EngineX-Ascend/enginex-ascend-910-llama.cpp
10
0
Fork 0
Code Issues Pull Requests Actions 4 Projects Releases Wiki Activity

SYCL: Rename oneMKL to oneMath (#12192)

Browse Source 
* Rename oneMKL Interface to oneMath

* Use oneMath for Intel vendor

* Rename occurences to mkl

* clang-format

* Silence verbose warnings

* Set oneMath HIP_TARGETS

* Fix silence warnings

* Remove step to build oneMath from build instructions

* Use fixed oneMath version

* Remove INTEL_CPU

* Fold CMake oneDNN conditions

* Use Intel oneMKL for Intel devices

* Improve CMake message

* Link against MKL::MKL_SYCL::BLAS only

* Move oneMath documentation to Nvidia and AMD sections
This commit is contained in:
Romain Biessy
2025-04-01 10:24:29 +02:00
committed by GitHub
parent 8bbf26083d
commit 8293970542
5 changed files with 189 additions and 181 deletions
Download Patch File Download Diff File Expand all files Collapse all files

111
ggml/src/ggml-sycl/CMakeLists.txt
View File

@@ -23,6 +23,23 @@ ggml_add_backend_library(ggml-sycl
../../include/ggml-sycl.h
)
file(GLOB GGML_HEADERS_SYCL "*.hpp")
file(GLOB GGML_SOURCES_SYCL "*.cpp")
target_sources(ggml-sycl PRIVATE ${GGML_HEADERS_SYCL} ${GGML_SOURCES_SYCL})
find_package(IntelSYCL)
if (IntelSYCL_FOUND)
# Use oneAPI CMake when possible
target_link_libraries(ggml-sycl PRIVATE IntelSYCL::SYCL_CXX)
else()
# Fallback to the simplest way of enabling SYCL when using intel/llvm nightly for instance
target_compile_options(ggml-sycl PRIVATE "-fsycl")
target_link_options(ggml-sycl PRIVATE "-fsycl")
endif()
target_compile_options(ggml-sycl PRIVATE "-Wno-narrowing")
# Link against oneDNN
find_package(DNNL)
set(GGML_SYCL_DNNL 0)
if(DNNL_FOUND)
@@ -62,8 +79,6 @@ if (GGML_SYCL_F16)
add_compile_definitions(GGML_SYCL_F16)
endif()
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Wno-narrowing -fsycl")
if (GGML_SYCL_TARGET STREQUAL "NVIDIA")
add_compile_definitions(GGML_SYCL_WARP_SIZE=32)
elseif (GGML_SYCL_TARGET STREQUAL "AMD")
@@ -76,34 +91,84 @@ else()
add_compile_definitions(GGML_SYCL_WARP_SIZE=16)
endif()
file(GLOB GGML_HEADERS_SYCL "*.hpp")
file(GLOB GGML_SOURCES_SYCL "*.cpp")
target_sources(ggml-sycl PRIVATE ${GGML_HEADERS_SYCL} ${GGML_SOURCES_SYCL})
if (GGML_SYCL_GRAPH)
target_compile_definitions(ggml-sycl PRIVATE GGML_SYCL_GRAPH)
endif()
if (WIN32)
find_package(IntelSYCL REQUIRED)
# Link against Intel oneMKL or oneMath
if (GGML_SYCL_TARGET STREQUAL "INTEL")
# Intel devices use Intel oneMKL directly instead of oneMath to avoid the limitation of linking Intel oneMKL statically
# See https://github.com/uxlfoundation/oneMath/issues/654
find_package(MKL REQUIRED)
target_link_libraries(ggml-sycl PRIVATE IntelSYCL::SYCL_CXX MKL::MKL MKL::MKL_SYCL)
target_link_libraries(ggml-sycl PRIVATE MKL::MKL_SYCL::BLAS)
target_compile_definitions(ggml-sycl PRIVATE GGML_SYCL_USE_INTEL_ONEMKL)
else()
if (GGML_SYCL_GRAPH)
add_compile_definitions(GGML_SYCL_GRAPH)
find_package(oneMath QUIET)
if (NOT oneMath_FOUND)
message(STATUS "oneMath not found: oneMath will be automatically downloaded")
# Use FetchContent to automatically pull and build oneMath
include(FetchContent)
set(BUILD_FUNCTIONAL_TESTS False)
set(BUILD_EXAMPLES False)
set(TARGET_DOMAINS blas)
if (GGML_SYCL_TARGET STREQUAL "NVIDIA")
set(ENABLE_MKLCPU_BACKEND False)
set(ENABLE_MKLGPU_BACKEND False)
set(ENABLE_CUBLAS_BACKEND True)
elseif (GGML_SYCL_TARGET STREQUAL "AMD")
set(ENABLE_MKLCPU_BACKEND False)
set(ENABLE_MKLGPU_BACKEND False)
set(ENABLE_ROCBLAS_BACKEND True)
# Ensure setting a string variable here is not overriden by oneMath CACHE variables
cmake_policy(SET CMP0126 NEW)
# Setting the device architecture is only needed and useful for AMD devices in oneMath
set(HIP_TARGETS ${GGML_SYCL_DEVICE_ARCH} CACHE STRING "oneMath HIP target" FORCE)
endif()
FetchContent_Declare(
ONEMATH
GIT_REPOSITORY https://github.com/uxlfoundation/oneMath.git
GIT_TAG c255b1b4c41e2ee3059455c1f96a965d6a62568a
)
FetchContent_MakeAvailable(ONEMATH)
# Create alias to match with find_package targets name
function(onemath_alias target)
if (TARGET ${target}_obj)
# Silence verbose warnings from external libraries
target_compile_options(${target}_obj PRIVATE -w)
endif()
if (TARGET ${target})
add_library(ONEMATH::${target} ALIAS ${target})
endif()
endfunction()
onemath_alias(onemath)
onemath_alias(onemath_blas_mklcpu)
onemath_alias(onemath_blas_mklgpu)
onemath_alias(onemath_blas_cublas)
onemath_alias(onemath_blas_rocblas)
endif()
if (GGML_SYCL_TARGET STREQUAL "INTEL")
target_link_libraries(ggml-sycl PRIVATE sycl OpenCL mkl_core pthread m dl mkl_sycl_blas mkl_intel_ilp64 mkl_tbb_thread)
elseif (GGML_SYCL_TARGET STREQUAL "NVIDIA")
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsycl-targets=nvptx64-nvidia-cuda")
add_compile_definitions(GGML_SYCL_NVIDIA)
target_link_libraries(ggml-sycl PRIVATE sycl pthread m dl onemkl_blas_cublas)
# Below oneMath compile-time dispatching is used for better performance
if (GGML_SYCL_TARGET STREQUAL "NVIDIA")
target_link_libraries(ggml-sycl PRIVATE ONEMATH::onemath_blas_cublas)
target_compile_options(ggml-sycl PRIVATE "-fsycl-targets=nvptx64-nvidia-cuda")
target_link_options(ggml-sycl PRIVATE "-fsycl-targets=nvptx64-nvidia-cuda")
target_compile_definitions(ggml-sycl PRIVATE GGML_SYCL_NVIDIA)
elseif (GGML_SYCL_TARGET STREQUAL "AMD")
if (NOT GGML_SYCL_DEVICE_ARCH)
message(ERROR "Can't enable SYCL hip backend, GGML_SYCL_DEVICE_ARCH has not been set.")
endif()
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -fsycl-targets=amdgcn-amd-amdhsa")
target_link_libraries(ggml-sycl PRIVATE sycl pthread m dl onemkl)
target_link_libraries(ggml-sycl PRIVATE ONEMATH::onemath_blas_rocblas)
target_compile_options(ggml-sycl PRIVATE "-fsycl-targets=amdgcn-amd-amdhsa")
target_link_options(ggml-sycl PRIVATE "-fsycl-targets=amdgcn-amd-amdhsa")
target_compile_definitions(ggml-sycl PRIVATE GGML_SYCL_AMD)
else()
# Fallback to oneMath runtime dispatcher
target_link_libraries(ggml-sycl PRIVATE ONEMATH::onemath)
target_compile_definitions(ggml-sycl PRIVATE GGML_SYCL_GENERIC)
endif()
if (GGML_SYCL_DEVICE_ARCH)
set(CMAKE_CXX_FLAGS "${CMAKE_CXX_FLAGS} -Xsycl-target-backend --offload-arch=${GGML_SYCL_DEVICE_ARCH}")
endif()
endif()
if (GGML_SYCL_DEVICE_ARCH)
target_compile_options(ggml-sycl PRIVATE -Xsycl-target-backend --offload-arch=${GGML_SYCL_DEVICE_ARCH})
target_link_options(ggml-sycl PRIVATE -Xsycl-target-backend --offload-arch=${GGML_SYCL_DEVICE_ARCH})
endif()