ggml-cpu: cmake add arm64 cpu feature check for macos (#10487)

* ggml-cpu: cmake add arm64 cpu feature check for macos

* use vmmlaq_s32 for compile option i8mm check
This commit is contained in:
Charles Xu 2024-11-26 12:37:05 +01:00 committed by GitHub
parent 84e1c33cde
commit 25669aa92c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194

View File

@ -96,6 +96,39 @@ if (CMAKE_OSX_ARCHITECTURES STREQUAL "arm64" OR
endif () endif ()
set(CMAKE_REQUIRED_FLAGS ${CMAKE_REQUIRED_FLAGS_PREV}) set(CMAKE_REQUIRED_FLAGS ${CMAKE_REQUIRED_FLAGS_PREV})
elseif (APPLE)
if (GGML_NATIVE)
set(USER_PROVIDED_MARCH FALSE)
foreach(flag_var IN ITEMS CMAKE_C_FLAGS CMAKE_CXX_FLAGS CMAKE_REQUIRED_FLAGS)
if ("${${flag_var}}" MATCHES "-march=[a-zA-Z0-9+._-]+")
set(USER_PROVIDED_MARCH TRUE)
break()
endif()
endforeach()
if (NOT USER_PROVIDED_MARCH)
set(MARCH_FLAGS "-march=armv8.2a")
check_cxx_source_compiles("#include <arm_neon.h>\nint main() { int8x16_t _a, _b; int32x4_t _s = vdotq_s32(_s, _a, _b); return 0; }" GGML_COMPILER_SUPPORT_DOTPROD)
if (GGML_COMPILER_SUPPORT_DOTPROD)
set(MARCH_FLAGS "${MARCH_FLAGS}+dotprod")
add_compile_definitions(__ARM_FEATURE_DOTPROD)
endif ()
set(TEST_I8MM_FLAGS "-march=armv8.2a+i8mm")
set(CMAKE_REQUIRED_FLAGS_SAVE ${CMAKE_REQUIRED_FLAGS})
set(CMAKE_REQUIRED_FLAGS "${CMAKE_REQUIRED_FLAGS} ${TEST_I8MM_FLAGS}")
check_cxx_source_compiles("#include <arm_neon.h>\nint main() { int8x16_t _a, _b; int32x4_t _s = vmmlaq_s32(_s, _a, _b); return 0; }" GGML_COMPILER_SUPPORT_MATMUL_INT8)
if (GGML_COMPILER_SUPPORT_MATMUL_INT8)
set(MARCH_FLAGS "${MARCH_FLAGS}+i8mm")
add_compile_definitions(__ARM_FEATURE_MATMUL_INT8)
endif ()
set(CMAKE_REQUIRED_FLAGS ${CMAKE_REQUIRED_FLAGS_SAVE})
list(APPEND ARCH_FLAGS "${MARCH_FLAGS}")
endif ()
endif ()
else() else()
check_cxx_compiler_flag(-mfp16-format=ieee COMPILER_SUPPORTS_FP16_FORMAT_I3E) check_cxx_compiler_flag(-mfp16-format=ieee COMPILER_SUPPORTS_FP16_FORMAT_I3E)
if (NOT "${COMPILER_SUPPORTS_FP16_FORMAT_I3E}" STREQUAL "") if (NOT "${COMPILER_SUPPORTS_FP16_FORMAT_I3E}" STREQUAL "")