Skip to content

Commit

Permalink
Add GGML_MUSA in CMake
Browse files Browse the repository at this point in the history
Signed-off-by: Xiaodong Ye <[email protected]>
  • Loading branch information
yeahdongcn committed Jul 12, 2024
1 parent 59db73d commit ca22c6d
Show file tree
Hide file tree
Showing 2 changed files with 61 additions and 8 deletions.
1 change: 1 addition & 0 deletions ggml/CMakeLists.txt
Original file line number Diff line number Diff line change
Expand Up @@ -107,6 +107,7 @@ set(GGML_BLAS_VENDOR ${GGML_BLAS_VENDOR_DEFAULT} CACHE STRING
option(GGML_LLAMAFILE "ggml: use LLAMAFILE" OFF)

option(GGML_CUDA "ggml: use CUDA" OFF)
option(GGML_MUSA "ggml: use MUSA" OFF)
option(GGML_CUDA_FORCE_DMMV "ggml: use dmmv instead of mmvq CUDA kernels" OFF)
option(GGML_CUDA_FORCE_MMQ "ggml: use mmq kernels instead of cuBLAS" OFF)
option(GGML_CUDA_FORCE_CUBLAS "ggml: always use cuBLAS instead of mmq kernels" OFF)
Expand Down
68 changes: 60 additions & 8 deletions ggml/src/CMakeLists.txt
Original file line number Diff line number Diff line change
Expand Up @@ -139,6 +139,19 @@ if (GGML_METAL)
)
endif()

if (GGML_MUSA)
set(CMAKE_C_COMPILER clang)
set(CMAKE_C_EXTENSIONS OFF)
set(CMAKE_CXX_COMPILER clang++)
set(CMAKE_CXX_EXTENSIONS OFF)

set(GGML_CUDA ON)

list(APPEND GGML_CDEF_PUBLIC GGML_USE_MUSA)

add_compile_definitions(GGML_USE_MUSA)
endif()

if (GGML_OPENMP)
find_package(OpenMP)
if (OpenMP_FOUND)
Expand All @@ -147,6 +160,11 @@ if (GGML_OPENMP)
add_compile_definitions(GGML_USE_OPENMP)

set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} OpenMP::OpenMP_C OpenMP::OpenMP_CXX)

if (GGML_MUSA)
set(GGML_EXTRA_INCLUDES ${GGML_EXTRA_INCLUDES} "/usr/lib/llvm-10/include/openmp")
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} "/usr/lib/llvm-10/lib/libomp.so")
endif()
else()
message(WARNING "OpenMP not found")
endif()
Expand Down Expand Up @@ -249,7 +267,13 @@ endif()
if (GGML_CUDA)
cmake_minimum_required(VERSION 3.18) # for CMAKE_CUDA_ARCHITECTURES

find_package(CUDAToolkit)
if (GGML_MUSA)
list(APPEND CMAKE_MODULE_PATH "/usr/local/musa/cmake/")
find_package(MUSAToolkit)
set(CUDAToolkit_FOUND ${MUSAToolkit_FOUND})
else()
find_package(CUDAToolkit)
endif()

if (CUDAToolkit_FOUND)
message(STATUS "CUDA found")
Expand All @@ -268,7 +292,11 @@ if (GGML_CUDA)
endif()
message(STATUS "Using CUDA architectures: ${CMAKE_CUDA_ARCHITECTURES}")

enable_language(CUDA)
if (GGML_MUSA)
set(CMAKE_CUDA_COMPILER ${MUSAToolkit_MCC_EXECUTABLE})
else()
enable_language(CUDA)
endif()

file(GLOB GGML_HEADERS_CUDA "ggml-cuda/*.cuh")
list(APPEND GGML_HEADERS_CUDA "../include/ggml-cuda.h")
Expand Down Expand Up @@ -332,21 +360,40 @@ if (GGML_CUDA)
add_compile_definitions(GGML_CUDA_NO_PEER_COPY)
endif()

if (GGML_MUSA)
set_source_files_properties(${GGML_SOURCES_CUDA} PROPERTIES LANGUAGE CXX)
foreach(SOURCE ${GGML_SOURCES_CUDA})
set_property(SOURCE ${SOURCE} PROPERTY COMPILE_FLAGS "-x musa -mtgpu --cuda-gpu-arch=mp_22")
endforeach()
endif()

if (GGML_STATIC)
if (WIN32)
# As of 12.3.1 CUDA Toolkit for Windows does not offer a static cublas library
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cudart_static CUDA::cublas CUDA::cublasLt)
else ()
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cudart_static CUDA::cublas_static CUDA::cublasLt_static)
if (GGML_MUSA)
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} MUSA::musart_static MUSA::mublas_static)
else()
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cudart_static CUDA::cublas_static CUDA::cublasLt_static)
endif()
endif()
else()
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cudart CUDA::cublas CUDA::cublasLt)
if (GGML_MUSA)
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} MUSA::musart MUSA::mublas)
else()
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cudart CUDA::cublas CUDA::cublasLt)
endif()
endif()

if (GGML_CUDA_NO_VMM)
# No VMM requested, no need to link directly with the cuda driver lib (libcuda.so)
else()
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cuda_driver) # required by cuDeviceGetAttribute(), cuMemGetAllocationGranularity(...), ...
if (GGML_MUSA)
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} MUSA::musa_driver) # required by muDeviceGetAttribute(), muMemGetAllocationGranularity(...), ...
else()
set(GGML_EXTRA_LIBS ${GGML_EXTRA_LIBS} CUDA::cuda_driver) # required by cuDeviceGetAttribute(), cuMemGetAllocationGranularity(...), ...
endif()
endif()
else()
message(WARNING "CUDA not found")
Expand Down Expand Up @@ -757,8 +804,10 @@ function(get_flags CCID CCVER)
set(C_FLAGS -Wdouble-promotion)
set(CXX_FLAGS -Wno-array-bounds)

if (CCVER VERSION_GREATER_EQUAL 7.1.0)
list(APPEND CXX_FLAGS -Wno-format-truncation)
if (NOT GGML_MUSA)
if (CCVER VERSION_GREATER_EQUAL 7.1.0)
list(APPEND CXX_FLAGS -Wno-format-truncation)
endif()
endif()
if (CCVER VERSION_GREATER_EQUAL 8.1.0)
list(APPEND CXX_FLAGS -Wextra-semi)
Expand Down Expand Up @@ -1059,7 +1108,9 @@ if (GGML_CUDA)
list(JOIN CUDA_CXX_FLAGS " " CUDA_CXX_FLAGS_JOINED) # pass host compiler flags as a single argument

if (NOT CUDA_CXX_FLAGS_JOINED STREQUAL "")
list(APPEND CUDA_FLAGS -Xcompiler ${CUDA_CXX_FLAGS_JOINED})
# list(APPEND CUDA_FLAGS -Xcompiler ${CUDA_CXX_FLAGS_JOINED})
# XXX: Removed flags: -Xcompiler
list(APPEND CUDA_FLAGS ${CUDA_CXX_FLAGS_JOINED})
endif()

add_compile_options("$<$<COMPILE_LANGUAGE:CUDA>:${CUDA_FLAGS}>")
Expand Down Expand Up @@ -1163,6 +1214,7 @@ endif()
target_compile_definitions(ggml PUBLIC ${GGML_CDEF_PUBLIC})
target_include_directories(ggml PUBLIC ../include)
target_include_directories(ggml PRIVATE . ${GGML_EXTRA_INCLUDES})
target_link_directories(ggml PRIVATE ${GGML_EXTRA_LIBDIRS})
target_compile_features (ggml PRIVATE c_std_11) # don't bump

target_link_libraries(ggml PRIVATE Threads::Threads ${GGML_EXTRA_LIBS})
Expand Down

0 comments on commit ca22c6d

Please sign in to comment.