vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

ggml: GGML_NATIVE uses -mcpu=native on ARM

Browse source 
Signed-off-by: Adrien Gallouët <angt@huggingface.co>
This commit is contained in:
Adrien Gallouët 2024-12-10 11:08:02 +00:00
parent 4da69d1abd
commit 7eb81e1603
2 changed files with 31 additions and 66 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml/CMakeLists.txt
View file

@ -75,7 +75,7 @@ endif()
# general # general
option(GGML_STATIC "ggml: static link libraries" OFF) option(GGML_STATIC "ggml: static link libraries" OFF)
option(GGML_NATIVE "ggml: enable -march=native flag" ${GGML_NATIVE_DEFAULT}) option(GGML_NATIVE "ggml: optimize the build for the current system" ${GGML_NATIVE_DEFAULT})
option(GGML_LTO "ggml: enable link time optimization" OFF) option(GGML_LTO "ggml: enable link time optimization" OFF)
option(GGML_CCACHE "ggml: use ccache if available" ON) option(GGML_CCACHE "ggml: use ccache if available" ON)

41
ggml/src/ggml-cpu/CMakeLists.txt
View file

@ -111,45 +111,9 @@ function(ggml_add_cpu_backend_variant_impl tag_name)
endif () endif ()
set(CMAKE_REQUIRED_FLAGS ${CMAKE_REQUIRED_FLAGS_PREV}) set(CMAKE_REQUIRED_FLAGS ${CMAKE_REQUIRED_FLAGS_PREV})
elseif (APPLE) else()
if (GGML_NATIVE) if (GGML_NATIVE)
set(USER_PROVIDED_MARCH FALSE) list(APPEND ARCH_FLAGS -mcpu=native)
foreach(flag_var IN ITEMS CMAKE_C_FLAGS CMAKE_CXX_FLAGS CMAKE_REQUIRED_FLAGS)
if ("${${flag_var}}" MATCHES "-march=[a-zA-Z0-9+._-]+")
set(USER_PROVIDED_MARCH TRUE)
break()
endif()
endforeach()
if (NOT USER_PROVIDED_MARCH)
set(MARCH_FLAGS "-march=armv8.2a")
check_cxx_source_compiles("#include <arm_neon.h>\nint main() { int8x16_t _a, _b; int32x4_t _s = vdotq_s32(_s, _a, _b); return 0; }" GGML_COMPILER_SUPPORT_DOTPROD)
if (GGML_COMPILER_SUPPORT_DOTPROD)
set(MARCH_FLAGS "${MARCH_FLAGS}+dotprod")
list(APPEND ARCH_DEFINITIONS __ARM_FEATURE_DOTPROD)
message(STATUS "ARM feature DOTPROD enabled")
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")
list(APPEND ARCH_DEFINITIONS __ARM_FEATURE_MATMUL_INT8)
message(STATUS "ARM feature MATMUL_INT8 enabled")
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 "")
@ -177,6 +141,7 @@ function(ggml_add_cpu_backend_variant_impl tag_name)
list(APPEND ARCH_FLAGS -march=armv8.6-a+sve) list(APPEND ARCH_FLAGS -march=armv8.6-a+sve)
endif() endif()
endif() endif()
endif()
elseif (CMAKE_OSX_ARCHITECTURES STREQUAL "x86_64" OR CMAKE_GENERATOR_PLATFORM_LWR MATCHES "^(x86_64|i686|amd64|x64|win32)$" OR elseif (CMAKE_OSX_ARCHITECTURES STREQUAL "x86_64" OR CMAKE_GENERATOR_PLATFORM_LWR MATCHES "^(x86_64|i686|amd64|x64|win32)$" OR
(NOT CMAKE_OSX_ARCHITECTURES AND NOT CMAKE_GENERATOR_PLATFORM_LWR AND (NOT CMAKE_OSX_ARCHITECTURES AND NOT CMAKE_GENERATOR_PLATFORM_LWR AND
CMAKE_SYSTEM_PROCESSOR MATCHES "^(x86_64|i686|AMD64|amd64)$")) CMAKE_SYSTEM_PROCESSOR MATCHES "^(x86_64|i686|AMD64|amd64)$"))