cmake : make LLAMA_NATIVE flag actually use the instructions supported by the processor (#3273)
* fix LLAMA_NATIVE
* syntax
* alternate implementation
* my eyes must be getting bad...
* set cmake LLAMA_NATIVE=ON by default
* march=native doesn't work for ios/tvos, so disable for those targets. also see what happens if we use it on msvc
* revert 8283237 and only allow LLAMA_NATIVE on x86 like the Makefile
* remove -DLLAMA_MPI=ON
---------
Co-authored-by: netrunnereve <netrunnereve@users.noreply.github.com>
This commit is contained in:
Eve
GitHub
parent
ff5a3f0c09
commit
017efe899d
16
.github/workflows/build.yml
vendored
16
.github/workflows/build.yml
vendored
|
|
@ -188,7 +188,7 @@ jobs:
|
|||
sysctl -a
|
||||
mkdir build
|
||||
cd build
|
||||
cmake -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF ..
|
||||
cmake ..
|
||||
cmake --build . --config Release -j $(sysctl -n hw.logicalcpu)
|
||||
|
||||
- name: Test
|
||||
|
|
@ -265,17 +265,17 @@ jobs:
|
|||
matrix:
|
||||
include:
|
||||
- build: 'noavx'
|
||||
defines: '-DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF -DBUILD_SHARED_LIBS=ON'
|
||||
defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF -DBUILD_SHARED_LIBS=ON'
|
||||
- build: 'avx2'
|
||||
defines: '-DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON'
|
||||
defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DBUILD_SHARED_LIBS=ON'
|
||||
- build: 'avx'
|
||||
defines: '-DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX2=OFF -DBUILD_SHARED_LIBS=ON'
|
||||
defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX2=OFF -DBUILD_SHARED_LIBS=ON'
|
||||
- build: 'avx512'
|
||||
defines: '-DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON'
|
||||
defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_AVX512=ON -DBUILD_SHARED_LIBS=ON'
|
||||
- build: 'clblast'
|
||||
defines: '-DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DBUILD_SHARED_LIBS=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"'
|
||||
defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CLBLAST=ON -DBUILD_SHARED_LIBS=ON -DCMAKE_PREFIX_PATH="$env:RUNNER_TEMP/clblast"'
|
||||
- build: 'openblas'
|
||||
defines: '-DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUILD_SHARED_LIBS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
|
||||
defines: '-DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_BLAS=ON -DBUILD_SHARED_LIBS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS -DBLAS_INCLUDE_DIRS="$env:RUNNER_TEMP/openblas/include" -DBLAS_LIBRARIES="$env:RUNNER_TEMP/openblas/lib/openblas.lib"'
|
||||
|
||||
steps:
|
||||
- name: Clone
|
||||
|
|
@ -414,7 +414,7 @@ jobs:
|
|||
run: |
|
||||
mkdir build
|
||||
cd build
|
||||
cmake .. -DLLAMA_BUILD_SERVER=ON -DLLAMA_CUBLAS=ON -DBUILD_SHARED_LIBS=ON
|
||||
cmake .. -DLLAMA_NATIVE=OFF -DLLAMA_BUILD_SERVER=ON -DLLAMA_CUBLAS=ON -DBUILD_SHARED_LIBS=ON
|
||||
cmake --build . --config Release -j ${env:NUMBER_OF_PROCESSORS}
|
||||
|
||||
- name: Determine tag name
|
||||
|
|
|
|||
|
|
@ -44,7 +44,7 @@ endif()
|
|||
|
||||
# general
|
||||
option(LLAMA_STATIC "llama: static link libraries" OFF)
|
||||
option(LLAMA_NATIVE "llama: enable -march=native flag" OFF)
|
||||
option(LLAMA_NATIVE "llama: enable -march=native flag" ON)
|
||||
option(LLAMA_LTO "llama: enable link time optimization" OFF)
|
||||
|
||||
# debug
|
||||
|
|
@ -58,15 +58,21 @@ option(LLAMA_SANITIZE_ADDRESS "llama: enable address sanitizer"
|
|||
option(LLAMA_SANITIZE_UNDEFINED "llama: enable undefined sanitizer" OFF)
|
||||
|
||||
# instruction set specific
|
||||
option(LLAMA_AVX "llama: enable AVX" ON)
|
||||
option(LLAMA_AVX2 "llama: enable AVX2" ON)
|
||||
option(LLAMA_AVX512 "llama: enable AVX512" OFF)
|
||||
option(LLAMA_AVX512_VBMI "llama: enable AVX512-VBMI" OFF)
|
||||
option(LLAMA_AVX512_VNNI "llama: enable AVX512-VNNI" OFF)
|
||||
option(LLAMA_FMA "llama: enable FMA" ON)
|
||||
if (LLAMA_NATIVE)
|
||||
set(INS_ENB OFF)
|
||||
else()
|
||||
set(INS_ENB ON)
|
||||
endif()
|
||||
|
||||
option(LLAMA_AVX "llama: enable AVX" ${INS_ENB})
|
||||
option(LLAMA_AVX2 "llama: enable AVX2" ${INS_ENB})
|
||||
option(LLAMA_AVX512 "llama: enable AVX512" OFF)
|
||||
option(LLAMA_AVX512_VBMI "llama: enable AVX512-VBMI" OFF)
|
||||
option(LLAMA_AVX512_VNNI "llama: enable AVX512-VNNI" OFF)
|
||||
option(LLAMA_FMA "llama: enable FMA" ${INS_ENB})
|
||||
# in MSVC F16C is implied with AVX2/AVX512
|
||||
if (NOT MSVC)
|
||||
option(LLAMA_F16C "llama: enable F16C" ON)
|
||||
option(LLAMA_F16C "llama: enable F16C" ${INS_ENB})
|
||||
endif()
|
||||
|
||||
# 3rd party libs
|
||||
|
|
@ -504,9 +510,6 @@ if (NOT MSVC)
|
|||
if (LLAMA_GPROF)
|
||||
add_compile_options(-pg)
|
||||
endif()
|
||||
if (LLAMA_NATIVE)
|
||||
add_compile_options(-march=native)
|
||||
endif()
|
||||
endif()
|
||||
|
||||
if ((${CMAKE_SYSTEM_PROCESSOR} MATCHES "arm") OR (${CMAKE_SYSTEM_PROCESSOR} MATCHES "aarch64") OR ("${CMAKE_GENERATOR_PLATFORM_LWR}" MATCHES "arm64"))
|
||||
|
|
@ -561,6 +564,9 @@ elseif (${CMAKE_SYSTEM_PROCESSOR} MATCHES "^(x86_64|i686|AMD64)$" OR "${CMAKE_GE
|
|||
add_compile_options($<$<COMPILE_LANGUAGE:CXX>:/arch:AVX>)
|
||||
endif()
|
||||
else()
|
||||
if (LLAMA_NATIVE)
|
||||
add_compile_options(-march=native)
|
||||
endif()
|
||||
if (LLAMA_F16C)
|
||||
add_compile_options(-mf16c)
|
||||
endif()
|
||||
|
|
|
|||
|
|
@ -62,7 +62,7 @@
|
|||
mkdir -p $out/include
|
||||
cp ${src}/llama.h $out/include/
|
||||
'';
|
||||
cmakeFlags = [ "-DLLAMA_BUILD_SERVER=ON" "-DLLAMA_MPI=ON" "-DBUILD_SHARED_LIBS=ON" "-DCMAKE_SKIP_BUILD_RPATH=ON" ];
|
||||
cmakeFlags = [ "-DLLAMA_NATIVE=OFF" "-DLLAMA_BUILD_SERVER=ON" "-DBUILD_SHARED_LIBS=ON" "-DCMAKE_SKIP_BUILD_RPATH=ON" ];
|
||||
in
|
||||
{
|
||||
packages.default = pkgs.stdenv.mkDerivation {
|
||||
|
|
|
|||
Loading…
Reference in a new issue