
+typedef struct HWLOC_NUMA_NODE_RELATIONSHIP {
   DWORD NodeNumber;
-  BYTE Reserved[20];
+  BYTE Reserved[18];
+  WORD GroupCount;
+  _ANONYMOUS_UNION
+  union {
     GROUP_AFFINITY GroupMask;
-} NUMA_NODE_RELATIONSHIP, *PNUMA_NODE_RELATIONSHIP;
-#endif
+    GROUP_AFFINITY GroupMasks[ANYSIZE_ARRAY];
+  } DUMMYUNIONNAME;
+} HWLOC_NUMA_NODE_RELATIONSHIP;
 
-#ifndef HAVE_CACHE_RELATIONSHIP
-typedef struct _CACHE_RELATIONSHIP {
+typedef struct HWLOC_CACHE_RELATIONSHIP {
   BYTE Level;
   BYTE Associativity;
   WORD LineSize;
   DWORD CacheSize;
   PROCESSOR_CACHE_TYPE Type;
-  BYTE Reserved[20];
+  BYTE Reserved[18];
+  WORD GroupCount;
+  union {
     GROUP_AFFINITY GroupMask;
-} CACHE_RELATIONSHIP, *PCACHE_RELATIONSHIP;
-#endif
+    GROUP_AFFINITY GroupMasks[ANYSIZE_ARRAY];
+  } DUMMYUNIONNAME;
+} HWLOC_CACHE_RELATIONSHIP;
 
 #ifndef HAVE_PROCESSOR_GROUP_INFO
 typedef struct _PROCESSOR_GROUP_INFO {
@@ -141,20 +127,19 @@ typedef struct _GROUP_RELATIONSHIP {
 } GROUP_RELATIONSHIP, *PGROUP_RELATIONSHIP;
 #endif
 
-#ifndef HAVE_SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX
-typedef struct _SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX {
+/* always use our own structure because we need our own HWLOC_PROCESSOR/CACHE/NUMA_NODE_RELATIONSHIP */
+typedef struct HWLOC_SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX {
   LOGICAL_PROCESSOR_RELATIONSHIP Relationship;
   DWORD Size;
   _ANONYMOUS_UNION
   union {
-    PROCESSOR_RELATIONSHIP Processor;
-    NUMA_NODE_RELATIONSHIP NumaNode;
-    CACHE_RELATIONSHIP Cache;
+    HWLOC_PROCESSOR_RELATIONSHIP Processor;
+    HWLOC_NUMA_NODE_RELATIONSHIP NumaNode;
+    HWLOC_CACHE_RELATIONSHIP Cache;
     GROUP_RELATIONSHIP Group;
     /* Odd: no member to tell the cpu mask of the package... */
   } DUMMYUNIONNAME;
-} SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX, *PSYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX;
-#endif
+} HWLOC_SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX;
 
 #ifndef HAVE_PSAPI_WORKING_SET_EX_BLOCK
 typedef union _PSAPI_WORKING_SET_EX_BLOCK {
@@ -200,10 +185,7 @@ static PFN_GETCURRENTPROCESSORNUMBER GetCurrentProcessorNumberProc;
 typedef VOID (WINAPI *PFN_GETCURRENTPROCESSORNUMBEREX)(PPROCESSOR_NUMBER);
 static PFN_GETCURRENTPROCESSORNUMBEREX GetCurrentProcessorNumberExProc;
 
-typedef BOOL (WINAPI *PFN_GETLOGICALPROCESSORINFORMATION)(PSYSTEM_LOGICAL_PROCESSOR_INFORMATION Buffer, PDWORD ReturnLength);
-static PFN_GETLOGICALPROCESSORINFORMATION GetLogicalProcessorInformationProc;
-
-typedef BOOL (WINAPI *PFN_GETLOGICALPROCESSORINFORMATIONEX)(LOGICAL_PROCESSOR_RELATIONSHIP relationship, PSYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX Buffer, PDWORD ReturnLength);
+typedef BOOL (WINAPI *PFN_GETLOGICALPROCESSORINFORMATIONEX)(LOGICAL_PROCESSOR_RELATIONSHIP relationship, HWLOC_SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *Buffer, PDWORD ReturnLength);
 static PFN_GETLOGICALPROCESSORINFORMATIONEX GetLogicalProcessorInformationExProc;
 
 typedef BOOL (WINAPI *PFN_SETTHREADGROUPAFFINITY)(HANDLE hThread, const GROUP_AFFINITY *GroupAffinity, PGROUP_AFFINITY PreviousGroupAffinity);
@@ -244,8 +226,6 @@ static void hwloc_win_get_function_ptrs(void)
 	(PFN_GETACTIVEPROCESSORGROUPCOUNT) GetProcAddress(kernel32, "GetActiveProcessorGroupCount");
       GetActiveProcessorCountProc =
 	(PFN_GETACTIVEPROCESSORCOUNT) GetProcAddress(kernel32, "GetActiveProcessorCount");
-      GetLogicalProcessorInformationProc =
-	(PFN_GETLOGICALPROCESSORINFORMATION) GetProcAddress(kernel32, "GetLogicalProcessorInformation");
       GetCurrentProcessorNumberProc =
 	(PFN_GETCURRENTPROCESSORNUMBER) GetProcAddress(kernel32, "GetCurrentProcessorNumber");
       GetCurrentProcessorNumberExProc =
@@ -370,13 +350,13 @@ static hwloc_cpuset_t * processor_group_cpusets = NULL;
 static void
 hwloc_win_get_processor_groups(void)
 {
-  PSYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX procInfoTotal, tmpprocInfoTotal, procInfo;
+  HWLOC_SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *procInfoTotal, *tmpprocInfoTotal, *procInfo;
   DWORD length;
   unsigned i;
 
   hwloc_debug("querying windows processor groups\n");
 
-  if (!GetActiveProcessorGroupCountProc || !GetLogicalProcessorInformationExProc)
+  if (!GetLogicalProcessorInformationExProc)
     goto error;
 
   nr_processor_groups = GetActiveProcessorGroupCountProc();
@@ -415,6 +395,8 @@ hwloc_win_get_processor_groups(void)
 
     assert(procInfo->Relationship == RelationGroup);
 
+    hwloc_debug("Found %u active windows processor groups\n",
+                (unsigned) procInfo->Group.ActiveGroupCount);
     for (id = 0; id < procInfo->Group.ActiveGroupCount; id++) {
       KAFFINITY mask;
       hwloc_bitmap_t set;
@@ -424,8 +406,8 @@ hwloc_win_get_processor_groups(void)
         goto error_with_cpusets;
 
       mask = procInfo->Group.GroupInfo[id].ActiveProcessorMask;
-      hwloc_debug("group %u %d cpus mask %lx\n", id,
-                  procInfo->Group.GroupInfo[id].ActiveProcessorCount, mask);
+      hwloc_debug("group %u with %u cpus mask 0x%llx\n", id,
+                  (unsigned) procInfo->Group.GroupInfo[id].ActiveProcessorCount, (unsigned long long) mask);
       /* KAFFINITY is ULONG_PTR */
       hwloc_bitmap_set_ith_ULONG_PTR(set, id, mask);
       /* FIXME: what if running 32bits on a 64bits windows with 64-processor groups?
@@ -1008,6 +990,8 @@ hwloc_look_windows(struct hwloc_backend *backend, struct hwloc_disc_status *dsta
   unsigned hostname_size = sizeof(hostname);
   int has_efficiencyclass = 0;
   struct hwloc_win_efficiency_classes eclasses;
+  char *env = getenv("HWLOC_WINDOWS_PROCESSOR_GROUP_OBJS");
+  int keep_pgroup_objs = (env && atoi(env));
 
   assert(dstatus->phase == HWLOC_DISC_PHASE_CPU);
 
@@ -1038,137 +1022,8 @@ hwloc_look_windows(struct hwloc_backend *backend, struct hwloc_disc_status *dsta
 
   GetSystemInfo(&SystemInfo);
 
-  if (!GetLogicalProcessorInformationExProc && GetLogicalProcessorInformationProc) {
-      PSYSTEM_LOGICAL_PROCESSOR_INFORMATION procInfo, tmpprocInfo;
-      unsigned id;
-      unsigned i;
-      struct hwloc_obj *obj;
-      hwloc_obj_type_t type;
-
-      length = 0;
-      procInfo = NULL;
-
-      while (1) {
-	if (GetLogicalProcessorInformationProc(procInfo, &length))
-	  break;
-	if (GetLastError() != ERROR_INSUFFICIENT_BUFFER)
-	  return -1;
-	tmpprocInfo = realloc(procInfo, length);
-	if (!tmpprocInfo) {
-	  free(procInfo);
-	  goto out;
-	}
-	procInfo = tmpprocInfo;
-      }
-
-      assert(!length || procInfo);
-
-      for (i = 0; i < length / sizeof(*procInfo); i++) {
-
-        /* Ignore unknown caches */
-	if (procInfo->Relationship == RelationCache
-		&& procInfo->Cache.Type != CacheUnified
-		&& procInfo->Cache.Type != CacheData
-		&& procInfo->Cache.Type != CacheInstruction)
-	  continue;
-
-	id = HWLOC_UNKNOWN_INDEX;
-	switch (procInfo[i].Relationship) {
-	  case RelationNumaNode:
-	    type = HWLOC_OBJ_NUMANODE;
-	    id = procInfo[i].NumaNode.NodeNumber;
-	    gotnuma++;
-	    if (id > max_numanode_index)
-	      max_numanode_index = id;
-	    break;
-	  case RelationProcessorPackage:
-	    type = HWLOC_OBJ_PACKAGE;
-	    break;
-	  case RelationCache:
-	    type = (procInfo[i].Cache.Type == CacheInstruction ? HWLOC_OBJ_L1ICACHE : HWLOC_OBJ_L1CACHE) + procInfo[i].Cache.Level - 1;
-	    break;
-	  case RelationProcessorCore:
-	    type = HWLOC_OBJ_CORE;
-	    break;
-	  case RelationGroup:
-	  default:
-	    type = HWLOC_OBJ_GROUP;
-	    break;
-	}
-
-	if (!hwloc_filter_check_keep_object_type(topology, type))
-	  continue;
-
-	obj = hwloc_alloc_setup_object(topology, type, id);
-        obj->cpuset = hwloc_bitmap_alloc();
-	hwloc_debug("%s#%u mask %llx\n", hwloc_obj_type_string(type), id, (unsigned long long) procInfo[i].ProcessorMask);
-	/* ProcessorMask is a ULONG_PTR */
-	hwloc_bitmap_set_ith_ULONG_PTR(obj->cpuset, 0, procInfo[i].ProcessorMask);
-	hwloc_debug_2args_bitmap("%s#%u bitmap %s\n", hwloc_obj_type_string(type), id, obj->cpuset);
-
-	switch (type) {
-	  case HWLOC_OBJ_NUMANODE:
-	    {
-	      ULONGLONG avail;
-	      obj->nodeset = hwloc_bitmap_alloc();
-	      hwloc_bitmap_set(obj->nodeset, id);
-	      if ((GetNumaAvailableMemoryNodeExProc && GetNumaAvailableMemoryNodeExProc(id, &avail))
-		  || (GetNumaAvailableMemoryNodeProc && GetNumaAvailableMemoryNodeProc(id, &avail))) {
-		obj->attr->numanode.local_memory = avail;
-		gotnumamemory++;
-	      }
-	      obj->attr->numanode.page_types_len = 2;
-	      obj->attr->numanode.page_types = malloc(2 * sizeof(*obj->attr->numanode.page_types));
-	      memset(obj->attr->numanode.page_types, 0, 2 * sizeof(*obj->attr->numanode.page_types));
-	      obj->attr->numanode.page_types_len = 1;
-	      obj->attr->numanode.page_types[0].size = SystemInfo.dwPageSize;
-#if HAVE_DECL__SC_LARGE_PAGESIZE
-	      obj->attr->numanode.page_types_len++;
-	      obj->attr->numanode.page_types[1].size = sysconf(_SC_LARGE_PAGESIZE);
-#endif
-	      break;
-	    }
-	  case HWLOC_OBJ_L1CACHE:
-	  case HWLOC_OBJ_L2CACHE:
-	  case HWLOC_OBJ_L3CACHE:
-	  case HWLOC_OBJ_L4CACHE:
-	  case HWLOC_OBJ_L5CACHE:
-	  case HWLOC_OBJ_L1ICACHE:
-	  case HWLOC_OBJ_L2ICACHE:
-	  case HWLOC_OBJ_L3ICACHE:
-	    obj->attr->cache.size = procInfo[i].Cache.Size;
-	    obj->attr->cache.associativity = procInfo[i].Cache.Associativity == CACHE_FULLY_ASSOCIATIVE ? -1 : procInfo[i].Cache.Associativity ;
-	    obj->attr->cache.linesize = procInfo[i].Cache.LineSize;
-	    obj->attr->cache.depth = procInfo[i].Cache.Level;
-	    switch (procInfo->Cache.Type) {
-	      case CacheUnified:
-		obj->attr->cache.type = HWLOC_OBJ_CACHE_UNIFIED;
-		break;
-	      case CacheData:
-		obj->attr->cache.type = HWLOC_OBJ_CACHE_DATA;
-		break;
-	      case CacheInstruction:
-		obj->attr->cache.type = HWLOC_OBJ_CACHE_INSTRUCTION;
-		break;
-	      default:
-		hwloc_free_unlinked_object(obj);
-		continue;
-	    }
-	    break;
-	  case HWLOC_OBJ_GROUP:
-	    obj->attr->group.kind = procInfo[i].Relationship == RelationGroup ? HWLOC_GROUP_KIND_WINDOWS_PROCESSOR_GROUP : HWLOC_GROUP_KIND_WINDOWS_RELATIONSHIP_UNKNOWN;
-	    break;
-	  default:
-	    break;
-	}
-	hwloc__insert_object_by_cpuset(topology, NULL, obj, "windows:GetLogicalProcessorInformation");
-      }
-
-      free(procInfo);
-  }
-
   if (GetLogicalProcessorInformationExProc) {
-      PSYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX procInfoTotal, tmpprocInfoTotal, procInfo;
+      HWLOC_SYSTEM_LOGICAL_PROCESSOR_INFORMATION_EX *procInfoTotal, *tmpprocInfoTotal, *procInfo;
       unsigned id;
       struct hwloc_obj *obj;
       hwloc_obj_type_t type;
@@ -1207,8 +1062,16 @@ hwloc_look_windows(struct hwloc_backend *backend, struct hwloc_disc_status *dsta
 	switch (procInfo->Relationship) {
 	  case RelationNumaNode:
 	    type = HWLOC_OBJ_NUMANODE;
+            /* Starting with Windows 11 and Server 2022, the GroupCount field is valid and >=1
+             * and we may read GroupMasks[]. Older releases have GroupCount==0 and we must read GroupMask.
+             */
+            if (procInfo->NumaNode.GroupCount) {
+              num = procInfo->NumaNode.GroupCount;
+              GroupMask = procInfo->NumaNode.GroupMasks;
+            } else {
               num = 1;
               GroupMask = &procInfo->NumaNode.GroupMask;
+            }
 	    id = procInfo->NumaNode.NodeNumber;
 	    gotnuma++;
 	    if (id > max_numanode_index)
@@ -1221,18 +1084,20 @@ hwloc_look_windows(struct hwloc_backend *backend, struct hwloc_disc_status *dsta
 	    break;
 	  case RelationCache:
 	    type = (procInfo->Cache.Type == CacheInstruction ? HWLOC_OBJ_L1ICACHE : HWLOC_OBJ_L1CACHE) + procInfo->Cache.Level - 1;
+            /* GroupCount added approximately with NumaNode.GroupCount above */
+            if (procInfo->Cache.GroupCount) {
+              num = procInfo->Cache.GroupCount;
+              GroupMask = procInfo->Cache.GroupMasks;
+            } else {
               num = 1;
               GroupMask = &procInfo->Cache.GroupMask;
+            }
 	    break;
 	  case RelationProcessorCore:
 	    type = HWLOC_OBJ_CORE;
             num = procInfo->Processor.GroupCount;
             GroupMask = procInfo->Processor.GroupMask;
-            if (has_efficiencyclass)
-              /* the EfficiencyClass field didn't exist before Windows10 and recent MSVC headers,
-               * so just access it manually instead of trying to detect it.
-               */
-              efficiency_class = * ((&procInfo->Processor.Flags) + 1);
+            efficiency_class = procInfo->Processor.EfficiencyClass;
 	    break;
 	  case RelationGroup:
 	    /* So strange an interface... */
@@ -1257,11 +1122,12 @@ hwloc_look_windows(struct hwloc_backend *backend, struct hwloc_disc_status *dsta
 		groups_pu_set = hwloc_bitmap_alloc();
 	      hwloc_bitmap_or(groups_pu_set, groups_pu_set, set);
 
-	      if (hwloc_filter_check_keep_object_type(topology, HWLOC_OBJ_GROUP)) {
+              /* Ignore processor groups unless requested and filtered-in */
+              if (keep_pgroup_objs && hwloc_filter_check_keep_object_type(topology, HWLOC_OBJ_GROUP)) {
 		obj = hwloc_alloc_setup_object(topology, HWLOC_OBJ_GROUP, id);
 		obj->cpuset = set;
 		obj->attr->group.kind = HWLOC_GROUP_KIND_WINDOWS_PROCESSOR_GROUP;
-		hwloc__insert_object_by_cpuset(topology, NULL, obj, "windows:GetLogicalProcessorInformation:ProcessorGroup");
+		hwloc__insert_object_by_cpuset(topology, NULL, obj, "windows:GetLogicalProcessorInformationEx:ProcessorGroup");
 	      } else
 		hwloc_bitmap_free(set);
 	    }

src/3rdparty/hwloc/src/topology-x86.c

@@ -500,7 +500,8 @@ static void read_amd_cores_topoext(struct procinfo *infos, unsigned long flags,
       nodes_per_proc = ((ecx >> 8) & 7) + 1;
     }
     if ((infos->cpufamilynumber == 0x15 && nodes_per_proc > 2)
-	|| ((infos->cpufamilynumber == 0x17 || infos->cpufamilynumber == 0x18) && nodes_per_proc > 4)) {
+	|| ((infos->cpufamilynumber == 0x17 || infos->cpufamilynumber == 0x18) && nodes_per_proc > 4)
+        || (infos->cpufamilynumber == 0x19 && nodes_per_proc > 1)) {
       hwloc_debug("warning: undefined nodes_per_proc value %u, assuming it means %u\n", nodes_per_proc, nodes_per_proc);
     }
   }
@@ -613,10 +614,13 @@ static void look_proc(struct hwloc_backend *backend, struct procinfo *infos, uns
   eax = 0x01;
   cpuid_or_from_dump(&eax, &ebx, &ecx, &edx, src_cpuiddump);
   infos->apicid = ebx >> 24;
-  if (edx & (1 << 28))
+  if (edx & (1 << 28)) {
     legacy_max_log_proc = 1 << hwloc_flsl(((ebx >> 16) & 0xff) - 1);
-  else
+  } else {
+    hwloc_debug("HTT bit not set in CPUID 0x01.edx, assuming legacy_max_log_proc = 1\n");
     legacy_max_log_proc = 1;
+  }
+
   hwloc_debug("APIC ID 0x%02x legacy_max_log_proc %u\n", infos->apicid, legacy_max_log_proc);
   infos->ids[PKG] = infos->apicid / legacy_max_log_proc;
   legacy_log_proc_id = infos->apicid % legacy_max_log_proc;
@@ -679,14 +683,25 @@ static void look_proc(struct hwloc_backend *backend, struct procinfo *infos, uns
       unsigned max_nbcores;
       unsigned max_nbthreads;
       unsigned threadid __hwloc_attribute_unused;
+      hwloc_debug("Trying to get core/thread IDs from 0x04...\n");
       max_nbcores = ((eax >> 26) & 0x3f) + 1;
+      hwloc_debug("found %u cores max\n", max_nbcores);
+      /* some VMs (e.g. issue#525) don't report valid information, check things before dividing by 0. */
+      if (!max_nbcores) {
+        hwloc_debug("cannot detect core/thread IDs from 0x04 without a valid max of cores\n");
+      } else {
         max_nbthreads = legacy_max_log_proc / max_nbcores;
-      hwloc_debug("thus %u threads\n", max_nbthreads);
+        hwloc_debug("found %u threads max\n", max_nbthreads);
+        if (!max_nbthreads) {
+          hwloc_debug("cannot detect core/thread IDs from 0x04 without a valid max of threads\n");
+        } else {
           threadid = legacy_log_proc_id % max_nbthreads;
           infos->ids[CORE] = legacy_log_proc_id / max_nbthreads;
           hwloc_debug("this is thread %u of core %u\n", threadid, infos->ids[CORE]);
         }
       }
+    }
+  }
 
   if (highest_cpuid >= 0x1a && has_hybrid(features)) {
     /* Get hybrid cpu information from cpuid 0x1a */
@@ -775,13 +790,19 @@ static void look_proc(struct hwloc_backend *backend, struct procinfo *infos, uns
 
     } else if (cpuid_type == amd) {
       /* AMD quirks */
-      if (infos->cpufamilynumber == 0x17
-	  && cache->level == 3 && cache->nbthreads_sharing == 6) {
-	/* AMD family 0x17 always shares L3 between 8 APIC ids,
-	 * even when only 6 APIC ids are enabled and reported in nbthreads_sharing
-	 * (on 24-core CPUs).
+      if (infos->cpufamilynumber >= 0x17 && cache->level == 3) {
+	/* AMD family 0x19 always shares L3 between 16 APIC ids (8 HT cores).
+         * while Family 0x17 shares between 8 APIC ids (4 HT cores).
+         * But many models have less APIC ids enabled and reported in nbthreads_sharing.
+         * It means we must round-up nbthreads_sharing to the nearest power of 2
+         * before computing cacheid.
 	 */
-	cache->cacheid = infos->apicid / 8;
+        unsigned nbapics_sharing = cache->nbthreads_sharing;
+        if (nbapics_sharing & (nbapics_sharing-1))
+          /* not a power of two, round-up */
+          nbapics_sharing = 1U<<(1+hwloc_ffsl(nbapics_sharing));
+
+	cache->cacheid = infos->apicid / nbapics_sharing;
 
       } else if (infos->cpufamilynumber== 0x10 && infos->cpumodelnumber == 0x9
 	  && cache->level == 3
@@ -807,7 +828,7 @@ static void look_proc(struct hwloc_backend *backend, struct procinfo *infos, uns
       } else if (infos->cpufamilynumber == 0x15
 		 && (infos->cpumodelnumber == 0x1 /* Bulldozer */ || infos->cpumodelnumber == 0x2 /* Piledriver */)
 		 && cache->level == 3 && cache->nbthreads_sharing == 6) {
-	/* AMD Bulldozer and Piledriver 12-core processors have same APIC ids as Magny-Cours below,
+	/* AMD Bulldozer and Piledriver 12-core processors have same APIC ids as Magny-Cours above,
 	 * but we can't merge the checks because the original nbthreads_sharing must be exactly 6 here.
 	 */
 	cache->cacheid = (infos->apicid % legacy_max_log_proc) / cache->nbthreads_sharing /* cacheid within the package */
@@ -1231,6 +1252,18 @@ static void summarize(struct hwloc_backend *backend, struct procinfo *infos, uns
 	    }
 	  }
 	  cache = hwloc_alloc_setup_object(topology, otype, HWLOC_UNKNOWN_INDEX);
+          /* We don't specify the os_index of caches because we want to be
+           * 100% sure they are identical to what the Linux kernel reports
+           * (so that things like resctrl work).
+           * However, vendor/model-specific quirks in the x86 code above
+           * make this difficult.
+           *
+           * Caveat: if the x86 backend is used on Linux to avoid kernel bugs,
+           * IDs won't be available to resctrl users. But resctrl heavily
+           * relies on the kernel x86 discovery being non-buggy anyway.
+           *
+           * TODO: make this optional? or only disable it on Linux?
+           */
 	  cache->attr->cache.depth = level;
 	  cache->attr->cache.size = infos[i].cache[l].size;
 	  cache->attr->cache.linesize = infos[i].cache[l].linesize;

src/3rdparty/hwloc/src/topology-xml.c

@@ -243,7 +243,7 @@ hwloc__xml_import_object_attr(struct hwloc_topology *topology,
   else if (!strcmp(name, "dont_merge")) {
     unsigned long lvalue = strtoul(value, NULL, 10);
     if (obj->type == HWLOC_OBJ_GROUP)
-      obj->attr->group.dont_merge = lvalue;
+      obj->attr->group.dont_merge = (unsigned char) lvalue;
     else if (hwloc__xml_verbose())
       fprintf(stderr, "%s: ignoring dont_merge attribute for non-group object type\n",
 	      state->global->msgprefix);
@@ -2825,6 +2825,7 @@ hwloc__xml_v1export_object_with_memory(hwloc__xml_export_state_t parentstate, hw
     /* child has sibling, we must add a Group around those memory children */
     hwloc_obj_t group = parentstate->global->v1_memory_group;
     parentstate->new_child(parentstate, &gstate, "object");
+    group->parent = obj->parent;
     group->cpuset = obj->cpuset;
     group->complete_cpuset = obj->complete_cpuset;
     group->nodeset = obj->nodeset;

src/3rdparty/hwloc/src/topology.c

@@ -3,6 +3,7 @@
  * Copyright © 2009-2021 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.
  * See COPYING in top-level directory.
  */
 
@@ -52,29 +53,41 @@
 #include <windows.h>
 #endif
 
+
+#ifdef HWLOC_HAVE_LEVELZERO
 /*
  * Define ZES_ENABLE_SYSMAN=1 early so that the LevelZero backend gets Sysman enabled.
+ *
+ * Only if the levelzero was enabled in this build so that we don't enable sysman
+ * for external levelzero users when hwloc doesn't need it. If somebody ever loads
+ * an external levelzero plugin in a hwloc library built without levelzero (unlikely),
+ * he may have to manually set ZES_ENABLE_SYSMAN=1.
+ *
  * Use the constructor if supported and/or the Windows DllMain callback.
  * Do it in the main hwloc library instead of the levelzero component because
  * the latter could be loaded later as a plugin.
  *
  * L0 seems to be using getenv() to check this variable on Windows
  * (at least in the Intel Compute-Runtime of March 2021),
- * so use putenv() to set the variable.
+ * but setenv() doesn't seem to exist on Windows, hence use putenv() to set the variable.
  *
  * For the record, Get/SetEnvironmentVariable() is not exactly the same as getenv/putenv():
  * - getenv() doesn't see what was set with SetEnvironmentVariable()
  * - GetEnvironmentVariable() doesn't see putenv() in cygwin (while it does in MSVC and MinGW).
  * Hence, if L0 ever switches from getenv() to GetEnvironmentVariable(),
  * it will break in cygwin, we'll have to use both putenv() and SetEnvironmentVariable().
- * Hopefully L0 will be provide a way to enable Sysman without env vars before it happens.
+ * Hopefully L0 will provide a way to enable Sysman without env vars before it happens.
  */
-#ifdef HWLOC_HAVE_ATTRIBUTE_CONSTRUCTOR
+#if HWLOC_HAVE_ATTRIBUTE_CONSTRUCTOR
 static void hwloc_constructor(void) __attribute__((constructor));
 static void hwloc_constructor(void)
 {
   if (!getenv("ZES_ENABLE_SYSMAN"))
-    putenv((char *) "ZES_ENABLE_SYSMAN=1");
+#ifdef HWLOC_WIN_SYS
+    putenv("ZES_ENABLE_SYSMAN=1");
+#else
+    setenv("ZES_ENABLE_SYSMAN", "1", 1);
+#endif
 }
 #endif
 #ifdef HWLOC_WIN_SYS
@@ -82,11 +95,14 @@ BOOL WINAPI DllMain(HINSTANCE hinstDLL, DWORD fdwReason, LPVOID lpReserved)
 {
   if (fdwReason == DLL_PROCESS_ATTACH) {
     if (!getenv("ZES_ENABLE_SYSMAN"))
+      /* Windows does not have a setenv, so use putenv. */
       putenv((char *) "ZES_ENABLE_SYSMAN=1");
   }
   return TRUE;
 }
 #endif
+#endif /* HWLOC_HAVE_LEVELZERO */
+
 
 unsigned hwloc_get_api_version(void)
 {
@@ -1901,6 +1917,9 @@ hwloc_topology_alloc_group_object(struct hwloc_topology *topology)
 static void hwloc_propagate_symmetric_subtree(hwloc_topology_t topology, hwloc_obj_t root);
 static void propagate_total_memory(hwloc_obj_t obj);
 static void hwloc_set_group_depth(hwloc_topology_t topology);
+static void hwloc_connect_children(hwloc_obj_t parent);
+static int hwloc_connect_levels(hwloc_topology_t topology);
+static int hwloc_connect_special_levels(hwloc_topology_t topology);
 
 hwloc_obj_t
 hwloc_topology_insert_group_object(struct hwloc_topology *topology, hwloc_obj_t obj)
@@ -2474,13 +2493,26 @@ hwloc_compare_levels_structure(hwloc_topology_t topology, unsigned i)
   return 0;
 }
 
-/* return > 0 if any level was removed, which means reconnect is needed */
-static void
+/* return > 0 if any level was removed.
+ * performs its own reconnect internally if needed
+ */
+static int
 hwloc_filter_levels_keep_structure(hwloc_topology_t topology)
 {
   unsigned i, j;
   int res = 0;
 
+  if (topology->modified) {
+    /* WARNING: hwloc_topology_reconnect() is duplicated partially here
+     * and at the end of this function:
+     * - we need normal levels before merging.
+     * - and we'll need to update special levels after merging.
+     */
+    hwloc_connect_children(topology->levels[0][0]);
+    if (hwloc_connect_levels(topology) < 0)
+      return -1;
+  }
+
   /* start from the bottom since we'll remove intermediate levels */
   for(i=topology->nb_levels-1; i>0; i--) {
     int replacechild = 0, replaceparent = 0;
@@ -2646,6 +2678,22 @@ hwloc_filter_levels_keep_structure(hwloc_topology_t topology)
 	topology->type_depth[type] = HWLOC_TYPE_DEPTH_MULTIPLE;
     }
   }
+
+
+  if (res > 0 || topology-> modified) {
+    /* WARNING: hwloc_topology_reconnect() is duplicated partially here
+     * and at the beginning of this function.
+     * If we merged some levels, some child+parent special children lisst
+     * may have been merged, hence specials level might need reordering,
+     * So reconnect special levels only here at the end
+     * (it's not needed at the beginning of this function).
+     */
+    if (hwloc_connect_special_levels(topology) < 0)
+      return -1;
+    topology->modified = 0;
+  }
+
+  return 0;
 }
 
 static void
@@ -2963,9 +3011,9 @@ hwloc_list_special_objects(hwloc_topology_t topology, hwloc_obj_t obj)
   }
 }
 
-/* Build I/O levels */
+/* Build Memory, I/O and Misc levels */
 static int
-hwloc_connect_io_misc_levels(hwloc_topology_t topology)
+hwloc_connect_special_levels(hwloc_topology_t topology)
 {
   unsigned i;
 
@@ -3176,6 +3224,10 @@ hwloc_connect_levels(hwloc_topology_t topology)
 int
 hwloc_topology_reconnect(struct hwloc_topology *topology, unsigned long flags)
 {
+  /* WARNING: when updating this function, the replicated code must
+   * also be updated inside hwloc_filter_levels_keep_structure()
+   */
+
   if (flags) {
     errno = EINVAL;
     return -1;
@@ -3188,7 +3240,7 @@ hwloc_topology_reconnect(struct hwloc_topology *topology, unsigned long flags)
   if (hwloc_connect_levels(topology) < 0)
     return -1;
 
-  if (hwloc_connect_io_misc_levels(topology) < 0)
+  if (hwloc_connect_special_levels(topology) < 0)
     return -1;
 
   topology->modified = 0;
@@ -3529,15 +3581,12 @@ hwloc_discover(struct hwloc_topology *topology,
   }
   hwloc_debug_print_objects(0, topology->levels[0][0]);
 
-  /* Reconnect things after all these changes.
-   * Often needed because of Groups inserted for I/Os.
-   * And required for KEEP_STRUCTURE below.
-   */
-  if (hwloc_topology_reconnect(topology, 0) < 0)
-    return -1;
-
   hwloc_debug("%s", "\nRemoving levels with HWLOC_TYPE_FILTER_KEEP_STRUCTURE\n");
-  hwloc_filter_levels_keep_structure(topology);
+  if (hwloc_filter_levels_keep_structure(topology) < 0)
+    return -1;
+  /* takes care of reconnecting children/levels internally,
+   * because it needs normal levels.
+   * and it's often needed below because of Groups inserted for I/Os anyway */
   hwloc_debug_print_objects(0, topology->levels[0][0]);
 
   /* accumulate children memory in total_memory fields (only once parent is set) */
@@ -4360,14 +4409,13 @@ hwloc_topology_restrict(struct hwloc_topology *topology, hwloc_const_bitmap_t se
   hwloc_bitmap_free(droppedcpuset);
   hwloc_bitmap_free(droppednodeset);
 
-  if (hwloc_topology_reconnect(topology, 0) < 0)
+  if (hwloc_filter_levels_keep_structure(topology) < 0) /* takes care of reconnecting internally */
     goto out;
 
   /* some objects may have disappeared, we need to update distances objs arrays */
   hwloc_internal_distances_invalidate_cached_objs(topology);
   hwloc_internal_memattrs_need_refresh(topology);
 
-  hwloc_filter_levels_keep_structure(topology);
   hwloc_propagate_symmetric_subtree(topology, topology->levels[0][0]);
   propagate_total_memory(topology->levels[0][0]);
   hwloc_internal_cpukinds_restrict(topology);

src/Summary.cpp

@@ -1,12 +1,6 @@
 /* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2019 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2021 XMRig       <support@xmrig.com>
+ * Copyright (c) 2018-2022 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2022 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
@@ -22,7 +16,6 @@
  *   along with this program. If not, see <http://www.gnu.org/licenses/>.
  */
 
-
 #include <cinttypes>
 #include <cstdio>
 #include <uv.h>
@@ -158,7 +151,7 @@ static void print_memory(const Config *config)
                        "", memory.id().data(), memory.size() / oneGiB, memory.type(), memory.speed() / 1000000ULL, memory.product().data());
         }
         else if (printEmpty) {
-            Log::print(WHITE_BOLD("   %-13s") "%s: " BLACK_BOLD("<empty>"), "", memory.slot().data());
+            Log::print(WHITE_BOLD("   %-13s") "%s: " BLACK_BOLD("<empty>"), "", memory.id().data());
         }
     }
 

src/Summary.h

@@ -1,12 +1,6 @@
 /* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2021 XMRig       <https://github.com/xmrig>, <support@xmrig.com>
+ * Copyright (c) 2018-2022 SChernykh   <https://github.com/SChernykh>
+ * Copyright (c) 2016-2022 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

src/backend/common/WorkerJob.h

@@ -30,6 +30,7 @@
 
 
 #include "base/net/stratum/Job.h"
+#include "base/tools/Alignment.h"
 #include "crypto/common/Nonce.h"
 
 
@@ -77,7 +78,7 @@ public:
         }
         else {
             for (size_t i = 0; i < N; ++i) {
-                *nonce(i) += roundSize;
+                writeUnaligned(nonce(i), readUnaligned(nonce(i)) + roundSize);
             }
         }
 
@@ -108,7 +109,7 @@ private:
     }
 
 
-    alignas(16) uint8_t m_blobs[2][Job::kMaxBlobSize * N]{};
+    alignas(8) uint8_t m_blobs[2][Job::kMaxBlobSize * N]{};
     Job m_jobs[2];
     uint32_t m_rounds[2] = { 0, 0 };
     uint64_t m_nonce_mask[2] = { 0, 0 };
@@ -136,11 +137,11 @@ inline bool xmrig::WorkerJob<1>::nextRound(uint32_t rounds, uint32_t roundSize)
             return false;
         }
         if (nonceSize() == sizeof(uint64_t)) {
-            m_jobs[index()].nonce()[1] = n[1];
+            writeUnaligned(m_jobs[index()].nonce() + 1, readUnaligned(n + 1));
         }
     }
     else {
-        *n += roundSize;
+        writeUnaligned(n, readUnaligned(n) + roundSize);
     }
 
     return true;

src/backend/cpu/CpuBackend.cpp

@@ -78,6 +78,7 @@ public:
         m_hugePages.reset();
         m_memory       = memory;
         m_started      = 0;
+        m_totalStarted = 0;
         m_errors       = 0;
         m_threads      = threads.size();
         m_ways         = 0;
@@ -435,10 +436,6 @@ rapidjson::Value xmrig::CpuBackend::toJSON(rapidjson::Document &doc) const
     out.AddMember("argon2-impl", argon2::Impl::name().toJSON(), allocator);
 #   endif
 
-#   ifdef XMRIG_ALGO_ASTROBWT
-    out.AddMember("astrobwt-max-size", cpu.astrobwtMaxSize(), allocator);
-#   endif
-
     out.AddMember("hugepages", d_ptr->hugePages(2, doc), allocator);
     out.AddMember("memory",    static_cast<uint64_t>(d_ptr->algo.isValid() ? (d_ptr->ways() * d_ptr->algo.l3()) : 0), allocator);
 

src/backend/cpu/CpuConfig.cpp

@@ -45,11 +45,6 @@ const char *CpuConfig::kAsm                 = "asm";
 const char *CpuConfig::kArgon2Impl          = "argon2-impl";
 #endif
 
-#ifdef XMRIG_ALGO_ASTROBWT
-const char *CpuConfig::kAstroBWTMaxSize     = "astrobwt-max-size";
-const char *CpuConfig::kAstroBWTAVX2        = "astrobwt-avx2";
-#endif
-
 
 extern template class Threads<CpuThreads>;
 
@@ -89,11 +84,6 @@ rapidjson::Value xmrig::CpuConfig::toJSON(rapidjson::Document &doc) const
     obj.AddMember(StringRef(kArgon2Impl), m_argon2Impl.toJSON(), allocator);
 #   endif
 
-#   ifdef XMRIG_ALGO_ASTROBWT
-    obj.AddMember(StringRef(kAstroBWTMaxSize),  m_astrobwtMaxSize, allocator);
-    obj.AddMember(StringRef(kAstroBWTAVX2),     m_astrobwtAVX2, allocator);
-#   endif
-
     m_threads.toJSON(obj, doc);
 
     return obj;
@@ -158,24 +148,6 @@ void xmrig::CpuConfig::read(const rapidjson::Value &value)
         m_argon2Impl = Json::getString(value, kArgon2Impl);
 #       endif
 
-#       ifdef XMRIG_ALGO_ASTROBWT
-        const auto& astroBWTMaxSize = Json::getValue(value, kAstroBWTMaxSize);
-        if (astroBWTMaxSize.IsNull() || !astroBWTMaxSize.IsInt()) {
-            m_shouldSave = true;
-        }
-        else {
-            m_astrobwtMaxSize = std::min(std::max(astroBWTMaxSize.GetInt(), 400), 1200);
-        }
-
-        const auto& astroBWTAVX2 = Json::getValue(value, kAstroBWTAVX2);
-        if (astroBWTAVX2.IsNull() || !astroBWTAVX2.IsBool()) {
-            m_shouldSave = true;
-        }
-        else {
-            m_astrobwtAVX2 = astroBWTAVX2.GetBool();
-        }
-#       endif
-
         m_threads.read(value);
 
         generate();
@@ -206,7 +178,6 @@ void xmrig::CpuConfig::generate()
     count += xmrig::generate<Algorithm::CN_FEMTO>(m_threads, m_limit);
     count += xmrig::generate<Algorithm::RANDOM_X>(m_threads, m_limit);
     count += xmrig::generate<Algorithm::ARGON2>(m_threads, m_limit);
-    count += xmrig::generate<Algorithm::ASTROBWT>(m_threads, m_limit);
     count += xmrig::generate<Algorithm::GHOSTRIDER>(m_threads, m_limit);
 
     m_shouldSave |= count > 0;

src/backend/cpu/CpuConfig.h

@@ -56,11 +56,6 @@ public:
     static const char *kArgon2Impl;
 #   endif
 
-#   ifdef XMRIG_ALGO_ASTROBWT
-    static const char *kAstroBWTMaxSize;
-    static const char *kAstroBWTAVX2;
-#   endif
-
     CpuConfig() = default;
 
     bool isHwAES() const;
@@ -69,7 +64,6 @@ public:
     std::vector<CpuLaunchData> get(const Miner *miner, const Algorithm &algorithm) const;
     void read(const rapidjson::Value &value);
 
-    inline bool astrobwtAVX2() const                    { return m_astrobwtAVX2; }
     inline bool isEnabled() const                       { return m_enabled; }
     inline bool isHugePages() const                     { return m_hugePageSize > 0; }
     inline bool isHugePagesJit() const                  { return m_hugePagesJit; }
@@ -78,7 +72,6 @@ public:
     inline const Assembly &assembly() const             { return m_assembly; }
     inline const String &argon2Impl() const             { return m_argon2Impl; }
     inline const Threads<CpuThreads> &threads() const   { return m_threads; }
-    inline int astrobwtMaxSize() const                  { return m_astrobwtMaxSize; }
     inline int priority() const                         { return m_priority; }
     inline size_t hugePageSize() const                  { return m_hugePageSize * 1024U; }
     inline uint32_t limit() const                       { return m_limit; }
@@ -96,12 +89,10 @@ private:
 
     AesMode m_aes           = AES_AUTO;
     Assembly m_assembly;
-    bool m_astrobwtAVX2     = false;
     bool m_enabled          = true;
     bool m_hugePagesJit     = false;
     bool m_shouldSave       = false;
     bool m_yield            = true;
-    int m_astrobwtMaxSize   = 550;
     int m_memoryPool        = 0;
     int m_priority          = -1;
     size_t m_hugePageSize   = kDefaultHugePageSizeKb;

src/backend/cpu/CpuConfig_gen.h

@@ -153,14 +153,6 @@ size_t inline generate<Algorithm::ARGON2>(Threads<CpuThreads> &threads, uint32_t
 #endif
 
 
-#ifdef XMRIG_ALGO_ASTROBWT
-template<>
-size_t inline generate<Algorithm::ASTROBWT>(Threads<CpuThreads>& threads, uint32_t limit)
-{
-    return generate(Algorithm::kASTROBWT, threads, Algorithm::ASTROBWT_DERO, limit);
-}
-#endif
-
 #ifdef XMRIG_ALGO_GHOSTRIDER
 template<>
 size_t inline generate<Algorithm::GHOSTRIDER>(Threads<CpuThreads>& threads, uint32_t limit)

src/backend/cpu/CpuLaunchData.cpp

@@ -35,11 +35,9 @@
 xmrig::CpuLaunchData::CpuLaunchData(const Miner *miner, const Algorithm &algorithm, const CpuConfig &config, const CpuThread &thread, size_t threads, const std::vector<int64_t>& affinities) :
     algorithm(algorithm),
     assembly(config.assembly()),
-    astrobwtAVX2(config.astrobwtAVX2()),
     hugePages(config.isHugePages()),
     hwAES(config.isHwAES()),
     yield(config.isYield()),
-    astrobwtMaxSize(config.astrobwtMaxSize()),
     priority(config.priority()),
     affinity(thread.affinity()),
     miner(miner),

src/backend/cpu/CpuLaunchData.h

@@ -58,11 +58,9 @@ public:
 
     const Algorithm algorithm;
     const Assembly assembly;
-    const bool astrobwtAVX2;
     const bool hugePages;
     const bool hwAES;
     const bool yield;
-    const int astrobwtMaxSize;
     const int priority;
     const int64_t affinity;
     const Miner *miner;

src/backend/cpu/CpuWorker.cpp

@@ -23,6 +23,7 @@
 
 #include "backend/cpu/Cpu.h"
 #include "backend/cpu/CpuWorker.h"
+#include "base/tools/Alignment.h"
 #include "base/tools/Chrono.h"
 #include "core/config/Config.h"
 #include "core/Miner.h"
@@ -43,11 +44,6 @@
 #endif
 
 
-#ifdef XMRIG_ALGO_ASTROBWT
-#   include "crypto/astrobwt/AstroBWT.h"
-#endif
-
-
 #ifdef XMRIG_FEATURE_BENCHMARK
 #   include "backend/common/benchmark/BenchState.h"
 #endif
@@ -72,19 +68,20 @@ xmrig::CpuWorker<N>::CpuWorker(size_t id, const CpuLaunchData &data) :
     Worker(id, data.affinity, data.priority),
     m_algorithm(data.algorithm),
     m_assembly(data.assembly),
-    m_astrobwtAVX2(data.astrobwtAVX2),
     m_hwAES(data.hwAES),
     m_yield(data.yield),
     m_av(data.av()),
-    m_astrobwtMaxSize(data.astrobwtMaxSize * 1000),
     m_miner(data.miner),
     m_threads(data.threads),
     m_ctx()
 {
 #   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
@@ -100,7 +97,7 @@ xmrig::CpuWorker<N>::CpuWorker(size_t id, const CpuLaunchData &data) :
     }
 
 #   ifdef XMRIG_ALGO_GHOSTRIDER
-    m_ghHelper = ghostrider::create_helper_thread(affinity(), data.affinities);
+    m_ghHelper = ghostrider::create_helper_thread(affinity(), data.priority, data.affinities);
 #   endif
 }
 
@@ -134,7 +131,7 @@ void xmrig::CpuWorker<N>::allocateRandomX_VM()
     RxDataset *dataset = Rx::dataset(m_job.currentJob(), node());
 
     while (dataset == nullptr) {
-        std::this_thread::sleep_for(std::chrono::milliseconds(200));
+        std::this_thread::sleep_for(std::chrono::milliseconds(20));
 
         if (Nonce::sequence(Nonce::CPU) == 0) {
             return;
@@ -222,12 +219,6 @@ bool xmrig::CpuWorker<N>::selfTest()
     }
 #   endif
 
-#   ifdef XMRIG_ALGO_ASTROBWT
-    if (m_algorithm.family() == Algorithm::ASTROBWT) {
-        return verify(Algorithm::ASTROBWT_DERO, astrobwt_dero_test_out);
-    }
-#   endif
-
     return false;
 }
 
@@ -246,7 +237,7 @@ void xmrig::CpuWorker<N>::start()
     while (Nonce::sequence(Nonce::CPU) > 0) {
         if (Nonce::isPaused()) {
             do {
-                std::this_thread::sleep_for(std::chrono::milliseconds(200));
+                std::this_thread::sleep_for(std::chrono::milliseconds(20));
             }
             while (Nonce::isPaused() && Nonce::sequence(Nonce::CPU) > 0);
 
@@ -271,7 +262,7 @@ void xmrig::CpuWorker<N>::start()
 
             uint32_t current_job_nonces[N];
             for (size_t i = 0; i < N; ++i) {
-                current_job_nonces[i] = *m_job.nonce(i);
+                current_job_nonces[i] = readUnaligned(m_job.nonce(i));
             }
 
 #           ifdef XMRIG_FEATURE_BENCHMARK
@@ -317,14 +308,6 @@ void xmrig::CpuWorker<N>::start()
             {
                 switch (job.algorithm().family()) {
 
-#               ifdef XMRIG_ALGO_ASTROBWT
-                case Algorithm::ASTROBWT:
-                    if (!astrobwt::astrobwt_dero(m_job.blob(), job.size(), m_ctx[0]->memory, m_hash, m_astrobwtMaxSize, m_astrobwtAVX2)) {
-                        valid = false;
-                    }
-                    break;
-#               endif
-
 #               ifdef XMRIG_ALGO_GHOSTRIDER
                 case Algorithm::GHOSTRIDER:
                     if (N == 8) {

src/backend/cpu/CpuWorker.h

@@ -55,7 +55,7 @@ public:
     size_t threads() const override
     {
 #       ifdef XMRIG_ALGO_GHOSTRIDER
-        return m_ghHelper ? 2 : 1;
+        return ((m_algorithm.family() == Algorithm::GHOSTRIDER) && m_ghHelper) ? 2 : 1;
 #       else
         return 1;
 #       endif
@@ -83,14 +83,12 @@ private:
     void allocateCnCtx();
     void consumeJob();
 
-    alignas(16) uint8_t m_hash[N * 32]{ 0 };
+    alignas(8) uint8_t m_hash[N * 32]{ 0 };
     const Algorithm m_algorithm;
     const Assembly m_assembly;
-    const bool m_astrobwtAVX2;
     const bool m_hwAES;
     const bool m_yield;
     const CnHash::AlgoVariant m_av;
-    const int m_astrobwtMaxSize;
     const Miner *m_miner;
     const size_t m_threads;
     cryptonight_ctx *m_ctx[N];

src/backend/cpu/interfaces/ICpuInfo.h

@@ -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,

src/backend/cpu/platform/BasicCpuInfo.cpp

@@ -30,6 +30,12 @@
 #endif
 
 
+#include "crypto/cn/CryptoNight_monero.h"
+#ifdef XMRIG_VAES
+#   include "crypto/cn/CryptoNight_x86_vaes.h"
+#endif
+
+
 #include "backend/cpu/platform/BasicCpuInfo.h"
 #include "3rdparty/rapidjson/document.h"
 #include "crypto/common/Assembly.h"
@@ -58,7 +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
@@ -140,7 +146,7 @@ static inline bool has_osxsave()    { return has_feature(PROCESSOR_INFO,
 static inline bool has_aes_ni()     { return has_feature(PROCESSOR_INFO,        ECX_Reg, 1 << 25); }
 static inline bool has_avx()        { return has_feature(PROCESSOR_INFO,        ECX_Reg, 1 << 28) && has_osxsave() && has_xcr_avx(); }
 static inline bool has_avx2()       { return has_feature(EXTENDED_FEATURES,     EBX_Reg, 1 << 5) && has_osxsave() && has_xcr_avx(); }
-static inline bool has_vaes()       { return has_feature(EXTENDED_FEATURES,     ECX_Reg, 1 << 9); }
+static inline bool has_vaes()       { return has_feature(EXTENDED_FEATURES,     ECX_Reg, 1 << 9) && has_osxsave() && has_xcr_avx(); }
 static inline bool has_avx512f()    { return has_feature(EXTENDED_FEATURES,     EBX_Reg, 1 << 16) && has_osxsave() && has_xcr_avx512(); }
 static inline bool has_bmi2()       { return has_feature(EXTENDED_FEATURES,     EBX_Reg, 1 << 8); }
 static inline bool has_pdpe1gb()    { return has_feature(PROCESSOR_EXT_INFO,    EDX_Reg, 1 << 26); }
@@ -244,8 +250,14 @@ xmrig::BasicCpuInfo::BasicCpuInfo() :
                     break;
 
                 case 0x19:
+                    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:
@@ -294,6 +306,9 @@ xmrig::BasicCpuInfo::BasicCpuInfo() :
         }
     }
 #   endif
+
+    cn_sse41_enabled = has(FLAG_SSE41);
+    cn_vaes_enabled = has(FLAG_VAES);
 }
 
 
@@ -353,16 +368,6 @@ xmrig::CpuThreads xmrig::BasicCpuInfo::threads(const Algorithm &algorithm, uint3
     }
 #   endif
 
-#   ifdef XMRIG_ALGO_ASTROBWT
-    if (f == Algorithm::ASTROBWT) {
-        CpuThreads threads;
-        for (size_t i = 0; i < count; ++i) {
-            threads.add(i, 0);
-        }
-        return threads;
-    }
-#   endif
-
 #   ifdef XMRIG_ALGO_GHOSTRIDER
     if (f == Algorithm::GHOSTRIDER) {
         return CpuThreads(std::max<size_t>(count / 2, 1), 8);

src/backend/cpu/platform/HwlocCpuInfo.cpp

@@ -318,13 +318,6 @@ void xmrig::HwlocCpuInfo::processTopLevelCache(hwloc_obj_t cache, const Algorith
     size_t scratchpad       = algorithm.l3();
     uint32_t intensity      = algorithm.maxIntensity() == 1 ? 0 : 1;
 
-#   ifdef XMRIG_ALGO_ASTROBWT
-    if (algorithm == Algorithm::ASTROBWT_DERO) {
-        // Use fake low value to force usage of all available cores for AstroBWT (taking 'limit' into account)
-        scratchpad = 16 * 1024;
-    }
-#   endif
-
     if (cache->attr->cache.depth == 3) {
         for (size_t i = 0; i < cache->arity; ++i) {
             hwloc_obj_t l2 = cache->children[i];

src/backend/cuda/CudaBackend.cpp

@@ -40,11 +40,6 @@
 #include "core/Controller.h"
 
 
-#ifdef XMRIG_ALGO_ASTROBWT
-#   include "backend/cuda/runners/CudaAstroBWTRunner.h"
-#endif
-
-
 #ifdef XMRIG_ALGO_KAWPOW
 #   include "crypto/kawpow/KPCache.h"
 #   include "crypto/kawpow/KPHash.h"
@@ -220,12 +215,6 @@ public:
 
         size_t algo_l3 = algo.l3();
 
-#       ifdef XMRIG_ALGO_ASTROBWT
-        if (algo.family() == Algorithm::ASTROBWT) {
-            algo_l3 = CudaAstroBWTRunner::BWT_DATA_STRIDE * 17 + 1024;
-        }
-#       endif
-
         size_t i = 0;
         for (const auto &data : threads) {
             size_t mem_used = (data.thread.threads() * data.thread.blocks()) * algo_l3 / oneMiB;

src/backend/cuda/CudaConfig.cpp

@@ -174,7 +174,6 @@ void xmrig::CudaConfig::generate()
     count += xmrig::generate<Algorithm::CN_PICO>(m_threads, devices);
     count += xmrig::generate<Algorithm::CN_FEMTO>(m_threads, devices);
     count += xmrig::generate<Algorithm::RANDOM_X>(m_threads, devices);
-    count += xmrig::generate<Algorithm::ASTROBWT>(m_threads, devices);
     count += xmrig::generate<Algorithm::KAWPOW>(m_threads, devices);
 
     generated    = true;

src/backend/cuda/CudaConfig_gen.h

@@ -135,15 +135,6 @@ size_t inline generate<Algorithm::RANDOM_X>(Threads<CudaThreads> &threads, const
 #endif
 
 
-#ifdef XMRIG_ALGO_ASTROBWT
-template<>
-size_t inline generate<Algorithm::ASTROBWT>(Threads<CudaThreads> &threads, const std::vector<CudaDevice> &devices)
-{
-    return generate(Algorithm::kASTROBWT, threads, Algorithm::ASTROBWT_DERO, devices);
-}
-#endif
-
-
 #ifdef XMRIG_ALGO_KAWPOW
 template<>
 size_t inline generate<Algorithm::KAWPOW>(Threads<CudaThreads> &threads, const std::vector<CudaDevice> &devices)

src/backend/cuda/CudaWorker.cpp

@@ -22,6 +22,7 @@
 #include "backend/cuda/runners/CudaCnRunner.h"
 #include "backend/cuda/wrappers/CudaDevice.h"
 #include "base/io/log/Log.h"
+#include "base/tools/Alignment.h"
 #include "base/tools/Chrono.h"
 #include "core/Miner.h"
 #include "crypto/common/Nonce.h"
@@ -33,11 +34,6 @@
 #endif
 
 
-#ifdef XMRIG_ALGO_ASTROBWT
-#   include "backend/cuda/runners/CudaAstroBWTRunner.h"
-#endif
-
-
 #ifdef XMRIG_ALGO_KAWPOW
 #   include "backend/cuda/runners/CudaKawPowRunner.h"
 #endif
@@ -75,12 +71,6 @@ xmrig::CudaWorker::CudaWorker(size_t id, const CudaLaunchData &data) :
     case Algorithm::ARGON2:
         break;
 
-    case Algorithm::ASTROBWT:
-#       ifdef XMRIG_ALGO_ASTROBWT
-        m_runner = new CudaAstroBWTRunner(id, data);
-#       endif
-        break;
-
     case Algorithm::KAWPOW:
 #       ifdef XMRIG_ALGO_KAWPOW
         m_runner = new CudaKawPowRunner(id, data);
@@ -152,7 +142,7 @@ void xmrig::CudaWorker::start()
             uint32_t foundNonce[16] = { 0 };
             uint32_t foundCount     = 0;
 
-            if (!m_runner->run(*m_job.nonce(), &foundCount, foundNonce)) {
+            if (!m_runner->run(readUnaligned(m_job.nonce()), &foundCount, foundNonce)) {
                 return;
             }
 

src/backend/cuda/cuda.cmake

@@ -54,11 +54,6 @@ if (WITH_CUDA)
        list(APPEND SOURCES_BACKEND_CUDA src/backend/cuda/runners/CudaRxRunner.cpp)
    endif()
 
-   if (WITH_ASTROBWT)
-       list(APPEND HEADERS_BACKEND_CUDA src/backend/cuda/runners/CudaAstroBWTRunner.h)
-       list(APPEND SOURCES_BACKEND_CUDA src/backend/cuda/runners/CudaAstroBWTRunner.cpp)
-   endif()
-
    if (WITH_KAWPOW)
        list(APPEND HEADERS_BACKEND_CUDA src/backend/cuda/runners/CudaKawPowRunner.h)
        list(APPEND SOURCES_BACKEND_CUDA src/backend/cuda/runners/CudaKawPowRunner.cpp)

src/backend/cuda/runners/CudaAstroBWTRunner.cpp

@@ -1,75 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-
-#include "backend/cuda/runners/CudaAstroBWTRunner.h"
-#include "backend/cuda/CudaLaunchData.h"
-#include "backend/cuda/wrappers/CudaLib.h"
-#include "base/net/stratum/Job.h"
-
-
-constexpr uint32_t xmrig::CudaAstroBWTRunner::BWT_DATA_STRIDE;
-
-
-xmrig::CudaAstroBWTRunner::CudaAstroBWTRunner(size_t index, const CudaLaunchData &data) :
-    CudaBaseRunner(index, data)
-{
-    m_intensity = m_data.thread.threads() * m_data.thread.blocks();
-    m_intensity -= m_intensity % 32;
-}
-
-
-bool xmrig::CudaAstroBWTRunner::run(uint32_t startNonce, uint32_t *rescount, uint32_t *resnonce)
-{
-    return callWrapper(CudaLib::astroBWTHash(m_ctx, startNonce, m_target, rescount, resnonce));
-}
-
-
-bool xmrig::CudaAstroBWTRunner::set(const Job &job, uint8_t *blob)
-{
-    if (!CudaBaseRunner::set(job, blob)) {
-        return false;
-    }
-
-    return callWrapper(CudaLib::astroBWTPrepare(m_ctx, static_cast<uint32_t>(m_intensity)));
-}
-
-
-size_t xmrig::CudaAstroBWTRunner::roundSize() const
-{
-    constexpr uint32_t STAGE1_SIZE = 147253;
-    constexpr uint32_t STAGE1_DATA_STRIDE = (STAGE1_SIZE + 256 + 255) & ~255U;
-
-    const uint32_t BATCH2_SIZE = m_intensity;
-    const uint32_t BWT_ALLOCATION_SIZE = BATCH2_SIZE * BWT_DATA_STRIDE;
-    const uint32_t BATCH1_SIZE = (BWT_ALLOCATION_SIZE / STAGE1_DATA_STRIDE) & ~255U;
-
-    return BATCH1_SIZE;
-}
-
-
-size_t xmrig::CudaAstroBWTRunner::processedHashes() const
-{
-    return CudaLib::deviceInt(m_ctx, CudaLib::DeviceAstroBWTProcessedHashes);
-}

src/backend/cuda/runners/CudaAstroBWTRunner.h

@@ -1,59 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef XMRIG_CUDAASTROBWTRUNNER_H
-#define XMRIG_CUDAASTROBWTRUNNER_H
-
-
-#include "backend/cuda/runners/CudaBaseRunner.h"
-
-
-namespace xmrig {
-
-
-class CudaAstroBWTRunner : public CudaBaseRunner
-{
-public:
-    static constexpr uint32_t BWT_DATA_MAX_SIZE = 560 * 1024 - 256;
-    static constexpr uint32_t BWT_DATA_STRIDE = (BWT_DATA_MAX_SIZE + 256 + 255) & ~255U;
-
-    CudaAstroBWTRunner(size_t index, const CudaLaunchData &data);
-
-protected:
-    inline size_t intensity() const override { return m_intensity; }
-    inline size_t roundSize() const override;
-    inline size_t processedHashes() const override;
-
-    bool run(uint32_t startNonce, uint32_t *rescount, uint32_t *resnonce) override;
-    bool set(const Job &job, uint8_t *blob) override;
-
-private:
-    size_t m_intensity  = 0;
-};
-
-
-} /* namespace xmrig */
-
-
-#endif // XMRIG_CUDAASTROBWTRUNNER_H

src/backend/cuda/wrappers/CudaLib.cpp

@@ -50,8 +50,6 @@ static String defaultLoader = "libxmrig-cuda.so";
 
 
 static const char *kAlloc                               = "alloc";
-static const char *kAstroBWTHash                        = "astroBWTHash";
-static const char *kAstroBWTPrepare                     = "astroBWTPrepare";
 static const char *kCnHash                              = "cnHash";
 static const char *kDeviceCount                         = "deviceCount";
 static const char *kDeviceInfo                          = "deviceInfo";
@@ -76,8 +74,6 @@ static const char *kVersion                             = "version";
 
 
 using alloc_t                                           = nvid_ctx * (*)(uint32_t, int32_t, int32_t);
-using astroBWTHash_t                                    = bool (*)(nvid_ctx *, uint32_t, uint64_t, uint32_t *, uint32_t *);
-using astroBWTPrepare_t                                 = bool (*)(nvid_ctx *, uint32_t);
 using cnHash_t                                          = bool (*)(nvid_ctx *, uint32_t, uint64_t, uint64_t, uint32_t *, uint32_t *);
 using deviceCount_t                                     = uint32_t (*)();
 using deviceInfo_t                                      = bool (*)(nvid_ctx *, int32_t, int32_t, uint32_t, int32_t);
@@ -102,8 +98,6 @@ using version_t                                         = uint32_t (*)(Version);
 
 
 static alloc_t pAlloc                                   = nullptr;
-static astroBWTHash_t pAstroBWTHash                     = nullptr;
-static astroBWTPrepare_t pAstroBWTPrepare               = nullptr;
 static cnHash_t pCnHash                                 = nullptr;
 static deviceCount_t pDeviceCount                       = nullptr;
 static deviceInfo_t pDeviceInfo                         = nullptr;
@@ -176,18 +170,6 @@ void xmrig::CudaLib::close()
 }
 
 
-bool xmrig::CudaLib::astroBWTHash(nvid_ctx *ctx, uint32_t startNonce, uint64_t target, uint32_t *rescount, uint32_t *resnonce) noexcept
-{
-    return pAstroBWTHash(ctx, startNonce, target, rescount, resnonce);
-}
-
-
-bool xmrig::CudaLib::astroBWTPrepare(nvid_ctx *ctx, uint32_t batchSize) noexcept
-{
-    return pAstroBWTPrepare(ctx, batchSize);
-}
-
-
 bool xmrig::CudaLib::cnHash(nvid_ctx *ctx, uint32_t startNonce, uint64_t height, uint64_t target, uint32_t *rescount, uint32_t *resnonce)
 {
     return pCnHash(ctx, startNonce, height, target, rescount, resnonce);
@@ -410,8 +392,6 @@ void xmrig::CudaLib::load()
     DLSYM(Release);
     DLSYM(RxHash);
     DLSYM(RxPrepare);
-    DLSYM(AstroBWTHash);
-    DLSYM(AstroBWTPrepare);
     DLSYM(KawPowHash);
     DLSYM(KawPowPrepare_v2);
     DLSYM(KawPowStopHash);

src/backend/cuda/wrappers/CudaLib.h

@@ -56,7 +56,6 @@ public:
         DevicePciDeviceID,
         DevicePciDomainID,
         DeviceDatasetHost,
-        DeviceAstroBWTProcessedHashes,
     };
 
     static bool init(const char *fileName = nullptr);
@@ -67,8 +66,6 @@ public:
     static inline bool isReady() noexcept { return m_ready; }
     static inline const String &loader()  { return m_loader; }
 
-    static bool astroBWTHash(nvid_ctx *ctx, uint32_t startNonce, uint64_t target, uint32_t *rescount, uint32_t *resnonce) noexcept;
-    static bool astroBWTPrepare(nvid_ctx *ctx, uint32_t batchSize) noexcept;
     static bool cnHash(nvid_ctx *ctx, uint32_t startNonce, uint64_t height, uint64_t target, uint32_t *rescount, uint32_t *resnonce);
     static bool deviceInfo(nvid_ctx *ctx, int32_t blocks, int32_t threads, const Algorithm &algorithm, int32_t dataset_host = -1) noexcept;
     static bool deviceInit(nvid_ctx *ctx) noexcept;

src/backend/opencl/OclBackend.cpp

@@ -29,7 +29,6 @@
 #include "backend/opencl/OclConfig.h"
 #include "backend/opencl/OclLaunchData.h"
 #include "backend/opencl/OclWorker.h"
-#include "backend/opencl/runners/OclAstroBWTRunner.h"
 #include "backend/opencl/runners/tools/OclSharedState.h"
 #include "backend/opencl/wrappers/OclContext.h"
 #include "backend/opencl/wrappers/OclLib.h"
@@ -204,12 +203,6 @@ public:
 
         size_t algo_l3 = algo.l3();
 
-#       ifdef XMRIG_ALGO_ASTROBWT
-        if (algo.family() == Algorithm::ASTROBWT) {
-            algo_l3 = OclAstroBWTRunner::BWT_DATA_STRIDE * 17 + 324;
-        }
-#       endif
-
         size_t i = 0;
         for (const auto &data : threads) {
             size_t mem_used = data.thread.intensity() * algo_l3 / oneMiB;

src/backend/opencl/OclConfig.cpp

@@ -214,7 +214,6 @@ void xmrig::OclConfig::generate()
     count += xmrig::generate<Algorithm::CN_PICO>(m_threads, devices);
     count += xmrig::generate<Algorithm::CN_FEMTO>(m_threads, devices);
     count += xmrig::generate<Algorithm::RANDOM_X>(m_threads, devices);
-    count += xmrig::generate<Algorithm::ASTROBWT>(m_threads, devices);
     count += xmrig::generate<Algorithm::KAWPOW>(m_threads, devices);
 
     m_shouldSave = count > 0;

src/backend/opencl/OclConfig_gen.h

@@ -129,15 +129,6 @@ size_t inline generate<Algorithm::RANDOM_X>(Threads<OclThreads> &threads, const
 #endif
 
 
-#ifdef XMRIG_ALGO_ASTROBWT
-template<>
-size_t inline generate<Algorithm::ASTROBWT>(Threads<OclThreads>& threads, const std::vector<OclDevice>& devices)
-{
-    return generate(Algorithm::kASTROBWT, threads, Algorithm::ASTROBWT_DERO, devices);
-}
-#endif
-
-
 #ifdef XMRIG_ALGO_KAWPOW
 template<>
 size_t inline generate<Algorithm::KAWPOW>(Threads<OclThreads>& threads, const std::vector<OclDevice>& devices)

src/backend/opencl/OclThread.cpp

@@ -116,9 +116,7 @@ rapidjson::Value xmrig::OclThread::toJSON(rapidjson::Document &doc) const
 
     out.AddMember(StringRef(kIndex),        index(), allocator);
     out.AddMember(StringRef(kIntensity),    intensity(), allocator);
-    if (!m_fields.test(ASTROBWT_FIELDS)) {
     out.AddMember(StringRef(kWorksize),     worksize(), allocator);
-    }
 
     if (m_fields.test(STRIDED_INDEX_FIELD)) {
         Value si(kArrayType);
@@ -144,7 +142,7 @@ rapidjson::Value xmrig::OclThread::toJSON(rapidjson::Document &doc) const
         out.AddMember(StringRef(kDatasetHost),  isDatasetHost(), allocator);
 #       endif
     }
-    else if (!m_fields.test(ASTROBWT_FIELDS) && !m_fields.test(KAWPOW_FIELDS)) {
+    else if (!m_fields.test(KAWPOW_FIELDS)) {
         out.AddMember(StringRef(kUnroll), unrollFactor(), allocator);
     }
 

src/backend/opencl/OclThread.h

@@ -61,20 +61,6 @@ public:
     }
 #   endif
 
-#   ifdef XMRIG_ALGO_ASTROBWT
-    OclThread(uint32_t index, uint32_t intensity, uint32_t threads) :
-        m_fields(4),
-        m_threads(threads, -1),
-        m_index(index),
-        m_memChunk(0),
-        m_stridedIndex(0),
-        m_unrollFactor(1),
-        m_worksize(1)
-    {
-        setIntensity(intensity);
-    }
-#   endif
-
 #   ifdef XMRIG_ALGO_KAWPOW
     OclThread(uint32_t index, uint32_t intensity, uint32_t worksize, uint32_t threads) :
         m_fields(8),
@@ -113,7 +99,6 @@ private:
     enum Fields {
         STRIDED_INDEX_FIELD,
         RANDOMX_FIELDS,
-        ASTROBWT_FIELDS,
         KAWPOW_FIELDS,
         FIELD_MAX
     };

src/backend/opencl/OclWorker.cpp

@@ -23,6 +23,7 @@
 #include "backend/opencl/runners/tools/OclSharedData.h"
 #include "backend/opencl/runners/tools/OclSharedState.h"
 #include "base/io/log/Log.h"
+#include "base/tools/Alignment.h"
 #include "base/tools/Chrono.h"
 #include "core/Miner.h"
 #include "crypto/common/Nonce.h"
@@ -34,10 +35,6 @@
 #   include "backend/opencl/runners/OclRxVmRunner.h"
 #endif
 
-#ifdef XMRIG_ALGO_ASTROBWT
-#   include "backend/opencl/runners/OclAstroBWTRunner.h"
-#endif
-
 #ifdef XMRIG_ALGO_KAWPOW
 #   include "backend/opencl/runners/OclKawPowRunner.h"
 #endif
@@ -89,12 +86,6 @@ xmrig::OclWorker::OclWorker(size_t id, const OclLaunchData &data) :
 #       endif
         break;
 
-    case Algorithm::ASTROBWT:
-#       ifdef XMRIG_ALGO_ASTROBWT
-        m_runner = new OclAstroBWTRunner(id, data);
-#       endif
-        break;
-
     case Algorithm::KAWPOW:
 #       ifdef XMRIG_ALGO_KAWPOW
         m_runner = new OclKawPowRunner(id, data);
@@ -179,7 +170,7 @@ void xmrig::OclWorker::start()
             const uint64_t t = Chrono::steadyMSecs();
 
             try {
-                m_runner->run(*m_job.nonce(), results);
+                m_runner->run(readUnaligned(m_job.nonce()), results);
             }
             catch (std::exception &ex) {
                 printError(id(), ex.what());

src/backend/opencl/cl/OclSource.cpp

@@ -32,10 +32,6 @@
 #   include "backend/opencl/cl/rx/randomx_cl.h"
 #endif
 
-#ifdef XMRIG_ALGO_ASTROBWT
-#   include "backend/opencl/cl/astrobwt/astrobwt_cl.h"
-#endif
-
 #ifdef XMRIG_ALGO_KAWPOW
 #   include "backend/opencl/cl/kawpow/kawpow_cl.h"
 #   include "backend/opencl/cl/kawpow/kawpow_dag_cl.h"
@@ -50,12 +46,6 @@ const char *xmrig::OclSource::get(const Algorithm &algorithm)
     }
 #   endif
 
-#   ifdef XMRIG_ALGO_ASTROBWT
-    if (algorithm.family() == Algorithm::ASTROBWT) {
-        return astrobwt_cl;
-    }
-#   endif
-
 #   ifdef XMRIG_ALGO_KAWPOW
     if (algorithm.family() == Algorithm::KAWPOW) {
         return kawpow_dag_cl;

src/backend/opencl/cl/astrobwt/BWT.cl

@@ -1,206 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#define STAGE1_SIZE 147253
-
-#define COUNTING_SORT_BITS 11
-#define COUNTING_SORT_SIZE (1 << COUNTING_SORT_BITS)
-
-__attribute__((reqd_work_group_size(BWT_GROUP_SIZE, 1, 1)))
-__kernel void BWT(__global uint8_t* datas, __global uint32_t* data_sizes, uint32_t data_stride, __global uint64_t* indices, __global uint64_t* tmp_indices)
-{
-	const uint32_t tid = get_local_id(0);
-	const uint32_t gid = get_group_id(0);
-
-	__local int counters[COUNTING_SORT_SIZE][2];
-
-	for (uint32_t i = tid; i < COUNTING_SORT_SIZE * 2; i += BWT_GROUP_SIZE)
-		((__local int*)counters)[i] = 0;
-
-	barrier(CLK_LOCAL_MEM_FENCE);
-
-	const uint64_t data_offset = (uint64_t)(gid) * data_stride;
-
-	__global uint8_t* input = datas + data_offset + 128;
-	const uint32_t N = data_sizes[gid] + 1;
-
-	__global uint64_t* p = (__global uint64_t*)(input);
-	volatile __local uint8_t* counters_atomic = (volatile __local uint8_t*)(counters);
-
-	indices += data_offset;
-	tmp_indices += data_offset;
-
-	for (uint32_t i = tid; i < N; i += BWT_GROUP_SIZE)
-	{
-		const uint32_t index = i >> 3;
-		const uint32_t bit_offset = (i & 7) << 3;
-
-		const uint64_t a = p[index];
-		uint64_t b = p[index + 1];
-		if (bit_offset == 0)
-			b = 0;
-
-		uint64_t value = (a >> bit_offset) | (b << (64 - bit_offset));
-
-		uint2 tmp;
-		const uchar4 mask = (uchar4)(3, 2, 1, 0);
-
-		tmp.x = as_uint(shuffle(as_uchar4(as_uint2(value).y), mask));
-		tmp.y = as_uint(shuffle(as_uchar4(as_uint2(value).x), mask));
-
-		value = as_ulong(tmp);
-
-		indices[i] = (value & ((uint64_t)(-1) << 21)) | i;
-		atomic_add((volatile __local int*)(counters_atomic + (((value >> (64 - COUNTING_SORT_BITS * 2)) & (COUNTING_SORT_SIZE - 1)) << 3)), 1);
-		atomic_add((volatile __local int*)(counters_atomic + ((value >> (64 - COUNTING_SORT_BITS)) << 3) + 4), 1);
-	}
-
-	barrier(CLK_LOCAL_MEM_FENCE);
-
-	if (tid == 0)
-	{
-		int t0 = counters[0][0];
-		int t1 = counters[0][1];
-		counters[0][0] = t0 - 1;
-		counters[0][1] = t1 - 1;
-		for (uint32_t i = 1; i < COUNTING_SORT_SIZE; ++i)
-		{
-			t0 += counters[i][0];
-			t1 += counters[i][1];
-			counters[i][0] = t0 - 1;
-			counters[i][1] = t1 - 1;
-		}
-	}
-
-	barrier(CLK_LOCAL_MEM_FENCE);
-
-	for (int i = tid; i < N; i += BWT_GROUP_SIZE)
-	{
-		const uint64_t data = indices[i];
-		const int k = atomic_sub((volatile __local int*)(counters_atomic + (((data >> (64 - COUNTING_SORT_BITS * 2)) & (COUNTING_SORT_SIZE - 1)) << 3)), 1);
-		tmp_indices[k] = data;
-	}
-
-	barrier(CLK_GLOBAL_MEM_FENCE);
-
-	if (tid == 0)
-	{
-		for (int i = N - 1; i >= 0; --i)
-		{
-			const uint64_t data = tmp_indices[i];
-			const int k = atomic_sub((volatile __local int*)(counters_atomic + ((data >> (64 - COUNTING_SORT_BITS)) << 3) + 4), 1);
-			indices[k] = data;
-		}
-	}
-
-	barrier(CLK_GLOBAL_MEM_FENCE);
-
-	const uint32_t N1 = N - 1;
-	__global uint32_t* indices32 = (__global uint32_t*)(indices);
-	for (uint32_t i = tid; i < N1; i += BWT_GROUP_SIZE)
-	{
-		const uint32_t value = indices32[i * 2 + 1] >> (32 - COUNTING_SORT_BITS * 2);
-		if (value != (indices32[i * 2 + 3] >> (32 - COUNTING_SORT_BITS * 2)))
-			continue;
-
-		if ((i > 0) && ((indices32[i * 2 - 1] >> (32 - COUNTING_SORT_BITS * 2)) == value))
-			continue;
-
-		uint32_t i1 = i + 2;
-		while ((i1 < N) && ((indices32[i1 * 2 + 1] >> (32 - COUNTING_SORT_BITS * 2)) == value))
-			++i1;
-
-		for (uint32_t j = i; j < i1; ++j)
-		{
-			uint64_t t = indices[j];
-			for (uint32_t k = j + 1; k < i1; ++k)
-			{
-				if (t > indices[k])
-				{
-					const uint64_t t1 = t;
-					t = indices[k];
-					indices[k] = t1;
-				}
-			}
-			indices[j] = t;
-		}
-	}
-
-	barrier(CLK_GLOBAL_MEM_FENCE);
-
-	--input;
-	__global uint8_t* output = (__global uint8_t*)(tmp_indices);
-	for (int i = tid; i <= N; i += BWT_GROUP_SIZE)
-		output[i] = input[indices[i] & ((1 << 21) - 1)];
-}
-
-__kernel void filter(uint32_t nonce, uint32_t bwt_max_size, __global const uint32_t* hashes, __global uint32_t* filtered_hashes)
-{
-	const uint32_t global_id = get_global_id(0);
-
-	__global const uint32_t* hash = hashes + global_id * (32 / sizeof(uint32_t));
-	const uint32_t stage2_size = STAGE1_SIZE + (*hash & 0xfffff);
-
-	if (stage2_size < bwt_max_size)
-	{
-		const int index = atomic_add((volatile __global int*)(filtered_hashes), 1) * (36 / sizeof(uint32_t)) + 1;
-
-		filtered_hashes[index] = nonce + global_id;
-
-		#pragma unroll 8
-		for (uint32_t i = 0; i < 8; ++i)
-			filtered_hashes[index + i + 1] = hash[i];
-	}
-}
-
-__kernel void prepare_batch2(__global uint32_t* hashes, __global uint32_t* filtered_hashes, __global uint32_t* data_sizes)
-{
-	const uint32_t global_id = get_global_id(0);
-	const uint32_t N = filtered_hashes[0] - get_global_size(0);
-
-	if (global_id == 0)
-		filtered_hashes[0] = N;
-
-	__global uint32_t* hash = hashes + global_id * 8;
-	__global uint32_t* filtered_hash = filtered_hashes + (global_id + N) * 9 + 1;
-
-	const uint32_t stage2_size = STAGE1_SIZE + (filtered_hash[1] & 0xfffff);
-	data_sizes[global_id] = stage2_size;
-
-	#pragma unroll 8
-	for (uint32_t i = 0; i < 8; ++i)
-		hash[i] = filtered_hash[i + 1];
-}
-
-__kernel void find_shares(__global const uint64_t* hashes, __global const uint32_t* filtered_hashes, uint64_t target, __global uint32_t* shares)
-{
-	const uint32_t global_index = get_global_id(0);
-
-	if (hashes[global_index * 4 + 3] < target)
-	{
-		const uint32_t idx = atomic_inc(shares + 0xFF);
-		if (idx < 0xFF)
-			shares[idx] = filtered_hashes[(filtered_hashes[0] + global_index) * 9 + 1];
-	}
-}

src/backend/opencl/cl/astrobwt/astrobwt.cl

@@ -1,35 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-typedef uchar uint8_t;
-typedef ushort uint16_t;
-typedef uint uint32_t;
-typedef ulong uint64_t;
-
-typedef int int32_t;
-typedef long int64_t;
-
-#include "BWT.cl"
-#include "salsa20.cl"
-#include "sha3.cl"

src/backend/opencl/cl/astrobwt/astrobwt_cl.h

@@ -1,399 +0,0 @@
-#pragma once
-
-namespace xmrig {
-
-static const char astrobwt_cl[12489] = {
-    0x74,0x79,0x70,0x65,0x64,0x65,0x66,0x20,0x75,0x63,0x68,0x61,0x72,0x20,0x75,0x69,0x6e,0x74,0x38,0x5f,0x74,0x3b,0x0a,0x74,0x79,0x70,0x65,0x64,0x65,0x66,0x20,0x75,
-    0x73,0x68,0x6f,0x72,0x74,0x20,0x75,0x69,0x6e,0x74,0x31,0x36,0x5f,0x74,0x3b,0x0a,0x74,0x79,0x70,0x65,0x64,0x65,0x66,0x20,0x75,0x69,0x6e,0x74,0x20,0x75,0x69,0x6e,
-    0x74,0x33,0x32,0x5f,0x74,0x3b,0x0a,0x74,0x79,0x70,0x65,0x64,0x65,0x66,0x20,0x75,0x6c,0x6f,0x6e,0x67,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x3b,0x0a,0x74,
-    0x79,0x70,0x65,0x64,0x65,0x66,0x20,0x69,0x6e,0x74,0x20,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x3b,0x0a,0x74,0x79,0x70,0x65,0x64,0x65,0x66,0x20,0x6c,0x6f,0x6e,0x67,
-    0x20,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x3b,0x0a,0x23,0x64,0x65,0x66,0x69,0x6e,0x65,0x20,0x53,0x54,0x41,0x47,0x45,0x31,0x5f,0x53,0x49,0x5a,0x45,0x20,0x31,0x34,
-    0x37,0x32,0x35,0x33,0x0a,0x23,0x64,0x65,0x66,0x69,0x6e,0x65,0x20,0x43,0x4f,0x55,0x4e,0x54,0x49,0x4e,0x47,0x5f,0x53,0x4f,0x52,0x54,0x5f,0x42,0x49,0x54,0x53,0x20,
-    0x31,0x31,0x0a,0x23,0x64,0x65,0x66,0x69,0x6e,0x65,0x20,0x43,0x4f,0x55,0x4e,0x54,0x49,0x4e,0x47,0x5f,0x53,0x4f,0x52,0x54,0x5f,0x53,0x49,0x5a,0x45,0x20,0x28,0x31,
-    0x20,0x3c,0x3c,0x20,0x43,0x4f,0x55,0x4e,0x54,0x49,0x4e,0x47,0x5f,0x53,0x4f,0x52,0x54,0x5f,0x42,0x49,0x54,0x53,0x29,0x0a,0x5f,0x5f,0x61,0x74,0x74,0x72,0x69,0x62,
-    0x75,0x74,0x65,0x5f,0x5f,0x28,0x28,0x72,0x65,0x71,0x64,0x5f,0x77,0x6f,0x72,0x6b,0x5f,0x67,0x72,0x6f,0x75,0x70,0x5f,0x73,0x69,0x7a,0x65,0x28,0x42,0x57,0x54,0x5f,
-    0x47,0x52,0x4f,0x55,0x50,0x5f,0x53,0x49,0x5a,0x45,0x2c,0x31,0x2c,0x31,0x29,0x29,0x29,0x0a,0x5f,0x5f,0x6b,0x65,0x72,0x6e,0x65,0x6c,0x20,0x76,0x6f,0x69,0x64,0x20,
-    0x42,0x57,0x54,0x28,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x38,0x5f,0x74,0x2a,0x20,0x64,0x61,0x74,0x61,0x73,0x2c,0x5f,0x5f,0x67,0x6c,
-    0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x2a,0x20,0x64,0x61,0x74,0x61,0x5f,0x73,0x69,0x7a,0x65,0x73,0x2c,0x75,0x69,0x6e,0x74,0x33,0x32,
-    0x5f,0x74,0x20,0x64,0x61,0x74,0x61,0x5f,0x73,0x74,0x72,0x69,0x64,0x65,0x2c,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,
-    0x2a,0x20,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x2c,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x2a,0x20,0x74,0x6d,0x70,
-    0x5f,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x29,0x0a,0x7b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x74,0x69,0x64,0x3d,0x67,
-    0x65,0x74,0x5f,0x6c,0x6f,0x63,0x61,0x6c,0x5f,0x69,0x64,0x28,0x30,0x29,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x67,
-    0x69,0x64,0x3d,0x67,0x65,0x74,0x5f,0x67,0x72,0x6f,0x75,0x70,0x5f,0x69,0x64,0x28,0x30,0x29,0x3b,0x0a,0x5f,0x5f,0x6c,0x6f,0x63,0x61,0x6c,0x20,0x69,0x6e,0x74,0x20,
-    0x63,0x6f,0x75,0x6e,0x74,0x65,0x72,0x73,0x5b,0x43,0x4f,0x55,0x4e,0x54,0x49,0x4e,0x47,0x5f,0x53,0x4f,0x52,0x54,0x5f,0x53,0x49,0x5a,0x45,0x5d,0x5b,0x32,0x5d,0x3b,
-    0x0a,0x66,0x6f,0x72,0x20,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x69,0x3d,0x74,0x69,0x64,0x3b,0x20,0x69,0x3c,0x43,0x4f,0x55,0x4e,0x54,0x49,0x4e,0x47,
-    0x5f,0x53,0x4f,0x52,0x54,0x5f,0x53,0x49,0x5a,0x45,0x2a,0x32,0x3b,0x20,0x69,0x2b,0x3d,0x42,0x57,0x54,0x5f,0x47,0x52,0x4f,0x55,0x50,0x5f,0x53,0x49,0x5a,0x45,0x29,
-    0x0a,0x28,0x28,0x5f,0x5f,0x6c,0x6f,0x63,0x61,0x6c,0x20,0x69,0x6e,0x74,0x2a,0x29,0x63,0x6f,0x75,0x6e,0x74,0x65,0x72,0x73,0x29,0x5b,0x69,0x5d,0x3d,0x30,0x3b,0x0a,
-    0x62,0x61,0x72,0x72,0x69,0x65,0x72,0x28,0x43,0x4c,0x4b,0x5f,0x4c,0x4f,0x43,0x41,0x4c,0x5f,0x4d,0x45,0x4d,0x5f,0x46,0x45,0x4e,0x43,0x45,0x29,0x3b,0x0a,0x63,0x6f,
-    0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x20,0x64,0x61,0x74,0x61,0x5f,0x6f,0x66,0x66,0x73,0x65,0x74,0x3d,0x28,0x75,0x69,0x6e,0x74,0x36,0x34,
-    0x5f,0x74,0x29,0x28,0x67,0x69,0x64,0x29,0x2a,0x64,0x61,0x74,0x61,0x5f,0x73,0x74,0x72,0x69,0x64,0x65,0x3b,0x0a,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,
-    0x69,0x6e,0x74,0x38,0x5f,0x74,0x2a,0x20,0x69,0x6e,0x70,0x75,0x74,0x3d,0x64,0x61,0x74,0x61,0x73,0x2b,0x64,0x61,0x74,0x61,0x5f,0x6f,0x66,0x66,0x73,0x65,0x74,0x2b,
-    0x31,0x32,0x38,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x4e,0x3d,0x64,0x61,0x74,0x61,0x5f,0x73,0x69,0x7a,0x65,0x73,
-    0x5b,0x67,0x69,0x64,0x5d,0x2b,0x31,0x3b,0x0a,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x2a,0x20,0x70,0x3d,0x28,0x5f,
-    0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x2a,0x29,0x28,0x69,0x6e,0x70,0x75,0x74,0x29,0x3b,0x0a,0x76,0x6f,0x6c,0x61,0x74,
-    0x69,0x6c,0x65,0x20,0x5f,0x5f,0x6c,0x6f,0x63,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x38,0x5f,0x74,0x2a,0x20,0x63,0x6f,0x75,0x6e,0x74,0x65,0x72,0x73,0x5f,0x61,0x74,
-    0x6f,0x6d,0x69,0x63,0x3d,0x28,0x76,0x6f,0x6c,0x61,0x74,0x69,0x6c,0x65,0x20,0x5f,0x5f,0x6c,0x6f,0x63,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x38,0x5f,0x74,0x2a,0x29,
-    0x28,0x63,0x6f,0x75,0x6e,0x74,0x65,0x72,0x73,0x29,0x3b,0x0a,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x2b,0x3d,0x64,0x61,0x74,0x61,0x5f,0x6f,0x66,0x66,0x73,0x65,0x74,
-    0x3b,0x0a,0x74,0x6d,0x70,0x5f,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x2b,0x3d,0x64,0x61,0x74,0x61,0x5f,0x6f,0x66,0x66,0x73,0x65,0x74,0x3b,0x0a,0x66,0x6f,0x72,0x20,
-    0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x69,0x3d,0x74,0x69,0x64,0x3b,0x20,0x69,0x3c,0x4e,0x3b,0x20,0x69,0x2b,0x3d,0x42,0x57,0x54,0x5f,0x47,0x52,0x4f,
-    0x55,0x50,0x5f,0x53,0x49,0x5a,0x45,0x29,0x0a,0x7b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x69,0x6e,0x64,0x65,0x78,0x3d,
-    0x69,0x3e,0x3e,0x33,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x62,0x69,0x74,0x5f,0x6f,0x66,0x66,0x73,0x65,0x74,0x3d,
-    0x28,0x69,0x26,0x37,0x29,0x3c,0x3c,0x33,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x20,0x61,0x3d,0x70,0x5b,0x69,0x6e,0x64,
-    0x65,0x78,0x5d,0x3b,0x0a,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x20,0x62,0x3d,0x70,0x5b,0x69,0x6e,0x64,0x65,0x78,0x2b,0x31,0x5d,0x3b,0x0a,0x69,0x66,0x28,0x62,
-    0x69,0x74,0x5f,0x6f,0x66,0x66,0x73,0x65,0x74,0x3d,0x3d,0x30,0x29,0x0a,0x62,0x3d,0x30,0x3b,0x0a,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x20,0x76,0x61,0x6c,0x75,
-    0x65,0x3d,0x28,0x61,0x3e,0x3e,0x62,0x69,0x74,0x5f,0x6f,0x66,0x66,0x73,0x65,0x74,0x29,0x7c,0x28,0x62,0x3c,0x3c,0x28,0x36,0x34,0x2d,0x62,0x69,0x74,0x5f,0x6f,0x66,
-    0x66,0x73,0x65,0x74,0x29,0x29,0x3b,0x0a,0x75,0x69,0x6e,0x74,0x32,0x20,0x74,0x6d,0x70,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x63,0x68,0x61,0x72,0x34,0x20,
-    0x6d,0x61,0x73,0x6b,0x3d,0x28,0x75,0x63,0x68,0x61,0x72,0x34,0x29,0x28,0x33,0x2c,0x32,0x2c,0x31,0x2c,0x30,0x29,0x3b,0x0a,0x74,0x6d,0x70,0x2e,0x78,0x3d,0x61,0x73,
-    0x5f,0x75,0x69,0x6e,0x74,0x28,0x73,0x68,0x75,0x66,0x66,0x6c,0x65,0x28,0x61,0x73,0x5f,0x75,0x63,0x68,0x61,0x72,0x34,0x28,0x61,0x73,0x5f,0x75,0x69,0x6e,0x74,0x32,
-    0x28,0x76,0x61,0x6c,0x75,0x65,0x29,0x2e,0x79,0x29,0x2c,0x6d,0x61,0x73,0x6b,0x29,0x29,0x3b,0x0a,0x74,0x6d,0x70,0x2e,0x79,0x3d,0x61,0x73,0x5f,0x75,0x69,0x6e,0x74,
-    0x28,0x73,0x68,0x75,0x66,0x66,0x6c,0x65,0x28,0x61,0x73,0x5f,0x75,0x63,0x68,0x61,0x72,0x34,0x28,0x61,0x73,0x5f,0x75,0x69,0x6e,0x74,0x32,0x28,0x76,0x61,0x6c,0x75,
-    0x65,0x29,0x2e,0x78,0x29,0x2c,0x6d,0x61,0x73,0x6b,0x29,0x29,0x3b,0x0a,0x76,0x61,0x6c,0x75,0x65,0x3d,0x61,0x73,0x5f,0x75,0x6c,0x6f,0x6e,0x67,0x28,0x74,0x6d,0x70,
-    0x29,0x3b,0x0a,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x5b,0x69,0x5d,0x3d,0x28,0x76,0x61,0x6c,0x75,0x65,0x26,0x28,0x28,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x29,
-    0x28,0x2d,0x31,0x29,0x3c,0x3c,0x32,0x31,0x29,0x29,0x7c,0x69,0x3b,0x0a,0x61,0x74,0x6f,0x6d,0x69,0x63,0x5f,0x61,0x64,0x64,0x28,0x28,0x76,0x6f,0x6c,0x61,0x74,0x69,
-    0x6c,0x65,0x20,0x5f,0x5f,0x6c,0x6f,0x63,0x61,0x6c,0x20,0x69,0x6e,0x74,0x2a,0x29,0x28,0x63,0x6f,0x75,0x6e,0x74,0x65,0x72,0x73,0x5f,0x61,0x74,0x6f,0x6d,0x69,0x63,
-    0x2b,0x28,0x28,0x28,0x76,0x61,0x6c,0x75,0x65,0x3e,0x3e,0x28,0x36,0x34,0x2d,0x43,0x4f,0x55,0x4e,0x54,0x49,0x4e,0x47,0x5f,0x53,0x4f,0x52,0x54,0x5f,0x42,0x49,0x54,
-    0x53,0x2a,0x32,0x29,0x29,0x26,0x28,0x43,0x4f,0x55,0x4e,0x54,0x49,0x4e,0x47,0x5f,0x53,0x4f,0x52,0x54,0x5f,0x53,0x49,0x5a,0x45,0x2d,0x31,0x29,0x29,0x3c,0x3c,0x33,
-    0x29,0x29,0x2c,0x31,0x29,0x3b,0x0a,0x61,0x74,0x6f,0x6d,0x69,0x63,0x5f,0x61,0x64,0x64,0x28,0x28,0x76,0x6f,0x6c,0x61,0x74,0x69,0x6c,0x65,0x20,0x5f,0x5f,0x6c,0x6f,
-    0x63,0x61,0x6c,0x20,0x69,0x6e,0x74,0x2a,0x29,0x28,0x63,0x6f,0x75,0x6e,0x74,0x65,0x72,0x73,0x5f,0x61,0x74,0x6f,0x6d,0x69,0x63,0x2b,0x28,0x28,0x76,0x61,0x6c,0x75,
-    0x65,0x3e,0x3e,0x28,0x36,0x34,0x2d,0x43,0x4f,0x55,0x4e,0x54,0x49,0x4e,0x47,0x5f,0x53,0x4f,0x52,0x54,0x5f,0x42,0x49,0x54,0x53,0x29,0x29,0x3c,0x3c,0x33,0x29,0x2b,
-    0x34,0x29,0x2c,0x31,0x29,0x3b,0x0a,0x7d,0x0a,0x62,0x61,0x72,0x72,0x69,0x65,0x72,0x28,0x43,0x4c,0x4b,0x5f,0x4c,0x4f,0x43,0x41,0x4c,0x5f,0x4d,0x45,0x4d,0x5f,0x46,
-    0x45,0x4e,0x43,0x45,0x29,0x3b,0x0a,0x69,0x66,0x28,0x74,0x69,0x64,0x3d,0x3d,0x30,0x29,0x0a,0x7b,0x0a,0x69,0x6e,0x74,0x20,0x74,0x30,0x3d,0x63,0x6f,0x75,0x6e,0x74,
-    0x65,0x72,0x73,0x5b,0x30,0x5d,0x5b,0x30,0x5d,0x3b,0x0a,0x69,0x6e,0x74,0x20,0x74,0x31,0x3d,0x63,0x6f,0x75,0x6e,0x74,0x65,0x72,0x73,0x5b,0x30,0x5d,0x5b,0x31,0x5d,
-    0x3b,0x0a,0x63,0x6f,0x75,0x6e,0x74,0x65,0x72,0x73,0x5b,0x30,0x5d,0x5b,0x30,0x5d,0x3d,0x74,0x30,0x2d,0x31,0x3b,0x0a,0x63,0x6f,0x75,0x6e,0x74,0x65,0x72,0x73,0x5b,
-    0x30,0x5d,0x5b,0x31,0x5d,0x3d,0x74,0x31,0x2d,0x31,0x3b,0x0a,0x66,0x6f,0x72,0x20,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x69,0x3d,0x31,0x3b,0x20,0x69,
-    0x3c,0x43,0x4f,0x55,0x4e,0x54,0x49,0x4e,0x47,0x5f,0x53,0x4f,0x52,0x54,0x5f,0x53,0x49,0x5a,0x45,0x3b,0x20,0x2b,0x2b,0x69,0x29,0x0a,0x7b,0x0a,0x74,0x30,0x2b,0x3d,
-    0x63,0x6f,0x75,0x6e,0x74,0x65,0x72,0x73,0x5b,0x69,0x5d,0x5b,0x30,0x5d,0x3b,0x0a,0x74,0x31,0x2b,0x3d,0x63,0x6f,0x75,0x6e,0x74,0x65,0x72,0x73,0x5b,0x69,0x5d,0x5b,
-    0x31,0x5d,0x3b,0x0a,0x63,0x6f,0x75,0x6e,0x74,0x65,0x72,0x73,0x5b,0x69,0x5d,0x5b,0x30,0x5d,0x3d,0x74,0x30,0x2d,0x31,0x3b,0x0a,0x63,0x6f,0x75,0x6e,0x74,0x65,0x72,
-    0x73,0x5b,0x69,0x5d,0x5b,0x31,0x5d,0x3d,0x74,0x31,0x2d,0x31,0x3b,0x0a,0x7d,0x0a,0x7d,0x0a,0x62,0x61,0x72,0x72,0x69,0x65,0x72,0x28,0x43,0x4c,0x4b,0x5f,0x4c,0x4f,
-    0x43,0x41,0x4c,0x5f,0x4d,0x45,0x4d,0x5f,0x46,0x45,0x4e,0x43,0x45,0x29,0x3b,0x0a,0x66,0x6f,0x72,0x20,0x28,0x69,0x6e,0x74,0x20,0x69,0x3d,0x74,0x69,0x64,0x3b,0x20,
-    0x69,0x3c,0x4e,0x3b,0x20,0x69,0x2b,0x3d,0x42,0x57,0x54,0x5f,0x47,0x52,0x4f,0x55,0x50,0x5f,0x53,0x49,0x5a,0x45,0x29,0x0a,0x7b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,
-    0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x20,0x64,0x61,0x74,0x61,0x3d,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x5b,0x69,0x5d,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,
-    0x69,0x6e,0x74,0x20,0x6b,0x3d,0x61,0x74,0x6f,0x6d,0x69,0x63,0x5f,0x73,0x75,0x62,0x28,0x28,0x76,0x6f,0x6c,0x61,0x74,0x69,0x6c,0x65,0x20,0x5f,0x5f,0x6c,0x6f,0x63,
-    0x61,0x6c,0x20,0x69,0x6e,0x74,0x2a,0x29,0x28,0x63,0x6f,0x75,0x6e,0x74,0x65,0x72,0x73,0x5f,0x61,0x74,0x6f,0x6d,0x69,0x63,0x2b,0x28,0x28,0x28,0x64,0x61,0x74,0x61,
-    0x3e,0x3e,0x28,0x36,0x34,0x2d,0x43,0x4f,0x55,0x4e,0x54,0x49,0x4e,0x47,0x5f,0x53,0x4f,0x52,0x54,0x5f,0x42,0x49,0x54,0x53,0x2a,0x32,0x29,0x29,0x26,0x28,0x43,0x4f,
-    0x55,0x4e,0x54,0x49,0x4e,0x47,0x5f,0x53,0x4f,0x52,0x54,0x5f,0x53,0x49,0x5a,0x45,0x2d,0x31,0x29,0x29,0x3c,0x3c,0x33,0x29,0x29,0x2c,0x31,0x29,0x3b,0x0a,0x74,0x6d,
-    0x70,0x5f,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x5b,0x6b,0x5d,0x3d,0x64,0x61,0x74,0x61,0x3b,0x0a,0x7d,0x0a,0x62,0x61,0x72,0x72,0x69,0x65,0x72,0x28,0x43,0x4c,0x4b,
-    0x5f,0x47,0x4c,0x4f,0x42,0x41,0x4c,0x5f,0x4d,0x45,0x4d,0x5f,0x46,0x45,0x4e,0x43,0x45,0x29,0x3b,0x0a,0x69,0x66,0x28,0x74,0x69,0x64,0x3d,0x3d,0x30,0x29,0x0a,0x7b,
-    0x0a,0x66,0x6f,0x72,0x20,0x28,0x69,0x6e,0x74,0x20,0x69,0x3d,0x4e,0x2d,0x31,0x3b,0x20,0x69,0x3e,0x3d,0x30,0x3b,0x20,0x2d,0x2d,0x69,0x29,0x0a,0x7b,0x0a,0x63,0x6f,
-    0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x20,0x64,0x61,0x74,0x61,0x3d,0x74,0x6d,0x70,0x5f,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x5b,0x69,0x5d,
-    0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x69,0x6e,0x74,0x20,0x6b,0x3d,0x61,0x74,0x6f,0x6d,0x69,0x63,0x5f,0x73,0x75,0x62,0x28,0x28,0x76,0x6f,0x6c,0x61,0x74,0x69,
-    0x6c,0x65,0x20,0x5f,0x5f,0x6c,0x6f,0x63,0x61,0x6c,0x20,0x69,0x6e,0x74,0x2a,0x29,0x28,0x63,0x6f,0x75,0x6e,0x74,0x65,0x72,0x73,0x5f,0x61,0x74,0x6f,0x6d,0x69,0x63,
-    0x2b,0x28,0x28,0x64,0x61,0x74,0x61,0x3e,0x3e,0x28,0x36,0x34,0x2d,0x43,0x4f,0x55,0x4e,0x54,0x49,0x4e,0x47,0x5f,0x53,0x4f,0x52,0x54,0x5f,0x42,0x49,0x54,0x53,0x29,
-    0x29,0x3c,0x3c,0x33,0x29,0x2b,0x34,0x29,0x2c,0x31,0x29,0x3b,0x0a,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x5b,0x6b,0x5d,0x3d,0x64,0x61,0x74,0x61,0x3b,0x0a,0x7d,0x0a,
-    0x7d,0x0a,0x62,0x61,0x72,0x72,0x69,0x65,0x72,0x28,0x43,0x4c,0x4b,0x5f,0x47,0x4c,0x4f,0x42,0x41,0x4c,0x5f,0x4d,0x45,0x4d,0x5f,0x46,0x45,0x4e,0x43,0x45,0x29,0x3b,
-    0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x4e,0x31,0x3d,0x4e,0x2d,0x31,0x3b,0x0a,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,
-    0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x2a,0x20,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x33,0x32,0x3d,0x28,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,
-    0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x2a,0x29,0x28,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x29,0x3b,0x0a,0x66,0x6f,0x72,0x20,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,
-    0x74,0x20,0x69,0x3d,0x74,0x69,0x64,0x3b,0x20,0x69,0x3c,0x4e,0x31,0x3b,0x20,0x69,0x2b,0x3d,0x42,0x57,0x54,0x5f,0x47,0x52,0x4f,0x55,0x50,0x5f,0x53,0x49,0x5a,0x45,
-    0x29,0x0a,0x7b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x76,0x61,0x6c,0x75,0x65,0x3d,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,
-    0x33,0x32,0x5b,0x69,0x2a,0x32,0x2b,0x31,0x5d,0x3e,0x3e,0x28,0x33,0x32,0x2d,0x43,0x4f,0x55,0x4e,0x54,0x49,0x4e,0x47,0x5f,0x53,0x4f,0x52,0x54,0x5f,0x42,0x49,0x54,
-    0x53,0x2a,0x32,0x29,0x3b,0x0a,0x69,0x66,0x28,0x76,0x61,0x6c,0x75,0x65,0x21,0x3d,0x28,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x33,0x32,0x5b,0x69,0x2a,0x32,0x2b,0x33,
-    0x5d,0x3e,0x3e,0x28,0x33,0x32,0x2d,0x43,0x4f,0x55,0x4e,0x54,0x49,0x4e,0x47,0x5f,0x53,0x4f,0x52,0x54,0x5f,0x42,0x49,0x54,0x53,0x2a,0x32,0x29,0x29,0x29,0x0a,0x63,
-    0x6f,0x6e,0x74,0x69,0x6e,0x75,0x65,0x3b,0x0a,0x69,0x66,0x28,0x28,0x69,0x3e,0x30,0x29,0x26,0x26,0x28,0x28,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x33,0x32,0x5b,0x69,
-    0x2a,0x32,0x2d,0x31,0x5d,0x3e,0x3e,0x28,0x33,0x32,0x2d,0x43,0x4f,0x55,0x4e,0x54,0x49,0x4e,0x47,0x5f,0x53,0x4f,0x52,0x54,0x5f,0x42,0x49,0x54,0x53,0x2a,0x32,0x29,
-    0x29,0x3d,0x3d,0x76,0x61,0x6c,0x75,0x65,0x29,0x29,0x0a,0x63,0x6f,0x6e,0x74,0x69,0x6e,0x75,0x65,0x3b,0x0a,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x69,0x31,
-    0x3d,0x69,0x2b,0x32,0x3b,0x0a,0x77,0x68,0x69,0x6c,0x65,0x20,0x28,0x28,0x69,0x31,0x3c,0x4e,0x29,0x26,0x26,0x28,0x28,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x33,0x32,
-    0x5b,0x69,0x31,0x2a,0x32,0x2b,0x31,0x5d,0x3e,0x3e,0x28,0x33,0x32,0x2d,0x43,0x4f,0x55,0x4e,0x54,0x49,0x4e,0x47,0x5f,0x53,0x4f,0x52,0x54,0x5f,0x42,0x49,0x54,0x53,
-    0x2a,0x32,0x29,0x29,0x3d,0x3d,0x76,0x61,0x6c,0x75,0x65,0x29,0x29,0x0a,0x2b,0x2b,0x69,0x31,0x3b,0x0a,0x66,0x6f,0x72,0x20,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,
-    0x74,0x20,0x6a,0x3d,0x69,0x3b,0x20,0x6a,0x3c,0x69,0x31,0x3b,0x20,0x2b,0x2b,0x6a,0x29,0x0a,0x7b,0x0a,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x20,0x74,0x3d,0x69,
-    0x6e,0x64,0x69,0x63,0x65,0x73,0x5b,0x6a,0x5d,0x3b,0x0a,0x66,0x6f,0x72,0x20,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x6b,0x3d,0x6a,0x2b,0x31,0x3b,0x20,
-    0x6b,0x3c,0x69,0x31,0x3b,0x20,0x2b,0x2b,0x6b,0x29,0x0a,0x7b,0x0a,0x69,0x66,0x28,0x74,0x3e,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x5b,0x6b,0x5d,0x29,0x0a,0x7b,0x0a,
-    0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x20,0x74,0x31,0x3d,0x74,0x3b,0x0a,0x74,0x3d,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x5b,0x6b,
-    0x5d,0x3b,0x0a,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x5b,0x6b,0x5d,0x3d,0x74,0x31,0x3b,0x0a,0x7d,0x0a,0x7d,0x0a,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x5b,0x6a,0x5d,
-    0x3d,0x74,0x3b,0x0a,0x7d,0x0a,0x7d,0x0a,0x62,0x61,0x72,0x72,0x69,0x65,0x72,0x28,0x43,0x4c,0x4b,0x5f,0x47,0x4c,0x4f,0x42,0x41,0x4c,0x5f,0x4d,0x45,0x4d,0x5f,0x46,
-    0x45,0x4e,0x43,0x45,0x29,0x3b,0x0a,0x2d,0x2d,0x69,0x6e,0x70,0x75,0x74,0x3b,0x0a,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x38,0x5f,0x74,
-    0x2a,0x20,0x6f,0x75,0x74,0x70,0x75,0x74,0x3d,0x28,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x38,0x5f,0x74,0x2a,0x29,0x28,0x74,0x6d,0x70,
-    0x5f,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x29,0x3b,0x0a,0x66,0x6f,0x72,0x20,0x28,0x69,0x6e,0x74,0x20,0x69,0x3d,0x74,0x69,0x64,0x3b,0x20,0x69,0x3c,0x3d,0x4e,0x3b,
-    0x20,0x69,0x2b,0x3d,0x42,0x57,0x54,0x5f,0x47,0x52,0x4f,0x55,0x50,0x5f,0x53,0x49,0x5a,0x45,0x29,0x0a,0x6f,0x75,0x74,0x70,0x75,0x74,0x5b,0x69,0x5d,0x3d,0x69,0x6e,
-    0x70,0x75,0x74,0x5b,0x69,0x6e,0x64,0x69,0x63,0x65,0x73,0x5b,0x69,0x5d,0x26,0x28,0x28,0x31,0x3c,0x3c,0x32,0x31,0x29,0x2d,0x31,0x29,0x5d,0x3b,0x0a,0x7d,0x0a,0x5f,
-    0x5f,0x6b,0x65,0x72,0x6e,0x65,0x6c,0x20,0x76,0x6f,0x69,0x64,0x20,0x66,0x69,0x6c,0x74,0x65,0x72,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x6e,0x6f,0x6e,
-    0x63,0x65,0x2c,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x62,0x77,0x74,0x5f,0x6d,0x61,0x78,0x5f,0x73,0x69,0x7a,0x65,0x2c,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,
-    0x6c,0x20,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x2a,0x20,0x68,0x61,0x73,0x68,0x65,0x73,0x2c,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,
-    0x6c,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x2a,0x20,0x66,0x69,0x6c,0x74,0x65,0x72,0x65,0x64,0x5f,0x68,0x61,0x73,0x68,0x65,0x73,0x29,0x0a,0x7b,0x0a,0x63,
-    0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x5f,0x69,0x64,0x3d,0x67,0x65,0x74,0x5f,0x67,0x6c,0x6f,0x62,
-    0x61,0x6c,0x5f,0x69,0x64,0x28,0x30,0x29,0x3b,0x0a,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,
-    0x74,0x2a,0x20,0x68,0x61,0x73,0x68,0x3d,0x68,0x61,0x73,0x68,0x65,0x73,0x2b,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x5f,0x69,0x64,0x2a,0x28,0x33,0x32,0x2f,0x73,0x69,0x7a,
-    0x65,0x6f,0x66,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x29,0x29,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x73,
-    0x74,0x61,0x67,0x65,0x32,0x5f,0x73,0x69,0x7a,0x65,0x3d,0x53,0x54,0x41,0x47,0x45,0x31,0x5f,0x53,0x49,0x5a,0x45,0x2b,0x28,0x2a,0x68,0x61,0x73,0x68,0x26,0x30,0x78,
-    0x66,0x66,0x66,0x66,0x66,0x29,0x3b,0x0a,0x69,0x66,0x28,0x73,0x74,0x61,0x67,0x65,0x32,0x5f,0x73,0x69,0x7a,0x65,0x3c,0x62,0x77,0x74,0x5f,0x6d,0x61,0x78,0x5f,0x73,
-    0x69,0x7a,0x65,0x29,0x0a,0x7b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x69,0x6e,0x74,0x20,0x69,0x6e,0x64,0x65,0x78,0x3d,0x61,0x74,0x6f,0x6d,0x69,0x63,0x5f,0x61,0x64,
-    0x64,0x28,0x28,0x76,0x6f,0x6c,0x61,0x74,0x69,0x6c,0x65,0x20,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x69,0x6e,0x74,0x2a,0x29,0x28,0x66,0x69,0x6c,0x74,0x65,
-    0x72,0x65,0x64,0x5f,0x68,0x61,0x73,0x68,0x65,0x73,0x29,0x2c,0x31,0x29,0x2a,0x28,0x33,0x36,0x2f,0x73,0x69,0x7a,0x65,0x6f,0x66,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,
-    0x5f,0x74,0x29,0x29,0x2b,0x31,0x3b,0x0a,0x66,0x69,0x6c,0x74,0x65,0x72,0x65,0x64,0x5f,0x68,0x61,0x73,0x68,0x65,0x73,0x5b,0x69,0x6e,0x64,0x65,0x78,0x5d,0x3d,0x6e,
-    0x6f,0x6e,0x63,0x65,0x2b,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x5f,0x69,0x64,0x3b,0x0a,0x23,0x70,0x72,0x61,0x67,0x6d,0x61,0x20,0x75,0x6e,0x72,0x6f,0x6c,0x6c,0x20,0x38,
-    0x0a,0x66,0x6f,0x72,0x20,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x69,0x3d,0x30,0x3b,0x20,0x69,0x3c,0x38,0x3b,0x20,0x2b,0x2b,0x69,0x29,0x0a,0x66,0x69,
-    0x6c,0x74,0x65,0x72,0x65,0x64,0x5f,0x68,0x61,0x73,0x68,0x65,0x73,0x5b,0x69,0x6e,0x64,0x65,0x78,0x2b,0x69,0x2b,0x31,0x5d,0x3d,0x68,0x61,0x73,0x68,0x5b,0x69,0x5d,
-    0x3b,0x0a,0x7d,0x0a,0x7d,0x0a,0x5f,0x5f,0x6b,0x65,0x72,0x6e,0x65,0x6c,0x20,0x76,0x6f,0x69,0x64,0x20,0x70,0x72,0x65,0x70,0x61,0x72,0x65,0x5f,0x62,0x61,0x74,0x63,
-    0x68,0x32,0x28,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x2a,0x20,0x68,0x61,0x73,0x68,0x65,0x73,0x2c,0x5f,0x5f,0x67,
-    0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x2a,0x20,0x66,0x69,0x6c,0x74,0x65,0x72,0x65,0x64,0x5f,0x68,0x61,0x73,0x68,0x65,0x73,0x2c,
-    0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x2a,0x20,0x64,0x61,0x74,0x61,0x5f,0x73,0x69,0x7a,0x65,0x73,0x29,0x0a,0x7b,
-    0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x5f,0x69,0x64,0x3d,0x67,0x65,0x74,0x5f,0x67,0x6c,
-    0x6f,0x62,0x61,0x6c,0x5f,0x69,0x64,0x28,0x30,0x29,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x4e,0x3d,0x66,0x69,0x6c,
-    0x74,0x65,0x72,0x65,0x64,0x5f,0x68,0x61,0x73,0x68,0x65,0x73,0x5b,0x30,0x5d,0x2d,0x67,0x65,0x74,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x5f,0x73,0x69,0x7a,0x65,0x28,
-    0x30,0x29,0x3b,0x0a,0x69,0x66,0x28,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x5f,0x69,0x64,0x3d,0x3d,0x30,0x29,0x0a,0x66,0x69,0x6c,0x74,0x65,0x72,0x65,0x64,0x5f,0x68,0x61,
-    0x73,0x68,0x65,0x73,0x5b,0x30,0x5d,0x3d,0x4e,0x3b,0x0a,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x2a,0x20,0x68,0x61,
-    0x73,0x68,0x3d,0x68,0x61,0x73,0x68,0x65,0x73,0x2b,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x5f,0x69,0x64,0x2a,0x38,0x3b,0x0a,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,
-    0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x2a,0x20,0x66,0x69,0x6c,0x74,0x65,0x72,0x65,0x64,0x5f,0x68,0x61,0x73,0x68,0x3d,0x66,0x69,0x6c,0x74,0x65,0x72,0x65,0x64,
-    0x5f,0x68,0x61,0x73,0x68,0x65,0x73,0x2b,0x28,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x5f,0x69,0x64,0x2b,0x4e,0x29,0x2a,0x39,0x2b,0x31,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,
-    0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x73,0x74,0x61,0x67,0x65,0x32,0x5f,0x73,0x69,0x7a,0x65,0x3d,0x53,0x54,0x41,0x47,0x45,0x31,0x5f,0x53,0x49,0x5a,
-    0x45,0x2b,0x28,0x66,0x69,0x6c,0x74,0x65,0x72,0x65,0x64,0x5f,0x68,0x61,0x73,0x68,0x5b,0x31,0x5d,0x26,0x30,0x78,0x66,0x66,0x66,0x66,0x66,0x29,0x3b,0x0a,0x64,0x61,
-    0x74,0x61,0x5f,0x73,0x69,0x7a,0x65,0x73,0x5b,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x5f,0x69,0x64,0x5d,0x3d,0x73,0x74,0x61,0x67,0x65,0x32,0x5f,0x73,0x69,0x7a,0x65,0x3b,
-    0x0a,0x23,0x70,0x72,0x61,0x67,0x6d,0x61,0x20,0x75,0x6e,0x72,0x6f,0x6c,0x6c,0x20,0x38,0x0a,0x66,0x6f,0x72,0x20,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,
-    0x69,0x3d,0x30,0x3b,0x20,0x69,0x3c,0x38,0x3b,0x20,0x2b,0x2b,0x69,0x29,0x0a,0x68,0x61,0x73,0x68,0x5b,0x69,0x5d,0x3d,0x66,0x69,0x6c,0x74,0x65,0x72,0x65,0x64,0x5f,
-    0x68,0x61,0x73,0x68,0x5b,0x69,0x2b,0x31,0x5d,0x3b,0x0a,0x7d,0x0a,0x5f,0x5f,0x6b,0x65,0x72,0x6e,0x65,0x6c,0x20,0x76,0x6f,0x69,0x64,0x20,0x66,0x69,0x6e,0x64,0x5f,
-    0x73,0x68,0x61,0x72,0x65,0x73,0x28,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x2a,0x20,
-    0x68,0x61,0x73,0x68,0x65,0x73,0x2c,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x2a,0x20,
-    0x66,0x69,0x6c,0x74,0x65,0x72,0x65,0x64,0x5f,0x68,0x61,0x73,0x68,0x65,0x73,0x2c,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x20,0x74,0x61,0x72,0x67,0x65,0x74,0x2c,
-    0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x2a,0x20,0x73,0x68,0x61,0x72,0x65,0x73,0x29,0x0a,0x7b,0x0a,0x63,0x6f,0x6e,
-    0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x5f,0x69,0x6e,0x64,0x65,0x78,0x3d,0x67,0x65,0x74,0x5f,0x67,0x6c,0x6f,
-    0x62,0x61,0x6c,0x5f,0x69,0x64,0x28,0x30,0x29,0x3b,0x0a,0x69,0x66,0x28,0x68,0x61,0x73,0x68,0x65,0x73,0x5b,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x5f,0x69,0x6e,0x64,0x65,
-    0x78,0x2a,0x34,0x2b,0x33,0x5d,0x3c,0x74,0x61,0x72,0x67,0x65,0x74,0x29,0x0a,0x7b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,
-    0x69,0x64,0x78,0x3d,0x61,0x74,0x6f,0x6d,0x69,0x63,0x5f,0x69,0x6e,0x63,0x28,0x73,0x68,0x61,0x72,0x65,0x73,0x2b,0x30,0x78,0x46,0x46,0x29,0x3b,0x0a,0x69,0x66,0x28,
-    0x69,0x64,0x78,0x3c,0x30,0x78,0x46,0x46,0x29,0x0a,0x73,0x68,0x61,0x72,0x65,0x73,0x5b,0x69,0x64,0x78,0x5d,0x3d,0x66,0x69,0x6c,0x74,0x65,0x72,0x65,0x64,0x5f,0x68,
-    0x61,0x73,0x68,0x65,0x73,0x5b,0x28,0x66,0x69,0x6c,0x74,0x65,0x72,0x65,0x64,0x5f,0x68,0x61,0x73,0x68,0x65,0x73,0x5b,0x30,0x5d,0x2b,0x67,0x6c,0x6f,0x62,0x61,0x6c,
-    0x5f,0x69,0x6e,0x64,0x65,0x78,0x29,0x2a,0x39,0x2b,0x31,0x5d,0x3b,0x0a,0x7d,0x0a,0x7d,0x0a,0x23,0x64,0x65,0x66,0x69,0x6e,0x65,0x20,0x52,0x4f,0x54,0x41,0x54,0x45,
-    0x28,0x76,0x2c,0x63,0x29,0x20,0x28,0x72,0x6f,0x74,0x61,0x74,0x65,0x28,0x76,0x2c,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x29,0x63,0x29,0x29,0x0a,0x23,0x64,
-    0x65,0x66,0x69,0x6e,0x65,0x20,0x58,0x4f,0x52,0x28,0x76,0x2c,0x77,0x29,0x20,0x28,0x28,0x76,0x29,0x20,0x5e,0x20,0x28,0x77,0x29,0x29,0x0a,0x23,0x64,0x65,0x66,0x69,
-    0x6e,0x65,0x20,0x50,0x4c,0x55,0x53,0x28,0x76,0x2c,0x77,0x29,0x20,0x28,0x28,0x76,0x29,0x20,0x2b,0x20,0x28,0x77,0x29,0x29,0x0a,0x5f,0x5f,0x61,0x74,0x74,0x72,0x69,
-    0x62,0x75,0x74,0x65,0x5f,0x5f,0x28,0x28,0x72,0x65,0x71,0x64,0x5f,0x77,0x6f,0x72,0x6b,0x5f,0x67,0x72,0x6f,0x75,0x70,0x5f,0x73,0x69,0x7a,0x65,0x28,0x53,0x41,0x4c,
-    0x53,0x41,0x32,0x30,0x5f,0x47,0x52,0x4f,0x55,0x50,0x5f,0x53,0x49,0x5a,0x45,0x2c,0x31,0x2c,0x31,0x29,0x29,0x29,0x0a,0x5f,0x5f,0x6b,0x65,0x72,0x6e,0x65,0x6c,0x20,
-    0x76,0x6f,0x69,0x64,0x20,0x53,0x61,0x6c,0x73,0x61,0x32,0x30,0x5f,0x58,0x4f,0x52,0x4b,0x65,0x79,0x53,0x74,0x72,0x65,0x61,0x6d,0x28,0x5f,0x5f,0x67,0x6c,0x6f,0x62,
-    0x61,0x6c,0x20,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x2a,0x20,0x6b,0x65,0x79,0x73,0x2c,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,
-    0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x2a,0x20,0x6f,0x75,0x74,0x70,0x75,0x74,0x73,0x2c,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,
-    0x33,0x32,0x5f,0x74,0x2a,0x20,0x6f,0x75,0x74,0x70,0x75,0x74,0x5f,0x73,0x69,0x7a,0x65,0x73,0x2c,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x6f,0x75,0x74,0x70,
-    0x75,0x74,0x5f,0x73,0x74,0x72,0x69,0x64,0x65,0x29,0x0a,0x7b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x74,0x3d,0x67,0x65,
-    0x74,0x5f,0x6c,0x6f,0x63,0x61,0x6c,0x5f,0x69,0x64,0x28,0x30,0x29,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x67,0x3d,
-    0x67,0x65,0x74,0x5f,0x67,0x72,0x6f,0x75,0x70,0x5f,0x69,0x64,0x28,0x30,0x29,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x20,
-    0x6f,0x75,0x74,0x70,0x75,0x74,0x5f,0x6f,0x66,0x66,0x73,0x65,0x74,0x3d,0x67,0x2a,0x28,0x28,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x29,0x6f,0x75,0x74,0x70,0x75,
-    0x74,0x5f,0x73,0x74,0x72,0x69,0x64,0x65,0x29,0x2b,0x31,0x32,0x38,0x3b,0x0a,0x7b,0x0a,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,
-    0x5f,0x74,0x2a,0x20,0x70,0x3d,0x6f,0x75,0x74,0x70,0x75,0x74,0x73,0x2b,0x28,0x6f,0x75,0x74,0x70,0x75,0x74,0x5f,0x6f,0x66,0x66,0x73,0x65,0x74,0x2d,0x31,0x32,0x38,
-    0x29,0x2f,0x73,0x69,0x7a,0x65,0x6f,0x66,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x29,0x3b,0x0a,0x66,0x6f,0x72,0x20,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,
-    0x74,0x20,0x69,0x3d,0x74,0x3b,0x20,0x69,0x3c,0x31,0x32,0x38,0x2f,0x73,0x69,0x7a,0x65,0x6f,0x66,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x29,0x3b,0x20,0x69,
-    0x2b,0x3d,0x53,0x41,0x4c,0x53,0x41,0x32,0x30,0x5f,0x47,0x52,0x4f,0x55,0x50,0x5f,0x53,0x49,0x5a,0x45,0x29,0x0a,0x70,0x5b,0x69,0x5d,0x3d,0x30,0x3b,0x0a,0x7d,0x0a,
-    0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x2a,0x20,0x6b,0x3d,0x6b,0x65,0x79,0x73,0x2b,
-    0x67,0x2a,0x38,0x3b,0x0a,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x2a,0x20,0x6f,0x75,0x74,0x70,0x75,0x74,0x3d,0x6f,
-    0x75,0x74,0x70,0x75,0x74,0x73,0x2b,0x28,0x6f,0x75,0x74,0x70,0x75,0x74,0x5f,0x6f,0x66,0x66,0x73,0x65,0x74,0x2b,0x28,0x74,0x2a,0x36,0x34,0x29,0x29,0x2f,0x73,0x69,
-    0x7a,0x65,0x6f,0x66,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x29,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x6f,
-    0x75,0x74,0x70,0x75,0x74,0x5f,0x73,0x69,0x7a,0x65,0x3d,0x6f,0x75,0x74,0x70,0x75,0x74,0x5f,0x73,0x69,0x7a,0x65,0x73,0x5b,0x67,0x5d,0x3b,0x0a,0x63,0x6f,0x6e,0x73,
-    0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x6a,0x31,0x3d,0x6b,0x5b,0x30,0x5d,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,
-    0x5f,0x74,0x20,0x6a,0x32,0x3d,0x6b,0x5b,0x31,0x5d,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x6a,0x33,0x3d,0x6b,0x5b,
-    0x32,0x5d,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x6a,0x34,0x3d,0x6b,0x5b,0x33,0x5d,0x3b,0x0a,0x63,0x6f,0x6e,0x73,
-    0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x6a,0x31,0x31,0x3d,0x6b,0x5b,0x34,0x5d,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,
-    0x32,0x5f,0x74,0x20,0x6a,0x31,0x32,0x3d,0x6b,0x5b,0x35,0x5d,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x6a,0x31,0x33,
-    0x3d,0x6b,0x5b,0x36,0x5d,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x6a,0x31,0x34,0x3d,0x6b,0x5b,0x37,0x5d,0x3b,0x0a,
-    0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x6a,0x30,0x3d,0x30,0x78,0x36,0x31,0x37,0x30,0x37,0x38,0x36,0x35,0x55,0x3b,0x0a,0x63,
-    0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x6a,0x35,0x3d,0x30,0x78,0x33,0x33,0x32,0x30,0x36,0x34,0x36,0x45,0x55,0x3b,0x0a,0x63,0x6f,
-    0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x6a,0x31,0x30,0x3d,0x30,0x78,0x37,0x39,0x36,0x32,0x32,0x44,0x33,0x32,0x55,0x3b,0x0a,0x63,0x6f,
-    0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x6a,0x31,0x35,0x3d,0x30,0x78,0x36,0x42,0x32,0x30,0x36,0x35,0x37,0x34,0x55,0x3b,0x0a,0x63,0x6f,
-    0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x6a,0x36,0x3d,0x30,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,
-    0x74,0x20,0x6a,0x37,0x3d,0x30,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x6a,0x38,0x3d,0x30,0x3b,0x0a,0x63,0x6f,0x6e,
-    0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x6a,0x39,0x3d,0x30,0x3b,0x0a,0x66,0x6f,0x72,0x20,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,
-    0x69,0x3d,0x74,0x2a,0x36,0x34,0x3b,0x20,0x69,0x3c,0x6f,0x75,0x74,0x70,0x75,0x74,0x5f,0x73,0x69,0x7a,0x65,0x3b,0x20,0x69,0x2b,0x3d,0x53,0x41,0x4c,0x53,0x41,0x32,
-    0x30,0x5f,0x47,0x52,0x4f,0x55,0x50,0x5f,0x53,0x49,0x5a,0x45,0x2a,0x36,0x34,0x29,0x0a,0x7b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,
-    0x74,0x20,0x6a,0x38,0x5f,0x31,0x3d,0x6a,0x38,0x2b,0x28,0x69,0x2f,0x36,0x34,0x29,0x3b,0x0a,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x78,0x30,0x3d,0x6a,0x30,
-    0x3b,0x0a,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x78,0x31,0x3d,0x6a,0x31,0x3b,0x0a,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x78,0x32,0x3d,0x6a,0x32,
-    0x3b,0x0a,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x78,0x33,0x3d,0x6a,0x33,0x3b,0x0a,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x78,0x34,0x3d,0x6a,0x34,
-    0x3b,0x0a,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x78,0x35,0x3d,0x6a,0x35,0x3b,0x0a,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x78,0x36,0x3d,0x6a,0x36,
-    0x3b,0x0a,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x78,0x37,0x3d,0x6a,0x37,0x3b,0x0a,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x78,0x38,0x3d,0x6a,0x38,
-    0x5f,0x31,0x3b,0x0a,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x78,0x39,0x3d,0x6a,0x39,0x3b,0x0a,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x78,0x31,0x30,
-    0x3d,0x6a,0x31,0x30,0x3b,0x0a,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x78,0x31,0x31,0x3d,0x6a,0x31,0x31,0x3b,0x0a,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,
-    0x20,0x78,0x31,0x32,0x3d,0x6a,0x31,0x32,0x3b,0x0a,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x78,0x31,0x33,0x3d,0x6a,0x31,0x33,0x3b,0x0a,0x75,0x69,0x6e,0x74,
-    0x33,0x32,0x5f,0x74,0x20,0x78,0x31,0x34,0x3d,0x6a,0x31,0x34,0x3b,0x0a,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x78,0x31,0x35,0x3d,0x6a,0x31,0x35,0x3b,0x0a,
-    0x23,0x70,0x72,0x61,0x67,0x6d,0x61,0x20,0x75,0x6e,0x72,0x6f,0x6c,0x6c,0x20,0x35,0x0a,0x66,0x6f,0x72,0x20,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x6a,
-    0x3d,0x30,0x3b,0x20,0x6a,0x3c,0x31,0x30,0x3b,0x20,0x2b,0x2b,0x6a,0x29,0x0a,0x7b,0x0a,0x78,0x34,0x3d,0x58,0x4f,0x52,0x28,0x20,0x78,0x34,0x2c,0x52,0x4f,0x54,0x41,
-    0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x20,0x78,0x30,0x2c,0x78,0x31,0x32,0x29,0x2c,0x37,0x29,0x29,0x3b,0x0a,0x78,0x38,0x3d,0x58,0x4f,0x52,0x28,0x20,0x78,0x38,
-    0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x20,0x78,0x34,0x2c,0x78,0x30,0x29,0x2c,0x39,0x29,0x29,0x3b,0x0a,0x78,0x31,0x32,0x3d,0x58,0x4f,
-    0x52,0x28,0x78,0x31,0x32,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x20,0x78,0x38,0x2c,0x78,0x34,0x29,0x2c,0x31,0x33,0x29,0x29,0x3b,0x0a,
-    0x78,0x30,0x3d,0x58,0x4f,0x52,0x28,0x20,0x78,0x30,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x78,0x31,0x32,0x2c,0x78,0x38,0x29,0x2c,0x31,
-    0x38,0x29,0x29,0x3b,0x0a,0x78,0x39,0x3d,0x58,0x4f,0x52,0x28,0x20,0x78,0x39,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x20,0x78,0x35,0x2c,
-    0x78,0x31,0x29,0x2c,0x37,0x29,0x29,0x3b,0x0a,0x78,0x31,0x33,0x3d,0x58,0x4f,0x52,0x28,0x78,0x31,0x33,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,
-    0x28,0x20,0x78,0x39,0x2c,0x78,0x35,0x29,0x2c,0x39,0x29,0x29,0x3b,0x0a,0x78,0x31,0x3d,0x58,0x4f,0x52,0x28,0x20,0x78,0x31,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,
-    0x50,0x4c,0x55,0x53,0x28,0x78,0x31,0x33,0x2c,0x78,0x39,0x29,0x2c,0x31,0x33,0x29,0x29,0x3b,0x0a,0x78,0x35,0x3d,0x58,0x4f,0x52,0x28,0x20,0x78,0x35,0x2c,0x52,0x4f,
-    0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x20,0x78,0x31,0x2c,0x78,0x31,0x33,0x29,0x2c,0x31,0x38,0x29,0x29,0x3b,0x0a,0x78,0x31,0x34,0x3d,0x58,0x4f,0x52,
-    0x28,0x78,0x31,0x34,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x78,0x31,0x30,0x2c,0x78,0x36,0x29,0x2c,0x37,0x29,0x29,0x3b,0x0a,0x78,0x32,
-    0x3d,0x58,0x4f,0x52,0x28,0x20,0x78,0x32,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x78,0x31,0x34,0x2c,0x78,0x31,0x30,0x29,0x2c,0x39,0x29,
-    0x29,0x3b,0x0a,0x78,0x36,0x3d,0x58,0x4f,0x52,0x28,0x20,0x78,0x36,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x20,0x78,0x32,0x2c,0x78,0x31,
-    0x34,0x29,0x2c,0x31,0x33,0x29,0x29,0x3b,0x0a,0x78,0x31,0x30,0x3d,0x58,0x4f,0x52,0x28,0x78,0x31,0x30,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,
-    0x28,0x20,0x78,0x36,0x2c,0x78,0x32,0x29,0x2c,0x31,0x38,0x29,0x29,0x3b,0x0a,0x78,0x33,0x3d,0x58,0x4f,0x52,0x28,0x20,0x78,0x33,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,
-    0x28,0x50,0x4c,0x55,0x53,0x28,0x78,0x31,0x35,0x2c,0x78,0x31,0x31,0x29,0x2c,0x37,0x29,0x29,0x3b,0x0a,0x78,0x37,0x3d,0x58,0x4f,0x52,0x28,0x20,0x78,0x37,0x2c,0x52,
-    0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x20,0x78,0x33,0x2c,0x78,0x31,0x35,0x29,0x2c,0x39,0x29,0x29,0x3b,0x0a,0x78,0x31,0x31,0x3d,0x58,0x4f,0x52,
-    0x28,0x78,0x31,0x31,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x20,0x78,0x37,0x2c,0x78,0x33,0x29,0x2c,0x31,0x33,0x29,0x29,0x3b,0x0a,0x78,
-    0x31,0x35,0x3d,0x58,0x4f,0x52,0x28,0x78,0x31,0x35,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x78,0x31,0x31,0x2c,0x78,0x37,0x29,0x2c,0x31,
-    0x38,0x29,0x29,0x3b,0x0a,0x78,0x31,0x3d,0x58,0x4f,0x52,0x28,0x20,0x78,0x31,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x20,0x78,0x30,0x2c,
-    0x78,0x33,0x29,0x2c,0x37,0x29,0x29,0x3b,0x0a,0x78,0x32,0x3d,0x58,0x4f,0x52,0x28,0x20,0x78,0x32,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,
-    0x20,0x78,0x31,0x2c,0x78,0x30,0x29,0x2c,0x39,0x29,0x29,0x3b,0x0a,0x78,0x33,0x3d,0x58,0x4f,0x52,0x28,0x20,0x78,0x33,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,
-    0x4c,0x55,0x53,0x28,0x20,0x78,0x32,0x2c,0x78,0x31,0x29,0x2c,0x31,0x33,0x29,0x29,0x3b,0x0a,0x78,0x30,0x3d,0x58,0x4f,0x52,0x28,0x20,0x78,0x30,0x2c,0x52,0x4f,0x54,
-    0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x20,0x78,0x33,0x2c,0x78,0x32,0x29,0x2c,0x31,0x38,0x29,0x29,0x3b,0x0a,0x78,0x36,0x3d,0x58,0x4f,0x52,0x28,0x20,0x78,
-    0x36,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x20,0x78,0x35,0x2c,0x78,0x34,0x29,0x2c,0x37,0x29,0x29,0x3b,0x0a,0x78,0x37,0x3d,0x58,0x4f,
-    0x52,0x28,0x20,0x78,0x37,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x20,0x78,0x36,0x2c,0x78,0x35,0x29,0x2c,0x39,0x29,0x29,0x3b,0x0a,0x78,
-    0x34,0x3d,0x58,0x4f,0x52,0x28,0x20,0x78,0x34,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x20,0x78,0x37,0x2c,0x78,0x36,0x29,0x2c,0x31,0x33,
-    0x29,0x29,0x3b,0x0a,0x78,0x35,0x3d,0x58,0x4f,0x52,0x28,0x20,0x78,0x35,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x20,0x78,0x34,0x2c,0x78,
-    0x37,0x29,0x2c,0x31,0x38,0x29,0x29,0x3b,0x0a,0x78,0x31,0x31,0x3d,0x58,0x4f,0x52,0x28,0x78,0x31,0x31,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,
-    0x28,0x78,0x31,0x30,0x2c,0x78,0x39,0x29,0x2c,0x37,0x29,0x29,0x3b,0x0a,0x78,0x38,0x3d,0x58,0x4f,0x52,0x28,0x20,0x78,0x38,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,
-    0x50,0x4c,0x55,0x53,0x28,0x78,0x31,0x31,0x2c,0x78,0x31,0x30,0x29,0x2c,0x39,0x29,0x29,0x3b,0x0a,0x78,0x39,0x3d,0x58,0x4f,0x52,0x28,0x20,0x78,0x39,0x2c,0x52,0x4f,
-    0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x20,0x78,0x38,0x2c,0x78,0x31,0x31,0x29,0x2c,0x31,0x33,0x29,0x29,0x3b,0x0a,0x78,0x31,0x30,0x3d,0x58,0x4f,0x52,
-    0x28,0x78,0x31,0x30,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x20,0x78,0x39,0x2c,0x78,0x38,0x29,0x2c,0x31,0x38,0x29,0x29,0x3b,0x0a,0x78,
-    0x31,0x32,0x3d,0x58,0x4f,0x52,0x28,0x78,0x31,0x32,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x78,0x31,0x35,0x2c,0x78,0x31,0x34,0x29,0x2c,
-    0x37,0x29,0x29,0x3b,0x0a,0x78,0x31,0x33,0x3d,0x58,0x4f,0x52,0x28,0x78,0x31,0x33,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x78,0x31,0x32,
-    0x2c,0x78,0x31,0x35,0x29,0x2c,0x39,0x29,0x29,0x3b,0x0a,0x78,0x31,0x34,0x3d,0x58,0x4f,0x52,0x28,0x78,0x31,0x34,0x2c,0x52,0x4f,0x54,0x41,0x54,0x45,0x28,0x50,0x4c,
-    0x55,0x53,0x28,0x78,0x31,0x33,0x2c,0x78,0x31,0x32,0x29,0x2c,0x31,0x33,0x29,0x29,0x3b,0x0a,0x78,0x31,0x35,0x3d,0x58,0x4f,0x52,0x28,0x78,0x31,0x35,0x2c,0x52,0x4f,
-    0x54,0x41,0x54,0x45,0x28,0x50,0x4c,0x55,0x53,0x28,0x78,0x31,0x34,0x2c,0x78,0x31,0x33,0x29,0x2c,0x31,0x38,0x29,0x29,0x3b,0x0a,0x7d,0x0a,0x6f,0x75,0x74,0x70,0x75,
-    0x74,0x5b,0x30,0x5d,0x3d,0x50,0x4c,0x55,0x53,0x28,0x78,0x30,0x2c,0x6a,0x30,0x29,0x3b,0x0a,0x6f,0x75,0x74,0x70,0x75,0x74,0x5b,0x31,0x5d,0x3d,0x50,0x4c,0x55,0x53,
-    0x28,0x78,0x31,0x2c,0x6a,0x31,0x29,0x3b,0x0a,0x6f,0x75,0x74,0x70,0x75,0x74,0x5b,0x32,0x5d,0x3d,0x50,0x4c,0x55,0x53,0x28,0x78,0x32,0x2c,0x6a,0x32,0x29,0x3b,0x0a,
-    0x6f,0x75,0x74,0x70,0x75,0x74,0x5b,0x33,0x5d,0x3d,0x50,0x4c,0x55,0x53,0x28,0x78,0x33,0x2c,0x6a,0x33,0x29,0x3b,0x0a,0x6f,0x75,0x74,0x70,0x75,0x74,0x5b,0x34,0x5d,
-    0x3d,0x50,0x4c,0x55,0x53,0x28,0x78,0x34,0x2c,0x6a,0x34,0x29,0x3b,0x0a,0x6f,0x75,0x74,0x70,0x75,0x74,0x5b,0x35,0x5d,0x3d,0x50,0x4c,0x55,0x53,0x28,0x78,0x35,0x2c,
-    0x6a,0x35,0x29,0x3b,0x0a,0x6f,0x75,0x74,0x70,0x75,0x74,0x5b,0x36,0x5d,0x3d,0x50,0x4c,0x55,0x53,0x28,0x78,0x36,0x2c,0x6a,0x36,0x29,0x3b,0x0a,0x6f,0x75,0x74,0x70,
-    0x75,0x74,0x5b,0x37,0x5d,0x3d,0x50,0x4c,0x55,0x53,0x28,0x78,0x37,0x2c,0x6a,0x37,0x29,0x3b,0x0a,0x6f,0x75,0x74,0x70,0x75,0x74,0x5b,0x38,0x5d,0x3d,0x50,0x4c,0x55,
-    0x53,0x28,0x78,0x38,0x2c,0x6a,0x38,0x5f,0x31,0x29,0x3b,0x0a,0x6f,0x75,0x74,0x70,0x75,0x74,0x5b,0x39,0x5d,0x3d,0x50,0x4c,0x55,0x53,0x28,0x78,0x39,0x2c,0x6a,0x39,
-    0x29,0x3b,0x0a,0x6f,0x75,0x74,0x70,0x75,0x74,0x5b,0x31,0x30,0x5d,0x3d,0x50,0x4c,0x55,0x53,0x28,0x78,0x31,0x30,0x2c,0x6a,0x31,0x30,0x29,0x3b,0x0a,0x6f,0x75,0x74,
-    0x70,0x75,0x74,0x5b,0x31,0x31,0x5d,0x3d,0x50,0x4c,0x55,0x53,0x28,0x78,0x31,0x31,0x2c,0x6a,0x31,0x31,0x29,0x3b,0x0a,0x6f,0x75,0x74,0x70,0x75,0x74,0x5b,0x31,0x32,
-    0x5d,0x3d,0x50,0x4c,0x55,0x53,0x28,0x78,0x31,0x32,0x2c,0x6a,0x31,0x32,0x29,0x3b,0x0a,0x6f,0x75,0x74,0x70,0x75,0x74,0x5b,0x31,0x33,0x5d,0x3d,0x50,0x4c,0x55,0x53,
-    0x28,0x78,0x31,0x33,0x2c,0x6a,0x31,0x33,0x29,0x3b,0x0a,0x6f,0x75,0x74,0x70,0x75,0x74,0x5b,0x31,0x34,0x5d,0x3d,0x50,0x4c,0x55,0x53,0x28,0x78,0x31,0x34,0x2c,0x6a,
-    0x31,0x34,0x29,0x3b,0x0a,0x6f,0x75,0x74,0x70,0x75,0x74,0x5b,0x31,0x35,0x5d,0x3d,0x50,0x4c,0x55,0x53,0x28,0x78,0x31,0x35,0x2c,0x6a,0x31,0x35,0x29,0x3b,0x0a,0x6f,
-    0x75,0x74,0x70,0x75,0x74,0x2b,0x3d,0x28,0x53,0x41,0x4c,0x53,0x41,0x32,0x30,0x5f,0x47,0x52,0x4f,0x55,0x50,0x5f,0x53,0x49,0x5a,0x45,0x2a,0x36,0x34,0x29,0x2f,0x73,
-    0x69,0x7a,0x65,0x6f,0x66,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x29,0x3b,0x0a,0x7d,0x0a,0x62,0x61,0x72,0x72,0x69,0x65,0x72,0x28,0x43,0x4c,0x4b,0x5f,0x47,
-    0x4c,0x4f,0x42,0x41,0x4c,0x5f,0x4d,0x45,0x4d,0x5f,0x46,0x45,0x4e,0x43,0x45,0x29,0x3b,0x0a,0x69,0x66,0x28,0x74,0x3c,0x31,0x36,0x29,0x0a,0x7b,0x0a,0x5f,0x5f,0x67,
-    0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x2a,0x20,0x70,0x3d,0x6f,0x75,0x74,0x70,0x75,0x74,0x73,0x2b,0x28,0x6f,0x75,0x74,0x70,0x75,
-    0x74,0x5f,0x6f,0x66,0x66,0x73,0x65,0x74,0x2b,0x6f,0x75,0x74,0x70,0x75,0x74,0x5f,0x73,0x69,0x7a,0x65,0x2b,0x33,0x29,0x2f,0x73,0x69,0x7a,0x65,0x6f,0x66,0x28,0x75,
-    0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x29,0x3b,0x0a,0x70,0x5b,0x74,0x5d,0x3d,0x30,0x3b,0x0a,0x7d,0x0a,0x69,0x66,0x28,0x28,0x74,0x3d,0x3d,0x30,0x29,0x26,0x26,0x28,
-    0x6f,0x75,0x74,0x70,0x75,0x74,0x5f,0x73,0x69,0x7a,0x65,0x26,0x33,0x29,0x29,0x0a,0x6f,0x75,0x74,0x70,0x75,0x74,0x73,0x5b,0x28,0x6f,0x75,0x74,0x70,0x75,0x74,0x5f,
-    0x6f,0x66,0x66,0x73,0x65,0x74,0x2b,0x6f,0x75,0x74,0x70,0x75,0x74,0x5f,0x73,0x69,0x7a,0x65,0x29,0x2f,0x73,0x69,0x7a,0x65,0x6f,0x66,0x28,0x75,0x69,0x6e,0x74,0x33,
-    0x32,0x5f,0x74,0x29,0x5d,0x20,0x26,0x3d,0x20,0x30,0x78,0x46,0x46,0x46,0x46,0x46,0x46,0x46,0x46,0x55,0x3e,0x3e,0x28,0x28,0x34,0x2d,0x28,0x6f,0x75,0x74,0x70,0x75,
-    0x74,0x5f,0x73,0x69,0x7a,0x65,0x26,0x33,0x29,0x29,0x3c,0x3c,0x33,0x29,0x3b,0x0a,0x7d,0x0a,0x23,0x64,0x65,0x66,0x69,0x6e,0x65,0x20,0x52,0x4f,0x55,0x4e,0x44,0x53,
-    0x20,0x32,0x34,0x0a,0x23,0x64,0x65,0x66,0x69,0x6e,0x65,0x20,0x52,0x36,0x34,0x28,0x61,0x2c,0x62,0x2c,0x63,0x29,0x20,0x28,0x28,0x28,0x61,0x29,0x20,0x3c,0x3c,0x20,
-    0x62,0x29,0x20,0x7c,0x20,0x28,0x28,0x61,0x29,0x20,0x3e,0x3e,0x20,0x63,0x29,0x29,0x0a,0x5f,0x5f,0x63,0x6f,0x6e,0x73,0x74,0x61,0x6e,0x74,0x20,0x63,0x6f,0x6e,0x73,
-    0x74,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x20,0x72,0x63,0x5b,0x32,0x5d,0x5b,0x52,0x4f,0x55,0x4e,0x44,0x53,0x5d,0x3d,0x7b,0x0a,0x7b,0x30,0x78,0x30,0x30,
-    0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x31,0x55,0x4c,0x2c,0x30,0x78,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x38,
-    0x30,0x38,0x32,0x55,0x4c,0x2c,0x30,0x78,0x38,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x38,0x30,0x38,0x41,0x55,0x4c,0x2c,0x0a,0x30,0x78,0x38,0x30,
-    0x30,0x30,0x30,0x30,0x30,0x30,0x38,0x30,0x30,0x30,0x38,0x30,0x30,0x30,0x55,0x4c,0x2c,0x30,0x78,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x38,
-    0x30,0x38,0x42,0x55,0x4c,0x2c,0x30,0x78,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x38,0x30,0x30,0x30,0x30,0x30,0x30,0x31,0x55,0x4c,0x2c,0x0a,0x30,0x78,0x38,0x30,
-    0x30,0x30,0x30,0x30,0x30,0x30,0x38,0x30,0x30,0x30,0x38,0x30,0x38,0x31,0x55,0x4c,0x2c,0x30,0x78,0x38,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x38,
-    0x30,0x30,0x39,0x55,0x4c,0x2c,0x30,0x78,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x38,0x41,0x55,0x4c,0x2c,0x0a,0x30,0x78,0x30,0x30,
-    0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x38,0x38,0x55,0x4c,0x2c,0x30,0x78,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x38,0x30,0x30,0x30,0x38,
-    0x30,0x30,0x39,0x55,0x4c,0x2c,0x30,0x78,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x38,0x30,0x30,0x30,0x30,0x30,0x30,0x41,0x55,0x4c,0x2c,0x0a,0x30,0x78,0x30,0x30,
-    0x30,0x30,0x30,0x30,0x30,0x30,0x38,0x30,0x30,0x30,0x38,0x30,0x38,0x42,0x55,0x4c,0x2c,0x30,0x78,0x38,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,
-    0x30,0x38,0x42,0x55,0x4c,0x2c,0x30,0x78,0x38,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x38,0x30,0x38,0x39,0x55,0x4c,0x2c,0x0a,0x30,0x78,0x38,0x30,
-    0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x38,0x30,0x30,0x33,0x55,0x4c,0x2c,0x30,0x78,0x38,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x38,
-    0x30,0x30,0x32,0x55,0x4c,0x2c,0x30,0x78,0x38,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x38,0x30,0x55,0x4c,0x2c,0x0a,0x30,0x78,0x30,0x30,
-    0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x38,0x30,0x30,0x41,0x55,0x4c,0x2c,0x30,0x78,0x38,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x38,0x30,0x30,0x30,0x30,
-    0x30,0x30,0x41,0x55,0x4c,0x2c,0x30,0x78,0x38,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x38,0x30,0x30,0x30,0x38,0x30,0x38,0x31,0x55,0x4c,0x2c,0x0a,0x30,0x78,0x38,0x30,
-    0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x38,0x30,0x38,0x30,0x55,0x4c,0x2c,0x30,0x78,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x38,0x30,0x30,0x30,0x30,
-    0x30,0x30,0x31,0x55,0x4c,0x2c,0x30,0x78,0x38,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x38,0x30,0x30,0x30,0x38,0x30,0x30,0x38,0x55,0x4c,0x7d,0x2c,0x0a,0x7b,0x30,0x55,
-    0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x0a,0x30,
-    0x55,0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x0a,
-    0x30,0x55,0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x30,0x55,0x4c,0x2c,0x30,0x55,0x4c,0x7d,
-    0x0a,0x7d,0x3b,0x0a,0x5f,0x5f,0x63,0x6f,0x6e,0x73,0x74,0x61,0x6e,0x74,0x20,0x63,0x6f,0x6e,0x73,0x74,0x20,0x69,0x6e,0x74,0x20,0x72,0x6f,0x5b,0x32,0x35,0x5d,0x5b,
-    0x32,0x5d,0x3d,0x7b,0x0a,0x7b,0x20,0x30,0x2c,0x36,0x34,0x7d,0x2c,0x7b,0x34,0x34,0x2c,0x32,0x30,0x7d,0x2c,0x7b,0x34,0x33,0x2c,0x32,0x31,0x7d,0x2c,0x7b,0x32,0x31,
-    0x2c,0x34,0x33,0x7d,0x2c,0x7b,0x31,0x34,0x2c,0x35,0x30,0x7d,0x2c,0x0a,0x7b,0x20,0x31,0x2c,0x36,0x33,0x7d,0x2c,0x7b,0x20,0x36,0x2c,0x35,0x38,0x7d,0x2c,0x7b,0x32,
-    0x35,0x2c,0x33,0x39,0x7d,0x2c,0x7b,0x20,0x38,0x2c,0x35,0x36,0x7d,0x2c,0x7b,0x31,0x38,0x2c,0x34,0x36,0x7d,0x2c,0x0a,0x7b,0x36,0x32,0x2c,0x32,0x7d,0x2c,0x7b,0x35,
-    0x35,0x2c,0x39,0x7d,0x2c,0x7b,0x33,0x39,0x2c,0x32,0x35,0x7d,0x2c,0x7b,0x34,0x31,0x2c,0x32,0x33,0x7d,0x2c,0x7b,0x20,0x32,0x2c,0x36,0x32,0x7d,0x2c,0x0a,0x7b,0x32,
-    0x38,0x2c,0x33,0x36,0x7d,0x2c,0x7b,0x32,0x30,0x2c,0x34,0x34,0x7d,0x2c,0x7b,0x20,0x33,0x2c,0x36,0x31,0x7d,0x2c,0x7b,0x34,0x35,0x2c,0x31,0x39,0x7d,0x2c,0x7b,0x36,
-    0x31,0x2c,0x33,0x7d,0x2c,0x0a,0x7b,0x32,0x37,0x2c,0x33,0x37,0x7d,0x2c,0x7b,0x33,0x36,0x2c,0x32,0x38,0x7d,0x2c,0x7b,0x31,0x30,0x2c,0x35,0x34,0x7d,0x2c,0x7b,0x31,
-    0x35,0x2c,0x34,0x39,0x7d,0x2c,0x7b,0x35,0x36,0x2c,0x38,0x7d,0x0a,0x7d,0x3b,0x0a,0x5f,0x5f,0x63,0x6f,0x6e,0x73,0x74,0x61,0x6e,0x74,0x20,0x63,0x6f,0x6e,0x73,0x74,
-    0x20,0x69,0x6e,0x74,0x20,0x61,0x5b,0x32,0x35,0x5d,0x3d,0x7b,0x0a,0x30,0x2c,0x36,0x2c,0x31,0x32,0x2c,0x31,0x38,0x2c,0x32,0x34,0x2c,0x0a,0x31,0x2c,0x37,0x2c,0x31,
-    0x33,0x2c,0x31,0x39,0x2c,0x32,0x30,0x2c,0x0a,0x32,0x2c,0x38,0x2c,0x31,0x34,0x2c,0x31,0x35,0x2c,0x32,0x31,0x2c,0x0a,0x33,0x2c,0x39,0x2c,0x31,0x30,0x2c,0x31,0x36,
-    0x2c,0x32,0x32,0x2c,0x0a,0x34,0x2c,0x35,0x2c,0x31,0x31,0x2c,0x31,0x37,0x2c,0x32,0x33,0x0a,0x7d,0x3b,0x0a,0x5f,0x5f,0x63,0x6f,0x6e,0x73,0x74,0x61,0x6e,0x74,0x20,
-    0x63,0x6f,0x6e,0x73,0x74,0x20,0x69,0x6e,0x74,0x20,0x62,0x5b,0x32,0x35,0x5d,0x3d,0x7b,0x0a,0x30,0x2c,0x31,0x2c,0x32,0x2c,0x33,0x2c,0x34,0x2c,0x0a,0x31,0x2c,0x32,
-    0x2c,0x33,0x2c,0x34,0x2c,0x30,0x2c,0x0a,0x32,0x2c,0x33,0x2c,0x34,0x2c,0x30,0x2c,0x31,0x2c,0x0a,0x33,0x2c,0x34,0x2c,0x30,0x2c,0x31,0x2c,0x32,0x2c,0x0a,0x34,0x2c,
-    0x30,0x2c,0x31,0x2c,0x32,0x2c,0x33,0x0a,0x7d,0x3b,0x0a,0x5f,0x5f,0x63,0x6f,0x6e,0x73,0x74,0x61,0x6e,0x74,0x20,0x63,0x6f,0x6e,0x73,0x74,0x20,0x69,0x6e,0x74,0x20,
-    0x63,0x5b,0x32,0x35,0x5d,0x5b,0x33,0x5d,0x3d,0x7b,0x0a,0x7b,0x20,0x30,0x2c,0x31,0x2c,0x32,0x7d,0x2c,0x7b,0x20,0x31,0x2c,0x32,0x2c,0x33,0x7d,0x2c,0x7b,0x20,0x32,
-    0x2c,0x33,0x2c,0x34,0x7d,0x2c,0x7b,0x20,0x33,0x2c,0x34,0x2c,0x30,0x7d,0x2c,0x7b,0x20,0x34,0x2c,0x30,0x2c,0x31,0x7d,0x2c,0x0a,0x7b,0x20,0x35,0x2c,0x36,0x2c,0x37,
-    0x7d,0x2c,0x7b,0x20,0x36,0x2c,0x37,0x2c,0x38,0x7d,0x2c,0x7b,0x20,0x37,0x2c,0x38,0x2c,0x39,0x7d,0x2c,0x7b,0x20,0x38,0x2c,0x39,0x2c,0x35,0x7d,0x2c,0x7b,0x20,0x39,
-    0x2c,0x35,0x2c,0x36,0x7d,0x2c,0x0a,0x7b,0x31,0x30,0x2c,0x31,0x31,0x2c,0x31,0x32,0x7d,0x2c,0x7b,0x31,0x31,0x2c,0x31,0x32,0x2c,0x31,0x33,0x7d,0x2c,0x7b,0x31,0x32,
-    0x2c,0x31,0x33,0x2c,0x31,0x34,0x7d,0x2c,0x7b,0x31,0x33,0x2c,0x31,0x34,0x2c,0x31,0x30,0x7d,0x2c,0x7b,0x31,0x34,0x2c,0x31,0x30,0x2c,0x31,0x31,0x7d,0x2c,0x0a,0x7b,
-    0x31,0x35,0x2c,0x31,0x36,0x2c,0x31,0x37,0x7d,0x2c,0x7b,0x31,0x36,0x2c,0x31,0x37,0x2c,0x31,0x38,0x7d,0x2c,0x7b,0x31,0x37,0x2c,0x31,0x38,0x2c,0x31,0x39,0x7d,0x2c,
-    0x7b,0x31,0x38,0x2c,0x31,0x39,0x2c,0x31,0x35,0x7d,0x2c,0x7b,0x31,0x39,0x2c,0x31,0x35,0x2c,0x31,0x36,0x7d,0x2c,0x0a,0x7b,0x32,0x30,0x2c,0x32,0x31,0x2c,0x32,0x32,
-    0x7d,0x2c,0x7b,0x32,0x31,0x2c,0x32,0x32,0x2c,0x32,0x33,0x7d,0x2c,0x7b,0x32,0x32,0x2c,0x32,0x33,0x2c,0x32,0x34,0x7d,0x2c,0x7b,0x32,0x33,0x2c,0x32,0x34,0x2c,0x32,
-    0x30,0x7d,0x2c,0x7b,0x32,0x34,0x2c,0x32,0x30,0x2c,0x32,0x31,0x7d,0x0a,0x7d,0x3b,0x0a,0x5f,0x5f,0x63,0x6f,0x6e,0x73,0x74,0x61,0x6e,0x74,0x20,0x63,0x6f,0x6e,0x73,
-    0x74,0x20,0x69,0x6e,0x74,0x20,0x64,0x5b,0x32,0x35,0x5d,0x3d,0x7b,0x0a,0x30,0x2c,0x31,0x2c,0x32,0x2c,0x33,0x2c,0x34,0x2c,0x0a,0x31,0x30,0x2c,0x31,0x31,0x2c,0x31,
-    0x32,0x2c,0x31,0x33,0x2c,0x31,0x34,0x2c,0x0a,0x32,0x30,0x2c,0x32,0x31,0x2c,0x32,0x32,0x2c,0x32,0x33,0x2c,0x32,0x34,0x2c,0x0a,0x35,0x2c,0x36,0x2c,0x37,0x2c,0x38,
-    0x2c,0x39,0x2c,0x0a,0x31,0x35,0x2c,0x31,0x36,0x2c,0x31,0x37,0x2c,0x31,0x38,0x2c,0x31,0x39,0x0a,0x7d,0x3b,0x0a,0x5f,0x5f,0x61,0x74,0x74,0x72,0x69,0x62,0x75,0x74,
-    0x65,0x5f,0x5f,0x28,0x28,0x72,0x65,0x71,0x64,0x5f,0x77,0x6f,0x72,0x6b,0x5f,0x67,0x72,0x6f,0x75,0x70,0x5f,0x73,0x69,0x7a,0x65,0x28,0x33,0x32,0x2c,0x31,0x2c,0x31,
-    0x29,0x29,0x29,0x0a,0x5f,0x5f,0x6b,0x65,0x72,0x6e,0x65,0x6c,0x20,0x76,0x6f,0x69,0x64,0x20,0x73,0x68,0x61,0x33,0x28,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,
-    0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x38,0x5f,0x74,0x2a,0x20,0x69,0x6e,0x70,0x75,0x74,0x73,0x2c,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x63,
-    0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x2a,0x20,0x69,0x6e,0x70,0x75,0x74,0x5f,0x73,0x69,0x7a,0x65,0x73,0x2c,0x75,0x69,0x6e,0x74,0x33,
-    0x32,0x5f,0x74,0x20,0x69,0x6e,0x70,0x75,0x74,0x5f,0x73,0x74,0x72,0x69,0x64,0x65,0x2c,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,
-    0x5f,0x74,0x2a,0x20,0x68,0x61,0x73,0x68,0x65,0x73,0x29,0x0a,0x7b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x74,0x3d,0x67,
-    0x65,0x74,0x5f,0x6c,0x6f,0x63,0x61,0x6c,0x5f,0x69,0x64,0x28,0x30,0x29,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x67,
-    0x3d,0x67,0x65,0x74,0x5f,0x67,0x72,0x6f,0x75,0x70,0x5f,0x69,0x64,0x28,0x30,0x29,0x3b,0x0a,0x69,0x66,0x28,0x74,0x3e,0x3d,0x32,0x35,0x29,0x0a,0x72,0x65,0x74,0x75,
-    0x72,0x6e,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x73,0x3d,0x74,0x20,0x25,0x20,0x35,0x3b,0x0a,0x63,0x6f,0x6e,0x73,
-    0x74,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x20,0x69,0x6e,0x70,0x75,0x74,0x5f,0x6f,0x66,0x66,0x73,0x65,0x74,0x3d,0x28,0x28,0x75,0x69,0x6e,0x74,0x36,0x34,
-    0x5f,0x74,0x29,0x69,0x6e,0x70,0x75,0x74,0x5f,0x73,0x74,0x72,0x69,0x64,0x65,0x29,0x2a,0x67,0x3b,0x0a,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,
-    0x74,0x36,0x34,0x5f,0x74,0x2a,0x20,0x69,0x6e,0x70,0x75,0x74,0x3d,0x28,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x2a,
-    0x29,0x28,0x69,0x6e,0x70,0x75,0x74,0x73,0x2b,0x69,0x6e,0x70,0x75,0x74,0x5f,0x6f,0x66,0x66,0x73,0x65,0x74,0x29,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,
-    0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x69,0x6e,0x70,0x75,0x74,0x5f,0x73,0x69,0x7a,0x65,0x3d,0x69,0x6e,0x70,0x75,0x74,0x5f,0x73,0x69,0x7a,0x65,0x73,0x5b,0x67,0x5d,
-    0x2b,0x31,0x3b,0x0a,0x5f,0x5f,0x6c,0x6f,0x63,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x20,0x41,0x5b,0x32,0x35,0x5d,0x3b,0x0a,0x5f,0x5f,0x6c,0x6f,
-    0x63,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x20,0x43,0x5b,0x32,0x35,0x5d,0x3b,0x0a,0x5f,0x5f,0x6c,0x6f,0x63,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,
-    0x36,0x34,0x5f,0x74,0x20,0x44,0x5b,0x32,0x35,0x5d,0x3b,0x0a,0x41,0x5b,0x74,0x5d,0x3d,0x30,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,
-    0x5f,0x74,0x20,0x77,0x6f,0x72,0x64,0x73,0x3d,0x69,0x6e,0x70,0x75,0x74,0x5f,0x73,0x69,0x7a,0x65,0x2f,0x73,0x69,0x7a,0x65,0x6f,0x66,0x28,0x75,0x69,0x6e,0x74,0x36,
-    0x34,0x5f,0x74,0x29,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x74,0x61,0x69,0x6c,0x5f,0x73,0x69,0x7a,0x65,0x3d,0x69,
-    0x6e,0x70,0x75,0x74,0x5f,0x73,0x69,0x7a,0x65,0x20,0x25,0x20,0x73,0x69,0x7a,0x65,0x6f,0x66,0x28,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x29,0x3b,0x0a,0x75,0x69,
-    0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x77,0x6f,0x72,0x64,0x49,0x6e,0x64,0x65,0x78,0x3d,0x30,0x3b,0x0a,0x66,0x6f,0x72,0x20,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,
-    0x74,0x20,0x69,0x3d,0x30,0x3b,0x20,0x69,0x3c,0x77,0x6f,0x72,0x64,0x73,0x3b,0x20,0x2b,0x2b,0x69,0x2c,0x2b,0x2b,0x69,0x6e,0x70,0x75,0x74,0x29,0x0a,0x7b,0x0a,0x41,
-    0x5b,0x77,0x6f,0x72,0x64,0x49,0x6e,0x64,0x65,0x78,0x5d,0x20,0x5e,0x3d,0x20,0x2a,0x69,0x6e,0x70,0x75,0x74,0x3b,0x0a,0x2b,0x2b,0x77,0x6f,0x72,0x64,0x49,0x6e,0x64,
-    0x65,0x78,0x3b,0x0a,0x69,0x66,0x28,0x77,0x6f,0x72,0x64,0x49,0x6e,0x64,0x65,0x78,0x3d,0x3d,0x31,0x37,0x29,0x0a,0x7b,0x0a,0x23,0x70,0x72,0x61,0x67,0x6d,0x61,0x20,
-    0x75,0x6e,0x72,0x6f,0x6c,0x6c,0x20,0x52,0x4f,0x55,0x4e,0x44,0x53,0x0a,0x66,0x6f,0x72,0x20,0x28,0x69,0x6e,0x74,0x20,0x69,0x3d,0x30,0x3b,0x20,0x69,0x3c,0x52,0x4f,
-    0x55,0x4e,0x44,0x53,0x3b,0x20,0x2b,0x2b,0x69,0x29,0x0a,0x7b,0x0a,0x43,0x5b,0x74,0x5d,0x3d,0x41,0x5b,0x73,0x5d,0x5e,0x41,0x5b,0x73,0x2b,0x35,0x5d,0x5e,0x41,0x5b,
-    0x73,0x2b,0x31,0x30,0x5d,0x5e,0x41,0x5b,0x73,0x2b,0x31,0x35,0x5d,0x5e,0x41,0x5b,0x73,0x2b,0x32,0x30,0x5d,0x3b,0x0a,0x44,0x5b,0x74,0x5d,0x3d,0x43,0x5b,0x62,0x5b,
-    0x32,0x30,0x2b,0x73,0x5d,0x5d,0x5e,0x52,0x36,0x34,0x28,0x43,0x5b,0x62,0x5b,0x35,0x2b,0x73,0x5d,0x5d,0x2c,0x31,0x2c,0x36,0x33,0x29,0x3b,0x0a,0x43,0x5b,0x74,0x5d,
-    0x3d,0x52,0x36,0x34,0x28,0x41,0x5b,0x61,0x5b,0x74,0x5d,0x5d,0x5e,0x44,0x5b,0x62,0x5b,0x74,0x5d,0x5d,0x2c,0x72,0x6f,0x5b,0x74,0x5d,0x5b,0x30,0x5d,0x2c,0x72,0x6f,
-    0x5b,0x74,0x5d,0x5b,0x31,0x5d,0x29,0x3b,0x0a,0x41,0x5b,0x64,0x5b,0x74,0x5d,0x5d,0x3d,0x43,0x5b,0x63,0x5b,0x74,0x5d,0x5b,0x30,0x5d,0x5d,0x5e,0x28,0x28,0x7e,0x43,
-    0x5b,0x63,0x5b,0x74,0x5d,0x5b,0x31,0x5d,0x5d,0x29,0x26,0x43,0x5b,0x63,0x5b,0x74,0x5d,0x5b,0x32,0x5d,0x5d,0x29,0x3b,0x0a,0x41,0x5b,0x74,0x5d,0x20,0x5e,0x3d,0x20,
-    0x72,0x63,0x5b,0x28,0x74,0x3d,0x3d,0x30,0x29,0x3f,0x30,0x3a,0x31,0x5d,0x5b,0x69,0x5d,0x3b,0x0a,0x7d,0x0a,0x77,0x6f,0x72,0x64,0x49,0x6e,0x64,0x65,0x78,0x3d,0x30,
-    0x3b,0x0a,0x7d,0x0a,0x7d,0x0a,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x20,0x74,0x61,0x69,0x6c,0x3d,0x30,0x3b,0x0a,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,
-    0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x38,0x5f,0x74,0x2a,0x20,0x70,0x3d,0x28,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x63,0x6f,0x6e,0x73,0x74,
-    0x20,0x75,0x69,0x6e,0x74,0x38,0x5f,0x74,0x2a,0x29,0x69,0x6e,0x70,0x75,0x74,0x3b,0x0a,0x66,0x6f,0x72,0x20,0x28,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x69,
-    0x3d,0x30,0x3b,0x20,0x69,0x3c,0x74,0x61,0x69,0x6c,0x5f,0x73,0x69,0x7a,0x65,0x3b,0x20,0x2b,0x2b,0x69,0x29,0x0a,0x7b,0x0a,0x74,0x61,0x69,0x6c,0x7c,0x3d,0x28,0x75,
-    0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x29,0x28,0x70,0x5b,0x69,0x5d,0x29,0x3c,0x3c,0x28,0x69,0x2a,0x38,0x29,0x3b,0x0a,0x7d,0x0a,0x41,0x5b,0x77,0x6f,0x72,0x64,0x49,
-    0x6e,0x64,0x65,0x78,0x5d,0x20,0x5e,0x3d,0x20,0x74,0x61,0x69,0x6c,0x5e,0x28,0x28,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x29,0x28,0x28,0x28,0x75,0x69,0x6e,0x74,
-    0x36,0x34,0x5f,0x74,0x29,0x28,0x30,0x78,0x30,0x32,0x7c,0x28,0x31,0x3c,0x3c,0x32,0x29,0x29,0x29,0x3c,0x3c,0x28,0x74,0x61,0x69,0x6c,0x5f,0x73,0x69,0x7a,0x65,0x2a,
-    0x38,0x29,0x29,0x29,0x3b,0x0a,0x41,0x5b,0x31,0x36,0x5d,0x20,0x5e,0x3d,0x20,0x30,0x78,0x38,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,
-    0x30,0x55,0x4c,0x3b,0x0a,0x23,0x70,0x72,0x61,0x67,0x6d,0x61,0x20,0x75,0x6e,0x72,0x6f,0x6c,0x6c,0x20,0x31,0x0a,0x66,0x6f,0x72,0x20,0x28,0x69,0x6e,0x74,0x20,0x69,
-    0x3d,0x30,0x3b,0x20,0x69,0x3c,0x52,0x4f,0x55,0x4e,0x44,0x53,0x3b,0x20,0x2b,0x2b,0x69,0x29,0x0a,0x7b,0x0a,0x43,0x5b,0x74,0x5d,0x3d,0x41,0x5b,0x73,0x5d,0x5e,0x41,
-    0x5b,0x73,0x2b,0x35,0x5d,0x5e,0x41,0x5b,0x73,0x2b,0x31,0x30,0x5d,0x5e,0x41,0x5b,0x73,0x2b,0x31,0x35,0x5d,0x5e,0x41,0x5b,0x73,0x2b,0x32,0x30,0x5d,0x3b,0x0a,0x44,
-    0x5b,0x74,0x5d,0x3d,0x43,0x5b,0x62,0x5b,0x32,0x30,0x2b,0x73,0x5d,0x5d,0x5e,0x52,0x36,0x34,0x28,0x43,0x5b,0x62,0x5b,0x35,0x2b,0x73,0x5d,0x5d,0x2c,0x31,0x2c,0x36,
-    0x33,0x29,0x3b,0x0a,0x43,0x5b,0x74,0x5d,0x3d,0x52,0x36,0x34,0x28,0x41,0x5b,0x61,0x5b,0x74,0x5d,0x5d,0x5e,0x44,0x5b,0x62,0x5b,0x74,0x5d,0x5d,0x2c,0x72,0x6f,0x5b,
-    0x74,0x5d,0x5b,0x30,0x5d,0x2c,0x72,0x6f,0x5b,0x74,0x5d,0x5b,0x31,0x5d,0x29,0x3b,0x0a,0x41,0x5b,0x64,0x5b,0x74,0x5d,0x5d,0x3d,0x43,0x5b,0x63,0x5b,0x74,0x5d,0x5b,
-    0x30,0x5d,0x5d,0x5e,0x28,0x28,0x7e,0x43,0x5b,0x63,0x5b,0x74,0x5d,0x5b,0x31,0x5d,0x5d,0x29,0x26,0x43,0x5b,0x63,0x5b,0x74,0x5d,0x5b,0x32,0x5d,0x5d,0x29,0x3b,0x0a,
-    0x41,0x5b,0x74,0x5d,0x20,0x5e,0x3d,0x20,0x72,0x63,0x5b,0x28,0x74,0x3d,0x3d,0x30,0x29,0x3f,0x30,0x3a,0x31,0x5d,0x5b,0x69,0x5d,0x3b,0x0a,0x7d,0x0a,0x69,0x66,0x28,
-    0x74,0x3c,0x34,0x29,0x0a,0x7b,0x0a,0x68,0x61,0x73,0x68,0x65,0x73,0x2b,0x3d,0x67,0x2a,0x28,0x33,0x32,0x2f,0x73,0x69,0x7a,0x65,0x6f,0x66,0x28,0x75,0x69,0x6e,0x74,
-    0x36,0x34,0x5f,0x74,0x29,0x29,0x3b,0x0a,0x68,0x61,0x73,0x68,0x65,0x73,0x5b,0x74,0x5d,0x3d,0x41,0x5b,0x74,0x5d,0x3b,0x0a,0x7d,0x0a,0x7d,0x0a,0x5f,0x5f,0x61,0x74,
-    0x74,0x72,0x69,0x62,0x75,0x74,0x65,0x5f,0x5f,0x28,0x28,0x72,0x65,0x71,0x64,0x5f,0x77,0x6f,0x72,0x6b,0x5f,0x67,0x72,0x6f,0x75,0x70,0x5f,0x73,0x69,0x7a,0x65,0x28,
-    0x33,0x32,0x2c,0x31,0x2c,0x31,0x29,0x29,0x29,0x0a,0x5f,0x5f,0x6b,0x65,0x72,0x6e,0x65,0x6c,0x20,0x76,0x6f,0x69,0x64,0x20,0x73,0x68,0x61,0x33,0x5f,0x69,0x6e,0x69,
-    0x74,0x69,0x61,0x6c,0x28,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x38,0x5f,0x74,0x2a,0x20,0x69,0x6e,0x70,
-    0x75,0x74,0x5f,0x64,0x61,0x74,0x61,0x2c,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x69,0x6e,0x70,0x75,0x74,0x5f,0x73,0x69,0x7a,0x65,0x2c,0x75,0x69,0x6e,0x74,
-    0x33,0x32,0x5f,0x74,0x20,0x6e,0x6f,0x6e,0x63,0x65,0x2c,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x2a,0x20,0x68,0x61,
-    0x73,0x68,0x65,0x73,0x29,0x0a,0x7b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x74,0x3d,0x67,0x65,0x74,0x5f,0x6c,0x6f,0x63,
-    0x61,0x6c,0x5f,0x69,0x64,0x28,0x30,0x29,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x67,0x3d,0x67,0x65,0x74,0x5f,0x67,
-    0x72,0x6f,0x75,0x70,0x5f,0x69,0x64,0x28,0x30,0x29,0x3b,0x0a,0x69,0x66,0x28,0x74,0x3e,0x3d,0x32,0x35,0x29,0x0a,0x72,0x65,0x74,0x75,0x72,0x6e,0x3b,0x0a,0x63,0x6f,
-    0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x73,0x3d,0x74,0x20,0x25,0x20,0x35,0x3b,0x0a,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,
-    0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x2a,0x20,0x69,0x6e,0x70,0x75,0x74,0x3d,0x28,0x5f,0x5f,0x67,0x6c,0x6f,0x62,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,
-    0x74,0x2a,0x29,0x28,0x69,0x6e,0x70,0x75,0x74,0x5f,0x64,0x61,0x74,0x61,0x29,0x3b,0x0a,0x5f,0x5f,0x6c,0x6f,0x63,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,
-    0x74,0x20,0x41,0x5b,0x32,0x35,0x5d,0x3b,0x0a,0x5f,0x5f,0x6c,0x6f,0x63,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x20,0x43,0x5b,0x32,0x35,0x5d,0x3b,
-    0x0a,0x5f,0x5f,0x6c,0x6f,0x63,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x20,0x44,0x5b,0x32,0x35,0x5d,0x3b,0x0a,0x41,0x5b,0x74,0x5d,0x3d,0x28,0x74,
-    0x3c,0x31,0x36,0x29,0x3f,0x69,0x6e,0x70,0x75,0x74,0x5b,0x74,0x5d,0x3a,0x30,0x3b,0x0a,0x5f,0x5f,0x6c,0x6f,0x63,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,
-    0x74,0x2a,0x20,0x6e,0x6f,0x6e,0x63,0x65,0x5f,0x70,0x6f,0x73,0x3d,0x28,0x5f,0x5f,0x6c,0x6f,0x63,0x61,0x6c,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x2a,0x29,
-    0x28,0x41,0x29,0x2b,0x39,0x3b,0x0a,0x6e,0x6f,0x6e,0x63,0x65,0x2b,0x3d,0x67,0x3b,0x0a,0x6e,0x6f,0x6e,0x63,0x65,0x5f,0x70,0x6f,0x73,0x5b,0x30,0x5d,0x3d,0x28,0x6e,
-    0x6f,0x6e,0x63,0x65,0x5f,0x70,0x6f,0x73,0x5b,0x30,0x5d,0x26,0x30,0x78,0x46,0x46,0x46,0x46,0x46,0x46,0x55,0x29,0x7c,0x28,0x28,0x6e,0x6f,0x6e,0x63,0x65,0x26,0x30,
-    0x78,0x46,0x46,0x29,0x3c,0x3c,0x32,0x34,0x29,0x3b,0x0a,0x6e,0x6f,0x6e,0x63,0x65,0x5f,0x70,0x6f,0x73,0x5b,0x31,0x5d,0x3d,0x28,0x6e,0x6f,0x6e,0x63,0x65,0x5f,0x70,
-    0x6f,0x73,0x5b,0x31,0x5d,0x26,0x30,0x78,0x46,0x46,0x30,0x30,0x30,0x30,0x30,0x30,0x55,0x29,0x7c,0x28,0x6e,0x6f,0x6e,0x63,0x65,0x3e,0x3e,0x38,0x29,0x3b,0x0a,0x75,
-    0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x77,0x6f,0x72,0x64,0x49,0x6e,0x64,0x65,0x78,0x3d,0x69,0x6e,0x70,0x75,0x74,0x5f,0x73,0x69,0x7a,0x65,0x2f,0x73,0x69,0x7a,
-    0x65,0x6f,0x66,0x28,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x29,0x3b,0x0a,0x63,0x6f,0x6e,0x73,0x74,0x20,0x75,0x69,0x6e,0x74,0x33,0x32,0x5f,0x74,0x20,0x74,0x61,
-    0x69,0x6c,0x5f,0x73,0x69,0x7a,0x65,0x3d,0x69,0x6e,0x70,0x75,0x74,0x5f,0x73,0x69,0x7a,0x65,0x20,0x25,0x20,0x73,0x69,0x7a,0x65,0x6f,0x66,0x28,0x75,0x69,0x6e,0x74,
-    0x36,0x34,0x5f,0x74,0x29,0x3b,0x0a,0x41,0x5b,0x77,0x6f,0x72,0x64,0x49,0x6e,0x64,0x65,0x78,0x5d,0x20,0x5e,0x3d,0x20,0x28,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,
-    0x29,0x28,0x28,0x28,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x29,0x28,0x30,0x78,0x30,0x32,0x7c,0x28,0x31,0x3c,0x3c,0x32,0x29,0x29,0x29,0x3c,0x3c,0x28,0x74,0x61,
-    0x69,0x6c,0x5f,0x73,0x69,0x7a,0x65,0x2a,0x38,0x29,0x29,0x3b,0x0a,0x41,0x5b,0x31,0x36,0x5d,0x20,0x5e,0x3d,0x20,0x30,0x78,0x38,0x30,0x30,0x30,0x30,0x30,0x30,0x30,
-    0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x30,0x55,0x4c,0x3b,0x0a,0x23,0x70,0x72,0x61,0x67,0x6d,0x61,0x20,0x75,0x6e,0x72,0x6f,0x6c,0x6c,0x20,0x52,0x4f,0x55,0x4e,0x44,
-    0x53,0x0a,0x66,0x6f,0x72,0x20,0x28,0x69,0x6e,0x74,0x20,0x69,0x3d,0x30,0x3b,0x20,0x69,0x3c,0x52,0x4f,0x55,0x4e,0x44,0x53,0x3b,0x20,0x2b,0x2b,0x69,0x29,0x0a,0x7b,
-    0x0a,0x43,0x5b,0x74,0x5d,0x3d,0x41,0x5b,0x73,0x5d,0x5e,0x41,0x5b,0x73,0x2b,0x35,0x5d,0x5e,0x41,0x5b,0x73,0x2b,0x31,0x30,0x5d,0x5e,0x41,0x5b,0x73,0x2b,0x31,0x35,
-    0x5d,0x5e,0x41,0x5b,0x73,0x2b,0x32,0x30,0x5d,0x3b,0x0a,0x44,0x5b,0x74,0x5d,0x3d,0x43,0x5b,0x62,0x5b,0x32,0x30,0x2b,0x73,0x5d,0x5d,0x5e,0x52,0x36,0x34,0x28,0x43,
-    0x5b,0x62,0x5b,0x35,0x2b,0x73,0x5d,0x5d,0x2c,0x31,0x2c,0x36,0x33,0x29,0x3b,0x0a,0x43,0x5b,0x74,0x5d,0x3d,0x52,0x36,0x34,0x28,0x41,0x5b,0x61,0x5b,0x74,0x5d,0x5d,
-    0x5e,0x44,0x5b,0x62,0x5b,0x74,0x5d,0x5d,0x2c,0x72,0x6f,0x5b,0x74,0x5d,0x5b,0x30,0x5d,0x2c,0x72,0x6f,0x5b,0x74,0x5d,0x5b,0x31,0x5d,0x29,0x3b,0x0a,0x41,0x5b,0x64,
-    0x5b,0x74,0x5d,0x5d,0x3d,0x43,0x5b,0x63,0x5b,0x74,0x5d,0x5b,0x30,0x5d,0x5d,0x5e,0x28,0x28,0x7e,0x43,0x5b,0x63,0x5b,0x74,0x5d,0x5b,0x31,0x5d,0x5d,0x29,0x26,0x43,
-    0x5b,0x63,0x5b,0x74,0x5d,0x5b,0x32,0x5d,0x5d,0x29,0x3b,0x0a,0x41,0x5b,0x74,0x5d,0x20,0x5e,0x3d,0x20,0x72,0x63,0x5b,0x28,0x74,0x3d,0x3d,0x30,0x29,0x3f,0x30,0x3a,
-    0x31,0x5d,0x5b,0x69,0x5d,0x3b,0x0a,0x7d,0x0a,0x69,0x66,0x28,0x74,0x3c,0x34,0x29,0x0a,0x7b,0x0a,0x68,0x61,0x73,0x68,0x65,0x73,0x2b,0x3d,0x67,0x2a,0x28,0x33,0x32,
-    0x2f,0x73,0x69,0x7a,0x65,0x6f,0x66,0x28,0x75,0x69,0x6e,0x74,0x36,0x34,0x5f,0x74,0x29,0x29,0x3b,0x0a,0x68,0x61,0x73,0x68,0x65,0x73,0x5b,0x74,0x5d,0x3d,0x41,0x5b,
-    0x74,0x5d,0x3b,0x0a,0x7d,0x0a,0x7d,0x0a,0x00
-};
-
-} // namespace xmrig

src/backend/opencl/cl/astrobwt/salsa20.cl

@@ -1,153 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#define ROTATE(v,c) (rotate(v,(uint32_t)c))
-#define XOR(v,w) ((v) ^ (w))
-#define PLUS(v,w) ((v) + (w))
-
-__attribute__((reqd_work_group_size(SALSA20_GROUP_SIZE, 1, 1)))
-__kernel void Salsa20_XORKeyStream(__global const uint32_t* keys, __global uint32_t* outputs, __global uint32_t* output_sizes, uint32_t output_stride)
-{
-	const uint32_t t = get_local_id(0);
-	const uint32_t g = get_group_id(0);
-
-	// Put zeroes in the beginning
-	const uint64_t output_offset = g * ((uint64_t)output_stride) + 128;
-	{
-		__global uint32_t* p = outputs + (output_offset - 128) / sizeof(uint32_t);
-		for (uint32_t i = t; i < 128 / sizeof(uint32_t); i += SALSA20_GROUP_SIZE)
-			p[i] = 0;
-	}
-	
-	__global const uint32_t* k = keys + g * 8;
-	__global uint32_t* output = outputs + (output_offset + (t * 64)) / sizeof(uint32_t);
-	const uint32_t output_size = output_sizes[g];
-
-	const uint32_t j1 = k[0];
-	const uint32_t j2 = k[1];
-	const uint32_t j3 = k[2];
-	const uint32_t j4 = k[3];
-	const uint32_t j11 = k[4];
-	const uint32_t j12 = k[5];
-	const uint32_t j13 = k[6];
-	const uint32_t j14 = k[7];
-	const uint32_t j0 = 0x61707865U;
-	const uint32_t j5 = 0x3320646EU;
-	const uint32_t j10 = 0x79622D32U;
-	const uint32_t j15 = 0x6B206574U;
-	const uint32_t j6 = 0;
-	const uint32_t j7 = 0;
-	const uint32_t j8 = 0;
-	const uint32_t j9 = 0;
-
-	for (uint32_t i = t * 64; i < output_size; i += SALSA20_GROUP_SIZE * 64)
-	{
-		const uint32_t j8_1 = j8 + (i / 64);
-
-		uint32_t x0 = j0;
-		uint32_t x1 = j1;
-		uint32_t x2 = j2;
-		uint32_t x3 = j3;
-		uint32_t x4 = j4;
-		uint32_t x5 = j5;
-		uint32_t x6 = j6;
-		uint32_t x7 = j7;
-		uint32_t x8 = j8_1;
-		uint32_t x9 = j9;
-		uint32_t x10 = j10;
-		uint32_t x11 = j11;
-		uint32_t x12 = j12;
-		uint32_t x13 = j13;
-		uint32_t x14 = j14;
-		uint32_t x15 = j15;
-
-		#pragma unroll 5
-		for (uint32_t j = 0; j < 10; ++j)
-		{
-			x4  = XOR( x4,ROTATE(PLUS( x0,x12), 7));
-			x8  = XOR( x8,ROTATE(PLUS( x4, x0), 9));
-			x12 = XOR(x12,ROTATE(PLUS( x8, x4),13));
-			x0  = XOR( x0,ROTATE(PLUS(x12, x8),18));
-			x9  = XOR( x9,ROTATE(PLUS( x5, x1), 7));
-			x13 = XOR(x13,ROTATE(PLUS( x9, x5), 9));
-			x1  = XOR( x1,ROTATE(PLUS(x13, x9),13));
-			x5  = XOR( x5,ROTATE(PLUS( x1,x13),18));
-			x14 = XOR(x14,ROTATE(PLUS(x10, x6), 7));
-			x2  = XOR( x2,ROTATE(PLUS(x14,x10), 9));
-			x6  = XOR( x6,ROTATE(PLUS( x2,x14),13));
-			x10 = XOR(x10,ROTATE(PLUS( x6, x2),18));
-			x3  = XOR( x3,ROTATE(PLUS(x15,x11), 7));
-			x7  = XOR( x7,ROTATE(PLUS( x3,x15), 9));
-			x11 = XOR(x11,ROTATE(PLUS( x7, x3),13));
-			x15 = XOR(x15,ROTATE(PLUS(x11, x7),18));
-			x1  = XOR( x1,ROTATE(PLUS( x0, x3), 7));
-			x2  = XOR( x2,ROTATE(PLUS( x1, x0), 9));
-			x3  = XOR( x3,ROTATE(PLUS( x2, x1),13));
-			x0  = XOR( x0,ROTATE(PLUS( x3, x2),18));
-			x6  = XOR( x6,ROTATE(PLUS( x5, x4), 7));
-			x7  = XOR( x7,ROTATE(PLUS( x6, x5), 9));
-			x4  = XOR( x4,ROTATE(PLUS( x7, x6),13));
-			x5  = XOR( x5,ROTATE(PLUS( x4, x7),18));
-			x11 = XOR(x11,ROTATE(PLUS(x10, x9), 7));
-			x8  = XOR( x8,ROTATE(PLUS(x11,x10), 9));
-			x9  = XOR( x9,ROTATE(PLUS( x8,x11),13));
-			x10 = XOR(x10,ROTATE(PLUS( x9, x8),18));
-			x12 = XOR(x12,ROTATE(PLUS(x15,x14), 7));
-			x13 = XOR(x13,ROTATE(PLUS(x12,x15), 9));
-			x14 = XOR(x14,ROTATE(PLUS(x13,x12),13));
-			x15 = XOR(x15,ROTATE(PLUS(x14,x13),18));
-		}
-
-		output[0]  = PLUS(x0, j0);
-		output[1]  = PLUS(x1, j1);
-		output[2]  = PLUS(x2, j2);
-		output[3]  = PLUS(x3, j3);
-		output[4]  = PLUS(x4, j4);
-		output[5]  = PLUS(x5, j5);
-		output[6]  = PLUS(x6, j6);
-		output[7]  = PLUS(x7, j7);
-		output[8]  = PLUS(x8, j8_1);
-		output[9]  = PLUS(x9, j9);
-		output[10] = PLUS(x10,j10);
-		output[11] = PLUS(x11,j11);
-		output[12] = PLUS(x12,j12);
-		output[13] = PLUS(x13,j13);
-		output[14] = PLUS(x14,j14);
-		output[15] = PLUS(x15,j15);
-
-		output += (SALSA20_GROUP_SIZE * 64) / sizeof(uint32_t);
-	}
-
-	barrier(CLK_GLOBAL_MEM_FENCE);
-
-	// Put zeroes after output's end
-	if (t < 16)
-	{
-		__global uint32_t* p = outputs + (output_offset + output_size + 3) / sizeof(uint32_t);
-		p[t] = 0;
-	}
-
-	if ((t == 0) && (output_size & 3))
-		outputs[(output_offset + output_size) / sizeof(uint32_t)] &= 0xFFFFFFFFU >> ((4 - (output_size & 3)) << 3);
-}

src/backend/opencl/cl/astrobwt/sha3.cl

@@ -1,198 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#define ROUNDS 24
-#define R64(a,b,c) (((a) << b) | ((a) >> c))
-
-__constant const uint64_t rc[2][ROUNDS] = {
-	{0x0000000000000001UL, 0x0000000000008082UL, 0x800000000000808AUL,
-	0x8000000080008000UL, 0x000000000000808BUL, 0x0000000080000001UL,
-	0x8000000080008081UL, 0x8000000000008009UL, 0x000000000000008AUL,
-	0x0000000000000088UL, 0x0000000080008009UL, 0x000000008000000AUL,
-	0x000000008000808BUL, 0x800000000000008BUL, 0x8000000000008089UL,
-	0x8000000000008003UL, 0x8000000000008002UL, 0x8000000000000080UL,
-	0x000000000000800AUL, 0x800000008000000AUL, 0x8000000080008081UL,
-	0x8000000000008080UL, 0x0000000080000001UL, 0x8000000080008008UL},
-	{0UL, 0UL, 0UL, 0UL, 0UL, 0UL, 0UL, 0UL,
-	0UL, 0UL, 0UL, 0UL, 0UL, 0UL, 0UL, 0UL,
-	0UL, 0UL, 0UL, 0UL, 0UL, 0UL, 0UL, 0UL}
-};
-
-
-__constant const int ro[25][2] = {
-	{ 0,64}, {44,20}, {43,21}, {21,43}, {14,50},
-	{ 1,63}, { 6,58}, {25,39}, { 8,56}, {18,46},
-	{62, 2}, {55, 9}, {39,25}, {41,23}, { 2,62},
-	{28,36}, {20,44}, { 3,61}, {45,19}, {61, 3},
-	{27,37}, {36,28}, {10,54}, {15,49}, {56, 8}
-};
-
-__constant const int a[25] = {
-	0,  6, 12, 18, 24,
-	1,  7, 13, 19, 20,
-	2,  8, 14, 15, 21,
-	3,  9, 10, 16, 22,
-	4,  5, 11, 17, 23
-};
-
-__constant const int b[25] = {
-	0,  1,  2,  3, 4,
-	1,  2,  3,  4, 0,
-	2,  3,  4,  0, 1,
-	3,  4,  0,  1, 2,
-	4,  0,  1,  2, 3
-};
-
-__constant const int c[25][3] = {
-	{ 0, 1, 2}, { 1, 2, 3}, { 2, 3, 4}, { 3, 4, 0}, { 4, 0, 1},
-	{ 5, 6, 7}, { 6, 7, 8}, { 7, 8, 9}, { 8, 9, 5}, { 9, 5, 6},
-	{10,11,12}, {11,12,13}, {12,13,14}, {13,14,10}, {14,10,11},
-	{15,16,17}, {16,17,18}, {17,18,19}, {18,19,15}, {19,15,16},
-	{20,21,22}, {21,22,23}, {22,23,24}, {23,24,20}, {24,20,21}
-};
-
-__constant const int d[25] = {
-	0,  1,  2,  3,  4,
-	10, 11, 12, 13, 14,
-	20, 21, 22, 23, 24,
-	5,  6,  7,  8,  9,
-	15, 16, 17, 18, 19
-};
-
-__attribute__((reqd_work_group_size(32, 1, 1)))
-__kernel void sha3(__global const uint8_t* inputs, __global const uint32_t* input_sizes, uint32_t input_stride, __global uint64_t* hashes)
-{
-	const uint32_t t = get_local_id(0);
-	const uint32_t g = get_group_id(0);
-
-	if (t >= 25)
-		return;
-
-	const uint32_t s = t % 5;
-
-	const uint64_t input_offset = ((uint64_t)input_stride) * g;
-	__global uint64_t* input = (__global uint64_t*)(inputs + input_offset);
-	const uint32_t input_size = input_sizes[g] + 1;
-
-	__local uint64_t A[25];
-	__local uint64_t C[25];
-	__local uint64_t D[25];
-
-	A[t] = 0;
-
-	const uint32_t words = input_size / sizeof(uint64_t);
-	const uint32_t tail_size = input_size % sizeof(uint64_t);
-
-	uint32_t wordIndex = 0;
-	for (uint32_t i = 0; i < words; ++i, ++input)
-	{
-		A[wordIndex] ^= *input;
-		++wordIndex;
-		if (wordIndex == 17)
-		{
-			#pragma unroll ROUNDS
-			for (int i = 0; i < ROUNDS; ++i)
-			{
-				C[t] = A[s] ^ A[s+5] ^ A[s+10] ^ A[s+15] ^ A[s+20];
-				D[t] = C[b[20+s]] ^ R64(C[b[5+s]], 1, 63);
-				C[t] = R64(A[a[t]] ^ D[b[t]], ro[t][0], ro[t][1]);
-				A[d[t]] = C[c[t][0]] ^ ((~C[c[t][1]]) & C[c[t][2]]);
-				A[t] ^= rc[(t == 0) ? 0 : 1][i];
-			}
-			wordIndex = 0;
-		}
-	}
-
-	uint64_t tail = 0;
-	__global const uint8_t* p = (__global const uint8_t*)input;
-	for (uint32_t i = 0; i < tail_size; ++i)
-	{
-		tail |= (uint64_t)(p[i]) << (i * 8);
-	}
-	A[wordIndex] ^= tail ^ ((uint64_t)(((uint64_t)(0x02 | (1 << 2))) << (tail_size * 8)));
-	A[16] ^= 0x8000000000000000UL;
-
-	#pragma unroll 1
-	for (int i = 0; i < ROUNDS; ++i)
-	{
-		C[t] = A[s] ^ A[s+5] ^ A[s+10] ^ A[s+15] ^ A[s+20];
-		D[t] = C[b[20+s]] ^ R64(C[b[5+s]], 1, 63);
-		C[t] = R64(A[a[t]] ^ D[b[t]], ro[t][0], ro[t][1]);
-		A[d[t]] = C[c[t][0]] ^ ((~C[c[t][1]]) & C[c[t][2]]);
-		A[t] ^= rc[(t == 0) ? 0 : 1][i];
-	}
-
-	if (t < 4)
-	{
-		hashes += g * (32 / sizeof(uint64_t));
-		hashes[t] = A[t];
-	}
-}
-
-__attribute__((reqd_work_group_size(32, 1, 1)))
-__kernel void sha3_initial(__global const uint8_t* input_data, uint32_t input_size, uint32_t nonce, __global uint64_t* hashes)
-{
-	const uint32_t t = get_local_id(0);
-	const uint32_t g = get_group_id(0);
-
-	if (t >= 25)
-		return;
-
-	const uint32_t s = t % 5;
-
-	__global uint64_t* input = (__global uint64_t*)(input_data);
-
-	__local uint64_t A[25];
-	__local uint64_t C[25];
-	__local uint64_t D[25];
-
-	A[t] = (t < 16) ? input[t] : 0;
-
-	__local uint32_t* nonce_pos = (__local uint32_t*)(A) + 9;
-	nonce += g;
-	nonce_pos[0] = (nonce_pos[0] & 0xFFFFFFU) | ((nonce & 0xFF) << 24);
-	nonce_pos[1] = (nonce_pos[1] & 0xFF000000U) | (nonce >> 8);
-
-	uint32_t wordIndex = input_size / sizeof(uint64_t);
-	const uint32_t tail_size = input_size % sizeof(uint64_t);
-
-	A[wordIndex] ^= (uint64_t)(((uint64_t)(0x02 | (1 << 2))) << (tail_size * 8));
-	A[16] ^= 0x8000000000000000UL;
-
-	#pragma unroll ROUNDS
-	for (int i = 0; i < ROUNDS; ++i)
-	{
-		C[t] = A[s] ^ A[s+5] ^ A[s+10] ^ A[s+15] ^ A[s+20];
-		D[t] = C[b[20+s]] ^ R64(C[b[5+s]], 1, 63);
-		C[t] = R64(A[a[t]] ^ D[b[t]], ro[t][0], ro[t][1]);
-		A[d[t]] = C[c[t][0]] ^ ((~C[c[t][1]]) & C[c[t][2]]);
-		A[t] ^= rc[(t == 0) ? 0 : 1][i];
-	}
-
-	if (t < 4)
-	{
-		hashes += g * (32 / sizeof(uint64_t));
-		hashes[t] = A[t];
-	}
-}

src/backend/opencl/cl/cn/algorithm.cl

@@ -27,7 +27,6 @@
 #define ALGO_AR2_CHUKWA     0x61130000
 #define ALGO_AR2_CHUKWA_V2  0x61140000
 #define ALGO_AR2_WRKZ       0x61120000
-#define ALGO_ASTROBWT_DERO  0x41000000
 #define ALGO_KAWPOW_RVN     0x6b0f0000
 
 #define FAMILY_UNKNOWN      0
@@ -38,5 +37,4 @@
 #define FAMILY_CN_FEMTO     0x63110000
 #define FAMILY_RANDOM_X     0x72000000
 #define FAMILY_ARGON2       0x61000000
-#define FAMILY_ASTROBWT     0x41000000
 #define FAMILY_KAWPOW       0x6b000000

src/backend/opencl/generators/ocl_generic_astrobwt_generator.cpp

@@ -1,64 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018      Lee Clagett <https://github.com/vtnerd>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-
-#include "backend/opencl/OclThreads.h"
-#include "backend/opencl/wrappers/OclDevice.h"
-#include "base/crypto/Algorithm.h"
-#include "crypto/randomx/randomx.h"
-#include "crypto/rx/RxAlgo.h"
-
-
-namespace xmrig {
-
-
-bool ocl_generic_astrobwt_generator(const OclDevice &device, const Algorithm &algorithm, OclThreads &threads)
-{
-    if (algorithm.family() != Algorithm::ASTROBWT) {
-        return false;
-    }
-
-    const size_t mem = device.globalMemSize();
-
-    uint32_t per_thread_mem = 10 << 20;
-    uint32_t intensity = static_cast<uint32_t>((mem - (128 << 20)) / per_thread_mem / 2);
-
-    intensity &= ~63U;
-
-    if (!intensity) {
-        return false;
-    }
-
-    if (intensity > 256) {
-        intensity = 256;
-    }
-
-    threads.add(OclThread(device.index(), intensity, 2));
-
-    return true;
-}
-
-
-} // namespace xmrig

src/backend/opencl/kernels/astrobwt/AstroBWT_FilterKernel.cpp

@@ -1,42 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-
-#include "backend/opencl/kernels/astrobwt/AstroBWT_FilterKernel.h"
-#include "backend/opencl/wrappers/OclLib.h"
-
-
-void xmrig::AstroBWT_FilterKernel::enqueue(cl_command_queue queue, size_t threads, size_t workgroup_size)
-{
-    enqueueNDRange(queue, 1, nullptr, &threads, &workgroup_size);
-}
-
-
-void xmrig::AstroBWT_FilterKernel::setArgs(uint32_t nonce, uint32_t bwt_max_size, cl_mem hashes, cl_mem filtered_hashes)
-{
-    setArg(0, sizeof(uint32_t), &nonce);
-    setArg(1, sizeof(uint32_t), &bwt_max_size);
-    setArg(2, sizeof(cl_mem), &hashes);
-    setArg(3, sizeof(cl_mem), &filtered_hashes);
-}

src/backend/opencl/kernels/astrobwt/AstroBWT_FilterKernel.h

@@ -1,48 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef XMRIG_ASTROBWT_FILTERKERNEL_H
-#define XMRIG_ASTROBWT_FILTERKERNEL_H
-
-
-#include "backend/opencl/wrappers/OclKernel.h"
-
-
-namespace xmrig {
-
-
-class AstroBWT_FilterKernel : public OclKernel
-{
-public:
-    inline AstroBWT_FilterKernel(cl_program program) : OclKernel(program, "filter") {}
-
-    void enqueue(cl_command_queue queue, size_t threads, size_t workgroup_size);
-    void setArgs(uint32_t nonce, uint32_t bwt_max_size, cl_mem hashes, cl_mem filtered_hashes);
-};
-
-
-} // namespace xmrig
-
-
-#endif /* XMRIG_ASTROBWT_FILTERKERNEL_H */

src/backend/opencl/kernels/astrobwt/AstroBWT_FindSharesKernel.cpp

@@ -1,47 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2019 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2019 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-
-#include "backend/opencl/kernels/astrobwt/AstroBWT_FindSharesKernel.h"
-#include "backend/opencl/wrappers/OclLib.h"
-
-
-void xmrig::AstroBWT_FindSharesKernel::enqueue(cl_command_queue queue, size_t threads, size_t workgroup_size)
-{
-    enqueueNDRange(queue, 1, nullptr, &threads, &workgroup_size);
-}
-
-
-void xmrig::AstroBWT_FindSharesKernel::setArgs(cl_mem hashes, cl_mem filtered_hashes, cl_mem shares)
-{
-    setArg(0, sizeof(cl_mem), &hashes);
-    setArg(1, sizeof(cl_mem), &filtered_hashes);
-    setArg(3, sizeof(cl_mem), &shares);
-}
-
-
-void xmrig::AstroBWT_FindSharesKernel::setTarget(uint64_t target)
-{
-    setArg(2, sizeof(uint64_t), &target);
-}

src/backend/opencl/kernels/astrobwt/AstroBWT_FindSharesKernel.h

@@ -1,49 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2019 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2019 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef XMRIG_ASTROBWTFINDSHARESKERNEL_H
-#define XMRIG_ASTROBWTFINDSHARESKERNEL_H
-
-
-#include "backend/opencl/wrappers/OclKernel.h"
-
-
-namespace xmrig {
-
-
-class AstroBWT_FindSharesKernel : public OclKernel
-{
-public:
-    inline AstroBWT_FindSharesKernel(cl_program program) : OclKernel(program, "find_shares") {}
-
-    void enqueue(cl_command_queue queue, size_t threads, size_t workgroup_size);
-    void setArgs(cl_mem hashes, cl_mem filtered_hashes, cl_mem shares);
-    void setTarget(uint64_t target);
-};
-
-
-} // namespace xmrig
-
-
-#endif /* XMRIG_ASTROBWTFINDSHARESKERNEL_H */

src/backend/opencl/kernels/astrobwt/AstroBWT_MainKernel.cpp

@@ -1,44 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-
-#include "backend/opencl/kernels/astrobwt/AstroBWT_MainKernel.h"
-#include "backend/opencl/wrappers/OclLib.h"
-
-
-void xmrig::AstroBWT_MainKernel::enqueue(cl_command_queue queue, size_t threads, size_t workgroup_size)
-{
-    const size_t gthreads       = threads * workgroup_size;
-    enqueueNDRange(queue, 1, nullptr, &gthreads, &workgroup_size);
-}
-
-
-void xmrig::AstroBWT_MainKernel::setArgs(cl_mem inputs, cl_mem input_sizes, uint32_t input_stride, cl_mem indices, cl_mem tmp_indices)
-{
-    setArg(0, sizeof(cl_mem), &inputs);
-    setArg(1, sizeof(cl_mem), &input_sizes);
-    setArg(2, sizeof(uint32_t), &input_stride);
-    setArg(3, sizeof(cl_mem), &indices);
-    setArg(4, sizeof(cl_mem), &tmp_indices);
-}

src/backend/opencl/kernels/astrobwt/AstroBWT_MainKernel.h

@@ -1,48 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef XMRIG_ASTROBWT_MAINKERNEL_H
-#define XMRIG_ASTROBWT_MAINKERNEL_H
-
-
-#include "backend/opencl/wrappers/OclKernel.h"
-
-
-namespace xmrig {
-
-
-class AstroBWT_MainKernel : public OclKernel
-{
-public:
-    inline AstroBWT_MainKernel(cl_program program) : OclKernel(program, "BWT") {}
-
-    void enqueue(cl_command_queue queue, size_t threads, size_t workgroup_size);
-    void setArgs(cl_mem inputs, cl_mem input_sizes, uint32_t input_stride, cl_mem indices, cl_mem tmp_indices);
-};
-
-
-} // namespace xmrig
-
-
-#endif /* XMRIG_ASTROBWT_MAINKERNEL_H */

src/backend/opencl/kernels/astrobwt/AstroBWT_PrepareBatch2Kernel.cpp

@@ -1,41 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-
-#include "backend/opencl/kernels/astrobwt/AstroBWT_PrepareBatch2Kernel.h"
-#include "backend/opencl/wrappers/OclLib.h"
-
-
-void xmrig::AstroBWT_PrepareBatch2Kernel::enqueue(cl_command_queue queue, size_t threads, size_t workgroup_size)
-{
-    enqueueNDRange(queue, 1, nullptr, &threads, &workgroup_size);
-}
-
-
-void xmrig::AstroBWT_PrepareBatch2Kernel::setArgs(cl_mem hashes, cl_mem filtered_hashes, cl_mem bwt_data_sizes)
-{
-    setArg(0, sizeof(cl_mem), &hashes);
-    setArg(1, sizeof(cl_mem), &filtered_hashes);
-    setArg(2, sizeof(cl_mem), &bwt_data_sizes);
-}

src/backend/opencl/kernels/astrobwt/AstroBWT_PrepareBatch2Kernel.h

@@ -1,48 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef XMRIG_ASTROBWT_PREPAREBATCH2KERNEL_H
-#define XMRIG_ASTROBWT_PREPAREBATCH2KERNEL_H
-
-
-#include "backend/opencl/wrappers/OclKernel.h"
-
-
-namespace xmrig {
-
-
-class AstroBWT_PrepareBatch2Kernel : public OclKernel
-{
-public:
-    inline AstroBWT_PrepareBatch2Kernel(cl_program program) : OclKernel(program, "prepare_batch2") {}
-
-    void enqueue(cl_command_queue queue, size_t threads, size_t workgroup_size);
-    void setArgs(cl_mem hashes, cl_mem filtered_hashes, cl_mem bwt_data_sizes);
-};
-
-
-} // namespace xmrig
-
-
-#endif /* XMRIG_ASTROBWT_PREPAREBATCH2KERNEL_H */

src/backend/opencl/kernels/astrobwt/AstroBWT_SHA3InitialKernel.cpp

@@ -1,44 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-
-#include "backend/opencl/kernels/astrobwt/AstroBWT_SHA3InitialKernel.h"
-#include "backend/opencl/wrappers/OclLib.h"
-
-
-void xmrig::AstroBWT_SHA3InitialKernel::enqueue(cl_command_queue queue, size_t threads)
-{
-    const size_t workgroup_size = 32;
-    const size_t gthreads       = threads * workgroup_size;
-    enqueueNDRange(queue, 1, nullptr, &gthreads, &workgroup_size);
-}
-
-
-void xmrig::AstroBWT_SHA3InitialKernel::setArgs(cl_mem input, uint32_t input_size, uint32_t nonce, cl_mem output_salsa20_keys)
-{
-    setArg(0, sizeof(cl_mem), &input);
-    setArg(1, sizeof(uint32_t), &input_size);
-    setArg(2, sizeof(uint32_t), &nonce);
-    setArg(3, sizeof(cl_mem), &output_salsa20_keys);
-}

src/backend/opencl/kernels/astrobwt/AstroBWT_SHA3InitialKernel.h

@@ -1,48 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef XMRIG_ASTROBWT_SHA3INITIALKERNEL_H
-#define XMRIG_ASTROBWT_SHA3INITIALKERNEL_H
-
-
-#include "backend/opencl/wrappers/OclKernel.h"
-
-
-namespace xmrig {
-
-
-class AstroBWT_SHA3InitialKernel : public OclKernel
-{
-public:
-    inline AstroBWT_SHA3InitialKernel(cl_program program) : OclKernel(program, "sha3_initial") {}
-
-    void enqueue(cl_command_queue queue, size_t threads);
-    void setArgs(cl_mem input, uint32_t input_size, uint32_t nonce, cl_mem output_salsa20_keys);
-};
-
-
-} // namespace xmrig
-
-
-#endif /* XMRIG_ASTROBWT_SHA3INITIALKERNEL_H */

src/backend/opencl/kernels/astrobwt/AstroBWT_SHA3Kernel.cpp

@@ -1,44 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-
-#include "backend/opencl/kernels/astrobwt/AstroBWT_SHA3Kernel.h"
-#include "backend/opencl/wrappers/OclLib.h"
-
-
-void xmrig::AstroBWT_SHA3Kernel::enqueue(cl_command_queue queue, size_t threads)
-{
-    const size_t workgroup_size = 32;
-    const size_t gthreads       = threads * workgroup_size;
-    enqueueNDRange(queue, 1, nullptr, &gthreads, &workgroup_size);
-}
-
-
-void xmrig::AstroBWT_SHA3Kernel::setArgs(cl_mem inputs, cl_mem input_sizes, uint32_t input_stride, cl_mem output_salsa20_keys)
-{
-    setArg(0, sizeof(cl_mem), &inputs);
-    setArg(1, sizeof(cl_mem), &input_sizes);
-    setArg(2, sizeof(uint32_t), &input_stride);
-    setArg(3, sizeof(cl_mem), &output_salsa20_keys);
-}

src/backend/opencl/kernels/astrobwt/AstroBWT_SHA3Kernel.h

@@ -1,48 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef XMRIG_ASTROBWT_SHA3KERNEL_H
-#define XMRIG_ASTROBWT_SHA3KERNEL_H
-
-
-#include "backend/opencl/wrappers/OclKernel.h"
-
-
-namespace xmrig {
-
-
-class AstroBWT_SHA3Kernel : public OclKernel
-{
-public:
-    inline AstroBWT_SHA3Kernel(cl_program program) : OclKernel(program, "sha3") {}
-
-    void enqueue(cl_command_queue queue, size_t threads);
-    void setArgs(cl_mem inputs, cl_mem input_sizes, uint32_t input_stride, cl_mem output_salsa20_keys);
-};
-
-
-} // namespace xmrig
-
-
-#endif /* XMRIG_ASTROBWT_SHA3KERNEL_H */

src/backend/opencl/kernels/astrobwt/AstroBWT_Salsa20Kernel.cpp

@@ -1,43 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-
-#include "backend/opencl/kernels/astrobwt/AstroBWT_Salsa20Kernel.h"
-#include "backend/opencl/wrappers/OclLib.h"
-
-
-void xmrig::AstroBWT_Salsa20Kernel::enqueue(cl_command_queue queue, size_t threads, size_t workgroup_size)
-{
-    const size_t gthreads       = threads * workgroup_size;
-    enqueueNDRange(queue, 1, nullptr, &gthreads, &workgroup_size);
-}
-
-
-void xmrig::AstroBWT_Salsa20Kernel::setArgs(cl_mem salsa20_keys, cl_mem outputs, cl_mem output_sizes, uint32_t output_stride)
-{
-    setArg(0, sizeof(cl_mem), &salsa20_keys);
-    setArg(1, sizeof(cl_mem), &outputs);
-    setArg(2, sizeof(cl_mem), &output_sizes);
-    setArg(3, sizeof(uint32_t), &output_stride);
-}

src/backend/opencl/kernels/astrobwt/AstroBWT_Salsa20Kernel.h

@@ -1,48 +0,0 @@
-/* XMRig
- * Copyright 2010      Jeff Garzik <jgarzik@pobox.com>
- * Copyright 2012-2014 pooler      <pooler@litecoinpool.org>
- * Copyright 2014      Lucas Jones <https://github.com/lucasjones>
- * Copyright 2014-2016 Wolf9466    <https://github.com/OhGodAPet>
- * Copyright 2016      Jay D Dee   <jayddee246@gmail.com>
- * Copyright 2017-2018 XMR-Stak    <https://github.com/fireice-uk>, <https://github.com/psychocrypt>
- * Copyright 2018-2020 SChernykh   <https://github.com/SChernykh>
- * Copyright 2016-2020 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef XMRIG_ASTROBWT_SALSA20KERNEL_H
-#define XMRIG_ASTROBWT_SALSA20KERNEL_H
-
-
-#include "backend/opencl/wrappers/OclKernel.h"
-
-
-namespace xmrig {
-
-
-class AstroBWT_Salsa20Kernel : public OclKernel
-{
-public:
-    inline AstroBWT_Salsa20Kernel(cl_program program) : OclKernel(program, "Salsa20_XORKeyStream") {}
-
-    void enqueue(cl_command_queue queue, size_t threads, size_t workgroup_size);
-    void setArgs(cl_mem salsa20_keys, cl_mem outputs, cl_mem output_sizes, uint32_t output_stride);
-};
-
-
-} // namespace xmrig
-
-
-#endif /* XMRIG_ASTROBWT_SALSA20KERNEL_H */

src/backend/opencl/opencl.cmake

@@ -110,31 +110,6 @@ if (WITH_OPENCL)
              )
     endif()
 
-    if (WITH_ASTROBWT)
-        list(APPEND HEADERS_BACKEND_OPENCL
-             src/backend/opencl/kernels/astrobwt/AstroBWT_FilterKernel.h
-             src/backend/opencl/kernels/astrobwt/AstroBWT_FindSharesKernel.h
-             src/backend/opencl/kernels/astrobwt/AstroBWT_MainKernel.h
-             src/backend/opencl/kernels/astrobwt/AstroBWT_PrepareBatch2Kernel.h
-             src/backend/opencl/kernels/astrobwt/AstroBWT_Salsa20Kernel.h
-             src/backend/opencl/kernels/astrobwt/AstroBWT_SHA3InitialKernel.h
-             src/backend/opencl/kernels/astrobwt/AstroBWT_SHA3Kernel.h
-             src/backend/opencl/runners/OclAstroBWTRunner.h
-             )
-
-        list(APPEND SOURCES_BACKEND_OPENCL
-             src/backend/opencl/generators/ocl_generic_astrobwt_generator.cpp
-             src/backend/opencl/kernels/astrobwt/AstroBWT_FilterKernel.cpp
-             src/backend/opencl/kernels/astrobwt/AstroBWT_FindSharesKernel.cpp
-             src/backend/opencl/kernels/astrobwt/AstroBWT_MainKernel.cpp
-             src/backend/opencl/kernels/astrobwt/AstroBWT_PrepareBatch2Kernel.cpp
-             src/backend/opencl/kernels/astrobwt/AstroBWT_Salsa20Kernel.cpp
-             src/backend/opencl/kernels/astrobwt/AstroBWT_SHA3InitialKernel.cpp
-             src/backend/opencl/kernels/astrobwt/AstroBWT_SHA3Kernel.cpp
-             src/backend/opencl/runners/OclAstroBWTRunner.cpp
-             )
-    endif()
-
     if (WITH_KAWPOW)
         list(APPEND HEADERS_BACKEND_OPENCL
              src/backend/opencl/kernels/kawpow/KawPow_CalculateDAGKernel.h

src/backend/opencl/runners/OclAstroBWTRunner.cpp

@@ -1,214 +0,0 @@
-/* XMRig
- * Copyright (c) 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2021 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#include "backend/opencl/runners/OclAstroBWTRunner.h"
-#include "backend/opencl/kernels/astrobwt/AstroBWT_FilterKernel.h"
-#include "backend/opencl/kernels/astrobwt/AstroBWT_FindSharesKernel.h"
-#include "backend/opencl/kernels/astrobwt/AstroBWT_MainKernel.h"
-#include "backend/opencl/kernels/astrobwt/AstroBWT_PrepareBatch2Kernel.h"
-#include "backend/opencl/kernels/astrobwt/AstroBWT_Salsa20Kernel.h"
-#include "backend/opencl/kernels/astrobwt/AstroBWT_SHA3InitialKernel.h"
-#include "backend/opencl/kernels/astrobwt/AstroBWT_SHA3Kernel.h"
-#include "backend/opencl/OclLaunchData.h"
-#include "backend/opencl/wrappers/OclLib.h"
-#include "base/io/log/Log.h"
-#include "base/net/stratum/Job.h"
-
-
-namespace xmrig {
-
-
-constexpr int STAGE1_SIZE = 147253;
-constexpr uint32_t STAGE1_DATA_STRIDE = (STAGE1_SIZE + 256 + 255) & ~255U;
-constexpr uint32_t OclAstroBWTRunner::BWT_DATA_STRIDE;
-
-
-} // namespace xmrig
-
-
-xmrig::OclAstroBWTRunner::OclAstroBWTRunner(size_t index, const OclLaunchData &data) : OclBaseRunner(index, data)
-{
-    switch (data.device.type())
-    {
-    case OclDevice::Baffin:
-    case OclDevice::Ellesmere:
-    case OclDevice::Polaris:
-    case OclDevice::Lexa:
-    case OclDevice::Vega_10:
-    case OclDevice::Vega_20:
-    case OclDevice::Raven:
-        m_workgroup_size = 64;
-        break;
-
-    default:
-        m_workgroup_size = 32;
-        break;
-    }
-
-    m_options += " -DSALSA20_GROUP_SIZE=" + std::to_string(m_workgroup_size);
-    m_options += " -DBWT_GROUP_SIZE="     + std::to_string(m_workgroup_size);
-
-    m_bwt_allocation_size = static_cast<uint64_t>(m_intensity) * BWT_DATA_STRIDE;
-    m_batch_size1 = static_cast<uint32_t>(m_bwt_allocation_size / STAGE1_DATA_STRIDE + 255U) & ~255U;
-    m_bwt_allocation_size = std::max(m_bwt_allocation_size, m_batch_size1 * STAGE1_DATA_STRIDE);
-
-    m_bwt_data_sizes_host = new uint32_t[m_batch_size1];
-}
-
-
-xmrig::OclAstroBWTRunner::~OclAstroBWTRunner()
-{
-    delete m_sha3_initial_kernel;
-    delete m_sha3_kernel;
-    delete m_salsa20_kernel;
-    delete m_bwt_kernel;
-    delete m_filter_kernel;
-    delete m_prepare_batch2_kernel;
-    delete m_find_shares_kernel;
-
-    OclLib::release(m_salsa20_keys);
-    OclLib::release(m_bwt_data);
-    OclLib::release(m_bwt_data_sizes);
-    OclLib::release(m_indices);
-    OclLib::release(m_tmp_indices);
-    OclLib::release(m_filtered_hashes);
-
-    delete [] m_bwt_data_sizes_host;
-}
-
-
-size_t xmrig::OclAstroBWTRunner::bufferSize() const
-{
-    return OclBaseRunner::bufferSize() +
-        align(m_batch_size1 * 32) +                    // m_salsa20_keys
-        align(m_bwt_allocation_size) +                 // m_bwt_data
-        align(m_batch_size1 * 4) +                     // m_bwt_data_sizes
-        align(m_bwt_allocation_size * 8) +             // m_indices
-        align(m_bwt_allocation_size * 8) +             // m_tmp_indices
-        align((m_batch_size1 + m_intensity) * 36 + 4); // m_filtered_hashes
-}
-
-
-void xmrig::OclAstroBWTRunner::run(uint32_t nonce, uint32_t *hashOutput)
-{
-    m_sha3_initial_kernel->setArg(2, sizeof(nonce), &nonce);
-    m_salsa20_kernel->setArg(3, sizeof(STAGE1_DATA_STRIDE), &STAGE1_DATA_STRIDE);
-    m_bwt_kernel->setArg(2, sizeof(STAGE1_DATA_STRIDE), &STAGE1_DATA_STRIDE);
-
-    const uint32_t t = STAGE1_DATA_STRIDE * 8;
-    m_sha3_kernel->setArg(2, sizeof(t), &t);
-    m_filter_kernel->setArg(0, sizeof(nonce), &nonce);
-
-    const uint32_t zero = 0;
-    enqueueWriteBuffer(m_output, CL_FALSE, sizeof(cl_uint) * 0xFF, sizeof(uint32_t), &zero);
-
-    m_sha3_initial_kernel->enqueue(m_queue, m_batch_size1);
-
-    for (uint32_t i = 0; i < m_batch_size1; ++i) {
-        m_bwt_data_sizes_host[i] = STAGE1_SIZE;
-    }
-
-    enqueueWriteBuffer(m_bwt_data_sizes, CL_FALSE, 0, m_batch_size1 * sizeof(uint32_t), m_bwt_data_sizes_host);
-
-    m_salsa20_kernel->enqueue(m_queue, m_batch_size1, m_workgroup_size);
-    m_bwt_kernel->enqueue(m_queue, m_batch_size1, m_workgroup_size);
-    m_sha3_kernel->enqueue(m_queue, m_batch_size1);
-    m_filter_kernel->enqueue(m_queue, m_batch_size1, m_workgroup_size);
-
-    uint32_t num_filtered_hashes = 0;
-    enqueueReadBuffer(m_filtered_hashes, CL_TRUE, 0, sizeof(num_filtered_hashes), &num_filtered_hashes);
-
-    m_processedHashes = 0;
-    while (num_filtered_hashes >= m_intensity)
-    {
-        num_filtered_hashes -= m_intensity;
-        m_processedHashes += m_intensity;
-
-        m_salsa20_kernel->setArg(3, sizeof(BWT_DATA_STRIDE), &BWT_DATA_STRIDE);
-        m_bwt_kernel->setArg(2, sizeof(BWT_DATA_STRIDE), &BWT_DATA_STRIDE);
-
-        const uint32_t t = BWT_DATA_STRIDE * 8;
-        m_sha3_kernel->setArg(2, sizeof(t), &t);
-
-        m_prepare_batch2_kernel->enqueue(m_queue, m_intensity, m_workgroup_size);
-        m_salsa20_kernel->enqueue(m_queue, m_intensity, m_workgroup_size);
-        m_bwt_kernel->enqueue(m_queue, m_intensity, m_workgroup_size);
-        m_sha3_kernel->enqueue(m_queue, m_intensity);
-
-        m_find_shares_kernel->enqueue(m_queue, m_intensity, m_workgroup_size);
-
-        finalize(hashOutput);
-
-        OclLib::finish(m_queue);
-    }
-}
-
-
-void xmrig::OclAstroBWTRunner::set(const Job &job, uint8_t *blob)
-{
-    if (job.size() > (Job::kMaxBlobSize - 4)) {
-        throw std::length_error("job size too big");
-    }
-
-    if (job.size() < Job::kMaxBlobSize) {
-        memset(blob + job.size(), 0, Job::kMaxBlobSize - job.size());
-    }
-
-    enqueueWriteBuffer(m_input, CL_TRUE, 0, Job::kMaxBlobSize, blob);
-
-    m_sha3_initial_kernel->setArgs(m_input, static_cast<uint32_t>(job.size()), *job.nonce(), m_salsa20_keys);
-    m_salsa20_kernel->setArgs(m_salsa20_keys, m_bwt_data, m_bwt_data_sizes, STAGE1_DATA_STRIDE);
-    m_bwt_kernel->setArgs(m_bwt_data, m_bwt_data_sizes, STAGE1_DATA_STRIDE, m_indices, m_tmp_indices);
-    m_sha3_kernel->setArgs(m_tmp_indices, m_bwt_data_sizes, STAGE1_DATA_STRIDE * 8, m_salsa20_keys);
-    m_filter_kernel->setArgs(*job.nonce(), BWT_DATA_MAX_SIZE, m_salsa20_keys, m_filtered_hashes);
-    m_prepare_batch2_kernel->setArgs(m_salsa20_keys, m_filtered_hashes, m_bwt_data_sizes);
-    m_find_shares_kernel->setArgs(m_salsa20_keys, m_filtered_hashes, m_output);
-    m_find_shares_kernel->setTarget(job.target());
-
-    const uint32_t zero = 0;
-    enqueueWriteBuffer(m_filtered_hashes, CL_TRUE, 0, sizeof(uint32_t), &zero);
-}
-
-
-void xmrig::OclAstroBWTRunner::build()
-{
-    OclBaseRunner::build();
-
-    m_sha3_initial_kernel   = new AstroBWT_SHA3InitialKernel(m_program);
-    m_sha3_kernel           = new AstroBWT_SHA3Kernel(m_program);
-    m_salsa20_kernel        = new AstroBWT_Salsa20Kernel(m_program);
-    m_bwt_kernel            = new AstroBWT_MainKernel(m_program);
-    m_filter_kernel         = new AstroBWT_FilterKernel(m_program);
-    m_prepare_batch2_kernel = new AstroBWT_PrepareBatch2Kernel(m_program);
-    m_find_shares_kernel    = new AstroBWT_FindSharesKernel(m_program);
-}
-
-
-void xmrig::OclAstroBWTRunner::init()
-{
-    OclBaseRunner::init();
-
-    const cl_mem_flags f = CL_MEM_READ_WRITE | CL_MEM_HOST_NO_ACCESS;
-
-    m_salsa20_keys    = createSubBuffer(f, m_batch_size1 * 32);
-    m_bwt_data        = createSubBuffer(f, m_bwt_allocation_size);
-    m_bwt_data_sizes  = createSubBuffer(CL_MEM_READ_WRITE | CL_MEM_HOST_WRITE_ONLY, m_batch_size1 * 4);
-    m_indices         = createSubBuffer(f, m_bwt_allocation_size * 8);
-    m_tmp_indices     = createSubBuffer(f, m_bwt_allocation_size * 8);
-    m_filtered_hashes = createSubBuffer(CL_MEM_READ_WRITE, (m_batch_size1 + m_intensity) * 36 + 4);
-}

src/backend/opencl/runners/OclAstroBWTRunner.h

@@ -1,89 +0,0 @@
-/* XMRig
- * Copyright (c) 2018-2021 SChernykh   <https://github.com/SChernykh>
- * Copyright (c) 2016-2021 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
- *   the Free Software Foundation, either version 3 of the License, or
- *   (at your option) any later version.
- *
- *   This program is distributed in the hope that it will be useful,
- *   but WITHOUT ANY WARRANTY; without even the implied warranty of
- *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- *   GNU General Public License for more details.
- *
- *   You should have received a copy of the GNU General Public License
- *   along with this program. If not, see <http://www.gnu.org/licenses/>.
- */
-
-#ifndef XMRIG_OCLASTROBWTRUNNER_H
-#define XMRIG_OCLASTROBWTRUNNER_H
-
-
-#include "backend/opencl/runners/OclBaseRunner.h"
-
-namespace xmrig {
-
-
-class AstroBWT_FilterKernel;
-class AstroBWT_MainKernel;
-class AstroBWT_PrepareBatch2Kernel;
-class AstroBWT_Salsa20Kernel;
-class AstroBWT_SHA3InitialKernel;
-class AstroBWT_SHA3Kernel;
-class AstroBWT_FindSharesKernel;
-
-
-class OclAstroBWTRunner : public OclBaseRunner
-{
-public:
-    static constexpr uint32_t BWT_DATA_MAX_SIZE = 600 * 1024 - 256;
-    static constexpr uint32_t BWT_DATA_STRIDE = (BWT_DATA_MAX_SIZE + 256 + 255) & ~255U;
-
-    XMRIG_DISABLE_COPY_MOVE_DEFAULT(OclAstroBWTRunner)
-
-    OclAstroBWTRunner(size_t index, const OclLaunchData &data);
-    ~OclAstroBWTRunner() override;
-
-    inline uint32_t roundSize() const override { return static_cast<uint32_t>(m_batch_size1); }
-
-    // ~0.5% of all hashes are invalid
-    inline uint32_t processedHashes() const override { return static_cast<uint32_t>(m_processedHashes * 0.995); }
-
-protected:
-    size_t bufferSize() const override;
-    void run(uint32_t nonce, uint32_t *hashOutput) override;
-    void set(const Job &job, uint8_t *blob) override;
-    void build() override;
-    void init() override;
-
-private:
-    AstroBWT_SHA3InitialKernel*   m_sha3_initial_kernel   = nullptr;
-    AstroBWT_SHA3Kernel*          m_sha3_kernel           = nullptr;
-    AstroBWT_Salsa20Kernel*       m_salsa20_kernel        = nullptr;
-    AstroBWT_MainKernel*          m_bwt_kernel            = nullptr;
-    AstroBWT_FilterKernel*        m_filter_kernel         = nullptr;
-    AstroBWT_PrepareBatch2Kernel* m_prepare_batch2_kernel = nullptr;
-    AstroBWT_FindSharesKernel*    m_find_shares_kernel    = nullptr;
-
-
-    cl_mem m_salsa20_keys                                 = nullptr;
-    cl_mem m_bwt_data                                     = nullptr;
-    cl_mem m_bwt_data_sizes                               = nullptr;
-    cl_mem m_indices                                      = nullptr;
-    cl_mem m_tmp_indices                                  = nullptr;
-    cl_mem m_filtered_hashes                              = nullptr;
-
-    uint32_t m_workgroup_size                             = 0;
-    uint64_t m_bwt_allocation_size                        = 0;
-    uint64_t m_batch_size1                                = 0;
-    uint32_t m_processedHashes                            = 0;
-
-    uint32_t* m_bwt_data_sizes_host                       = nullptr;
-};
-
-
-} /* namespace xmrig */
-
-
-#endif // XMRIG_OCLASTROBWTRUNNER_H

src/backend/opencl/runners/tools/OclKawPow.cpp

@@ -153,9 +153,35 @@ static KawPowCache cache;
 #define mix_dst()   ("mix[" + std::to_string(mix_seq_dst[(mix_seq_dst_cnt++) % KPHash::REGS]) + "]")
 #define mix_cache() ("mix[" + std::to_string(mix_seq_cache[(mix_seq_cache_cnt++) % KPHash::REGS]) + "]")
 
+class KawPowBaton : public Baton<uv_work_t>
+{
+public:
+    inline KawPowBaton(const IOclRunner& runner, uint64_t period, uint32_t worksize) :
+        runner(runner),
+        period(period),
+        worksize(worksize)
+    {}
+
+    const IOclRunner& runner;
+    const uint64_t period;
+    const uint32_t worksize;
+};
+
+
 class KawPowBuilder
 {
 public:
+    ~KawPowBuilder()
+    {
+        if (m_loop) {
+            uv_async_send(&m_shutdownAsync);
+            uv_thread_join(&m_loopThread);
+            delete m_loop;
+        }
+    }
+
+    void build_async(const IOclRunner& runner, uint64_t period, uint32_t worksize);
+
     cl_kernel build(const IOclRunner &runner, uint64_t period, uint32_t worksize)
     {
         std::lock_guard<std::mutex> lock(m_mutex);
@@ -368,40 +394,54 @@ private:
         st.jcong = 69069 * st.jcong + 1234567;
         return ((MWC ^ st.jcong) + st.jsr);
     }
-};
 
+private:
+    uv_loop_t* m_loop          = nullptr;
+    uv_thread_t m_loopThread   = {};
+    uv_async_t m_shutdownAsync = {};
 
-class KawPowBaton : public Baton<uv_work_t>
-{
-public:
-    inline KawPowBaton(const IOclRunner &runner, uint64_t period, uint32_t worksize) :
-        runner(runner),
-        period(period),
-        worksize(worksize)
-    {}
-
-    const IOclRunner &runner;
-    const uint64_t period;
-    const uint32_t worksize;
+    static void loop(void* data)
+    {
+        KawPowBuilder* builder = static_cast<KawPowBuilder*>(data);
+        uv_run(builder->m_loop, UV_RUN_DEFAULT);
+        uv_loop_close(builder->m_loop);
+    }
 };
 
 
 static KawPowBuilder builder;
 
 
+void KawPowBuilder::build_async(const IOclRunner& runner, uint64_t period, uint32_t worksize)
+{
+    std::lock_guard<std::mutex> lock(m_mutex);
+
+    if (!m_loop) {
+        m_loop = new uv_loop_t{};
+        uv_loop_init(m_loop);
+        uv_async_init(m_loop, &m_shutdownAsync, [](uv_async_t* handle) { uv_close(reinterpret_cast<uv_handle_t*>(handle), nullptr); });
+        uv_thread_create(&m_loopThread, loop, this);
+    }
+
+    KawPowBaton* baton = new KawPowBaton(runner, period, worksize);
+
+    uv_queue_work(m_loop, &baton->req,
+        [](uv_work_t* req) {
+            KawPowBaton* baton = static_cast<KawPowBaton*>(req->data);
+            builder.build(baton->runner, baton->period, baton->worksize);
+        },
+        [](uv_work_t* req, int) { delete static_cast<KawPowBaton*>(req->data); }
+    );
+}
+
+
 cl_kernel OclKawPow::get(const IOclRunner &runner, uint64_t height, uint32_t worksize)
 {
     const uint64_t period = height / KPHash::PERIOD_LENGTH;
 
-    KawPowBaton* baton = new KawPowBaton(runner, period + 1, worksize);
-
-    uv_queue_work(uv_default_loop(), &baton->req,
-        [](uv_work_t *req) {
-            KawPowBaton* baton = static_cast<KawPowBaton*>(req->data);
-            builder.build(baton->runner, baton->period, baton->worksize);
-        },
-        [](uv_work_t *req, int) { delete static_cast<KawPowBaton*>(req->data); }
-    );
+    if (!cache.search(runner, period + 1, worksize)) {
+        builder.build_async(runner, period + 1, worksize);
+    }
 
     cl_kernel kernel = cache.search(runner, period, worksize);
     if (kernel) {

src/backend/opencl/wrappers/OclDevice.cpp

@@ -47,10 +47,6 @@ namespace xmrig {
 extern bool ocl_generic_rx_generator(const OclDevice &device, const Algorithm &algorithm, OclThreads &threads);
 #endif
 
-#ifdef XMRIG_ALGO_ASTROBWT
-extern bool ocl_generic_astrobwt_generator(const OclDevice& device, const Algorithm& algorithm, OclThreads& threads);
-#endif
-
 #ifdef XMRIG_ALGO_KAWPOW
 extern bool ocl_generic_kawpow_generator(const OclDevice& device, const Algorithm& algorithm, OclThreads& threads);
 #endif
@@ -63,9 +59,6 @@ static ocl_gen_config_fun generators[] = {
 #   ifdef XMRIG_ALGO_RANDOMX
     ocl_generic_rx_generator,
 #   endif
-#   ifdef XMRIG_ALGO_ASTROBWT
-    ocl_generic_astrobwt_generator,
-#   endif
 #   ifdef XMRIG_ALGO_KAWPOW
     ocl_generic_kawpow_generator,
 #   endif

src/base/base.cmake

@@ -68,6 +68,7 @@ set(HEADERS_BASE
     src/base/net/tools/MemPool.h
     src/base/net/tools/NetBuffer.h
     src/base/net/tools/Storage.h
+    src/base/tools/Alignment.h
     src/base/tools/Arguments.h
     src/base/tools/Baton.h
     src/base/tools/bswap_64.h
@@ -132,6 +133,7 @@ set(SOURCES_BASE
     src/base/net/tools/LineReader.cpp
     src/base/net/tools/NetBuffer.cpp
     src/base/tools/Arguments.cpp
+    src/base/tools/Chrono.cpp
     src/base/tools/cryptonote/BlockTemplate.cpp
     src/base/tools/cryptonote/crypto-ops-data.c
     src/base/tools/cryptonote/crypto-ops.c

src/base/crypto/Algorithm.cpp

@@ -91,11 +91,6 @@ const char *Algorithm::kAR2_CHUKWA_V2   = "argon2/chukwav2";
 const char *Algorithm::kAR2_WRKZ        = "argon2/ninja";
 #endif
 
-#ifdef XMRIG_ALGO_ASTROBWT
-const char *Algorithm::kASTROBWT        = "astrobwt";
-const char *Algorithm::kASTROBWT_DERO   = "astrobwt";
-#endif
-
 #ifdef XMRIG_ALGO_KAWPOW
 const char *Algorithm::kKAWPOW          = "kawpow";
 const char *Algorithm::kKAWPOW_RVN      = "kawpow";
@@ -161,10 +156,6 @@ static const std::map<uint32_t, const char *> kAlgorithmNames = {
     ALGO_NAME(AR2_WRKZ),
 #   endif
 
-#   ifdef XMRIG_ALGO_ASTROBWT
-    ALGO_NAME(ASTROBWT_DERO),
-#   endif
-
 #   ifdef XMRIG_ALGO_KAWPOW
     ALGO_NAME(KAWPOW_RVN),
 #   endif
@@ -280,10 +271,6 @@ static const std::map<const char *, Algorithm::Id, aliasCompare> kAlgorithmAlias
     ALGO_ALIAS_AUTO(AR2_WRKZ),      ALGO_ALIAS(AR2_WRKZ,        "argon2/wrkz"),
 #   endif
 
-#   ifdef XMRIG_ALGO_ASTROBWT
-    ALGO_ALIAS_AUTO(ASTROBWT_DERO), ALGO_ALIAS(ASTROBWT_DERO,   "astrobwt/dero"),
-#   endif
-
 #   ifdef XMRIG_ALGO_KAWPOW
     ALGO_ALIAS_AUTO(KAWPOW_RVN),    ALGO_ALIAS(KAWPOW_RVN,      "kawpow/rvn"),
 #   endif
@@ -365,7 +352,6 @@ std::vector<xmrig::Algorithm> xmrig::Algorithm::all(const std::function<bool(con
         CN_UPX2,
         RX_0, RX_WOW, RX_ARQ, RX_GRAFT, RX_SFX, RX_KEVA,
         AR2_CHUKWA, AR2_CHUKWA_V2, AR2_WRKZ,
-        ASTROBWT_DERO,
         KAWPOW_RVN,
         GHOSTRIDER_RTM
     };

src/base/crypto/Algorithm.h

@@ -81,7 +81,6 @@ public:
         AR2_CHUKWA      = 0x61130000,   // "argon2/chukwa"    Argon2id (Chukwa).
         AR2_CHUKWA_V2   = 0x61140000,   // "argon2/chukwav2"  Argon2id (Chukwa v2).
         AR2_WRKZ        = 0x61120000,   // "argon2/wrkz"      Argon2id (WRKZ)
-        ASTROBWT_DERO   = 0x41000000,   // "astrobwt"         AstroBWT (Dero)
         KAWPOW_RVN      = 0x6b0f0000,   // "kawpow/rvn"       KawPow (RVN)
     };
 
@@ -95,7 +94,6 @@ public:
         CN_FEMTO        = 0x63110000,
         RANDOM_X        = 0x72000000,
         ARGON2          = 0x61000000,
-        ASTROBWT        = 0x41000000,
         KAWPOW          = 0x6b000000,
         GHOSTRIDER      = 0x6c000000
     };
@@ -155,11 +153,6 @@ public:
     static const char *kAR2_WRKZ;
 #   endif
 
-#   ifdef XMRIG_ALGO_ASTROBWT
-    static const char *kASTROBWT;
-    static const char *kASTROBWT_DERO;
-#   endif
-
 #   ifdef XMRIG_ALGO_KAWPOW
     static const char *kKAWPOW;
     static const char *kKAWPOW_RVN;
@@ -192,14 +185,7 @@ public:
     inline uint32_t minIntensity() const                    { return ((m_id == GHOSTRIDER_RTM) ? 8 : 1); };
     inline uint32_t maxIntensity() const                    { return isCN() ? 5 : ((m_id == GHOSTRIDER_RTM) ? 8 : 1); };
 
-    inline size_t l3() const
-    {
-#       ifdef XMRIG_ALGO_ASTROBWT
-        return m_id != ASTROBWT_DERO ? l3(m_id) : 0x100000 * 20;
-#       else
-        return l3(m_id);
-#       endif
-    }
+    inline size_t l3() const                                { return l3(m_id); }
 
     inline bool operator!=(Algorithm::Id id) const          { return m_id != id; }
     inline bool operator!=(const Algorithm &other) const    { return !isEqual(other); }

src/base/crypto/Coin.cpp

@@ -49,7 +49,6 @@ static const CoinInfo coinInfo[] = {
     { Algorithm::RX_0,            "XMR",      "Monero",       120,    1000000000000,  YELLOW_BG_BOLD( WHITE_BOLD_S " monero  ") },
     { Algorithm::CN_R,            "SUMO",     "Sumokoin",     240,    1000000000,     BLUE_BG_BOLD(   WHITE_BOLD_S " sumo    ") },
     { Algorithm::RX_ARQ,          "ARQ",      "ArQmA",        120,    1000000000,     BLUE_BG_BOLD(   WHITE_BOLD_S " arqma   ") },
-    { Algorithm::ASTROBWT_DERO, "DERO",     "DERO",         0,      0,              BLUE_BG_BOLD(   WHITE_BOLD_S " dero    ") },
     { Algorithm::RX_GRAFT,        "GRFT",     "Graft",        120,    10000000000,    BLUE_BG_BOLD(   WHITE_BOLD_S " graft   ") },
     { Algorithm::RX_KEVA,         "KVA",      "Kevacoin",     0,      0,              MAGENTA_BG_BOLD(WHITE_BOLD_S " keva    ") },
     { Algorithm::KAWPOW_RVN,      "RVN",      "Ravencoin",    0,      0,              BLUE_BG_BOLD(   WHITE_BOLD_S " raven   ") },

src/base/crypto/Coin.h

@@ -35,7 +35,6 @@ public:
         MONERO,
         SUMO,
         ARQMA,
-        DERO,
         GRAFT,
         KEVA,
         RAVEN,

src/base/crypto/keccak.cpp

@@ -53,10 +53,8 @@ const uint64_t keccakf_rndc[24] =
 
 void xmrig::keccakf(uint64_t st[25], int rounds)
 {
-    int i, j, round;
-    uint64_t t, bc[5];
-
-    for (round = 0; round < rounds; ++round) {
+    for (int round = 0; round < rounds; ++round) {
+        uint64_t bc[5];
 
         // Theta
         bc[0] = st[0] ^ st[5] ^ st[10] ^ st[15] ^ st[20];
@@ -65,17 +63,21 @@ void xmrig::keccakf(uint64_t st[25], int rounds)
         bc[3] = st[3] ^ st[8] ^ st[13] ^ st[18] ^ st[23];
         bc[4] = st[4] ^ st[9] ^ st[14] ^ st[19] ^ st[24];
 
-        for (i = 0; i < 5; ++i) {
-            t = bc[(i + 4) % 5] ^ ROTL64(bc[(i + 1) % 5], 1);
-            st[i     ] ^= t;
-            st[i +  5] ^= t;
-            st[i + 10] ^= t;
-            st[i + 15] ^= t;
-            st[i + 20] ^= t;
+#define X(i) { \
+            const uint64_t t = bc[(i + 4) % 5] ^ ROTL64(bc[(i + 1) % 5], 1); \
+            st[i     ] ^= t; \
+            st[i +  5] ^= t; \
+            st[i + 10] ^= t; \
+            st[i + 15] ^= t; \
+            st[i + 20] ^= t; \
         }
 
+        X(0); X(1); X(2); X(3); X(4);
+
+#undef X
+
         // Rho Pi
-        t = st[1];
+        const uint64_t t = st[1];
         st[ 1] = ROTL64(st[ 6], 44);
         st[ 6] = ROTL64(st[ 9], 20);
         st[ 9] = ROTL64(st[22], 61);
@@ -103,7 +105,7 @@ void xmrig::keccakf(uint64_t st[25], int rounds)
 
         //  Chi
         // unrolled loop, where only last iteration is different
-        j = 0;
+        int j = 0;
         bc[0] = st[j    ];
         bc[1] = st[j + 1];
 

src/base/kernel/interfaces/IConfig.h

@@ -111,8 +111,6 @@ public:
         CPUMaxThreadsKey     = 1026,
         MemoryPoolKey        = 1027,
         YieldKey             = 1030,
-        AstroBWTMaxSizeKey   = 1034,
-        AstroBWTAVX2Key      = 1036,
         Argon2ImplKey        = 1039,
         RandomXCacheQoSKey   = 1040,