mirror of
https://github.com/pytorch/pytorch.git
synced 2025-10-20 21:14:14 +08:00
44f19c7179
Fixes #ISSUE_NUMBER Currently the XPU and XCCL build settings are not recorded in the compiled binary and are not shown using the `torch.__config__.show()` which is a quick way to check if the binary has been built with such support. Below is the output adding them (see end of last line): ``` Python 3.12.8 | packaged by conda-forge | (main, Dec 5 2024, 14:24:40) [GCC 13.3.0] on linux Type "help", "copyright", "credits" or "license" for more information. >>> import torch >>> print(torch.__config__.show()) PyTorch built with: - GCC 13.3 - C++ Version: 201703 - Intel(R) oneAPI Math Kernel Library Version 2025.1-Product Build 20250203 for Intel(R) 64 architecture applications - Intel(R) MKL-DNN v3.5.3 (Git Hash 66f0cb9eb66affd2da3bf5f8d897376f04aae6af) - OpenMP 201511 (a.k.a. OpenMP 4.5) - LAPACK is enabled (usually provided by MKL) - CPU capability usage: AVX512 XPU backend - Build settings: BLAS_INFO=mkl, BUILD_TYPE=RelWithDebInfo, COMMIT_SHA=43eb39d7c832b5560f7bfa8d29cc7919ac21c0ca, CXX_COMPILER=/home/pkourdis/compilers/gcc-13.3.0/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=1 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DUSE_KINETO -DLIBKINETO_NOCUPTI -DLIBKINETO_NOROCTRACER -DLIBKINETO_NOXPUPTI=OFF -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=range-loop-construct -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-unknown-pragmas -Wno-unused-parameter -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-dangling-reference -Wno-error=dangling-reference -Wno-error=redundant-move -DUSE_XPU -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, TORCH_VERSION=2.7.0, USE_CUDA=0, USE_CUDNN=OFF, USE_CUSPARSELT=OFF, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=1, USE_MPI=0, USE_NCCL=OFF, USE_NNPACK=0, USE_OPENMP=ON, USE_ROCM=0, USE_ROCM_KERNEL_ASSERT=OFF, USE_XCCL=1, USE_XPU=1, ``` Pull Request resolved: https://github.com/pytorch/pytorch/pull/147161 Approved by: https://github.com/guangyey, https://github.com/EikanWang, https://github.com/albanD Co-authored-by: Yu, Guangye <106960996+guangyey@users.noreply.github.com>
71 lines
2.5 KiB
C
71 lines
2.5 KiB
C
// Automatically generated header file for caffe2 macros. These
|
|
// macros are used to build the Caffe2 binary, and if you are
|
|
// building a dependent library, they will need to be set as well
|
|
// for your program to link correctly.
|
|
|
|
#pragma once
|
|
|
|
#cmakedefine CAFFE2_BUILD_SHARED_LIBS
|
|
#cmakedefine CAFFE2_FORCE_FALLBACK_CUDA_MPI
|
|
#cmakedefine CAFFE2_HAS_MKL_DNN
|
|
#cmakedefine CAFFE2_HAS_MKL_SGEMM_PACK
|
|
#cmakedefine CAFFE2_PERF_WITH_AVX
|
|
#cmakedefine CAFFE2_PERF_WITH_AVX2
|
|
#cmakedefine CAFFE2_THREADPOOL_MAIN_IMBALANCE
|
|
#cmakedefine CAFFE2_THREADPOOL_STATS
|
|
#cmakedefine CAFFE2_USE_ACCELERATE
|
|
#cmakedefine CAFFE2_USE_CUDNN
|
|
#cmakedefine CAFFE2_USE_EIGEN_FOR_BLAS
|
|
#cmakedefine CAFFE2_USE_FBCODE
|
|
#cmakedefine CAFFE2_USE_GOOGLE_GLOG
|
|
#cmakedefine CAFFE2_USE_LITE_PROTO
|
|
#cmakedefine CAFFE2_USE_MKL
|
|
#cmakedefine USE_MKLDNN
|
|
#cmakedefine CAFFE2_USE_NVTX
|
|
#cmakedefine CAFFE2_USE_ITT
|
|
|
|
#ifndef EIGEN_MPL2_ONLY
|
|
#cmakedefine EIGEN_MPL2_ONLY
|
|
#endif
|
|
|
|
// Useful build settings that are recorded in the compiled binary
|
|
// torch.__config__.show()
|
|
#define CAFFE2_BUILD_STRINGS { \
|
|
{"TORCH_VERSION", "${TORCH_VERSION}"}, \
|
|
{"CXX_COMPILER", "${CMAKE_CXX_COMPILER}"}, \
|
|
{"CXX_FLAGS", "${CMAKE_CXX_FLAGS}"}, \
|
|
{"BUILD_TYPE", "${CMAKE_BUILD_TYPE}"}, \
|
|
{"BLAS_INFO", "${BLAS_INFO}"}, \
|
|
{"LAPACK_INFO", "${LAPACK_INFO}"}, \
|
|
{"USE_CUDA", "${USE_CUDA}"}, \
|
|
{"USE_ROCM", "${USE_ROCM}"}, \
|
|
{"CUDA_VERSION", "${CUDA_VERSION}"}, \
|
|
{"ROCM_VERSION", "${ROCM_VERSION}"}, \
|
|
{"USE_CUDNN", "${USE_CUDNN}"}, \
|
|
{"COMMIT_SHA", "${COMMIT_SHA}"}, \
|
|
{"CUDNN_VERSION", "${CUDNN_VERSION}"}, \
|
|
{"USE_NCCL", "${USE_NCCL}"}, \
|
|
{"USE_MPI", "${USE_MPI}"}, \
|
|
{"USE_GFLAGS", "${USE_GFLAGS}"}, \
|
|
{"USE_GLOG", "${USE_GLOG}"}, \
|
|
{"USE_GLOO", "${USE_GLOO}"}, \
|
|
{"USE_NNPACK", "${USE_NNPACK}"}, \
|
|
{"USE_OPENMP", "${USE_OPENMP}"}, \
|
|
{"FORCE_FALLBACK_CUDA_MPI", "${CAFFE2_FORCE_FALLBACK_CUDA_MPI}"}, \
|
|
{"HAS_MKL_DNN", "${CAFFE2_HAS_MKL_DNN}"}, \
|
|
{"HAS_MKL_SGEMM_PACK", "${CAFFE2_HAS_MKL_SGEMM_PACK}"}, \
|
|
{"PERF_WITH_AVX", "${CAFFE2_PERF_WITH_AVX}"}, \
|
|
{"PERF_WITH_AVX2", "${CAFFE2_PERF_WITH_AVX2}"}, \
|
|
{"USE_ACCELERATE", "${CAFFE2_USE_ACCELERATE}"}, \
|
|
{"USE_EIGEN_FOR_BLAS", "${CAFFE2_USE_EIGEN_FOR_BLAS}"}, \
|
|
{"USE_LITE_PROTO", "${CAFFE2_USE_LITE_PROTO}"}, \
|
|
{"USE_MKL", "${CAFFE2_USE_MKL}"}, \
|
|
{"USE_MKLDNN", "${USE_MKLDNN}"}, \
|
|
{"USE_NVTX", "${CAFFE2_USE_NVTX}"}, \
|
|
{"USE_ITT", "${CAFFE2_USE_ITT}"}, \
|
|
{"USE_ROCM_KERNEL_ASSERT", "${USE_ROCM_KERNEL_ASSERT}"}, \
|
|
{"USE_CUSPARSELT", "${USE_CUSPARSELT}"}, \
|
|
{"USE_XPU", "${USE_XPU}"}, \
|
|
{"USE_XCCL", "${USE_XCCL}"}, \
|
|
}
|