mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-12-25 05:48:47 +01:00
cmake : ARM intrinsics detection for MSVC (#5401)
This commit is contained in:
parent
aa23412989
commit
8084d55440
@ -855,11 +855,21 @@ if (CMAKE_OSX_ARCHITECTURES STREQUAL "arm64" OR CMAKE_GENERATOR_PLATFORM_LWR STR
|
||||
CMAKE_SYSTEM_PROCESSOR MATCHES "^(aarch64|arm.*|ARM64)$"))
|
||||
message(STATUS "ARM detected")
|
||||
if (MSVC)
|
||||
add_compile_definitions(__aarch64__) # MSVC defines _M_ARM64 instead
|
||||
add_compile_definitions(__ARM_NEON)
|
||||
add_compile_definitions(__ARM_FEATURE_FMA)
|
||||
add_compile_definitions(__ARM_FEATURE_DOTPROD)
|
||||
# add_compile_definitions(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) # MSVC doesn't support vdupq_n_f16, vld1q_f16, vst1q_f16
|
||||
add_compile_definitions(__aarch64__) # MSVC defines _M_ARM64 instead
|
||||
|
||||
set(CMAKE_REQUIRED_FLAGS_PREV ${CMAKE_REQUIRED_FLAGS})
|
||||
string(JOIN " " CMAKE_REQUIRED_FLAGS ${CMAKE_REQUIRED_FLAGS} "/arch:armv8.2")
|
||||
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)
|
||||
add_compile_definitions(__ARM_FEATURE_DOTPROD)
|
||||
endif ()
|
||||
check_cxx_source_compiles("#include <arm_neon.h>\nint main() { float16_t _a; float16x8_t _s = vdupq_n_f16(_a); return 0; }" GGML_COMPILER_SUPPORT_FP16_VECTOR_ARITHMETIC)
|
||||
if (GGML_COMPILER_SUPPORT_FP16_VECTOR_ARITHMETIC)
|
||||
add_compile_definitions(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC)
|
||||
endif ()
|
||||
set(CMAKE_REQUIRED_FLAGS ${CMAKE_REQUIRED_FLAGS_PREV})
|
||||
else()
|
||||
check_cxx_compiler_flag(-mfp16-format=ieee COMPILER_SUPPORTS_FP16_FORMAT_I3E)
|
||||
if (NOT "${COMPILER_SUPPORTS_FP16_FORMAT_I3E}" STREQUAL "")
|
||||
|
Loading…
Reference in New Issue
Block a user