Revert "feature : add blis and other BLAS implementation support (#1502)"

This reverts commit 07e9ace0f9.
This commit is contained in:
Georgi Gerganov 2023-05-20 12:03:48 +03:00
parent 07e9ace0f9
commit ea600071cb
No known key found for this signature in database
GPG key ID: 449E073F9DC10735
4 changed files with 24 additions and 103 deletions

67
BLIS.md
View file

@ -1,67 +0,0 @@
BLIS Installation Manual
------------------------
BLIS is a portable software framework for high-performance BLAS-like dense linear algebra libraries. It has received awards and recognition, including the 2023 James H. Wilkinson Prize for Numerical Software and the 2020 SIAM Activity Group on Supercomputing Best Paper Prize. BLIS provides a new BLAS-like API and a compatibility layer for traditional BLAS routine calls. It offers features such as object-based API, typed API, BLAS and CBLAS compatibility layers.
Project URL: https://github.com/flame/blis
### Prepare:
Compile BLIS:
```bash
git clone https://github.com/flame/blis
cd blis
./configure --enable-cblas -t openmp,pthreads auto
# will install to /usr/local/ by default.
make -j
```
Install BLIS:
```bash
sudo make install
```
We recommend using openmp since it's easier to modify the cores been used.
### llama.cpp compilation
Makefile:
```bash
make LLAMA_BLIS=1 -j
# make LLAMA_BLIS=1 benchmark-matmult
```
CMake:
```bash
mkdir build
cd build
cmake -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=FLAME ..
make -j
```
### llama.cpp execution
According to the BLIS documentation, we could set the following
environment variables to modify the behavior of openmp:
```
export GOMP_GPU_AFFINITY="0-19"
export BLIS_NUM_THREADS=14
```
And then run the binaries as normal.
### Intel specific issue
Some might get the error message saying that `libimf.so` cannot be found.
Please follow this [stackoverflow page](https://stackoverflow.com/questions/70687930/intel-oneapi-2022-libimf-so-no-such-file-or-directory-during-openmpi-compila).
### Reference:
1. https://github.com/flame/blis#getting-started
2. https://github.com/flame/blis/blob/master/docs/Multithreading.md

View file

@ -65,8 +65,7 @@ endif()
# 3rd party libs
option(LLAMA_ACCELERATE "llama: enable Accelerate framework" ON)
option(LLAMA_BLAS "llama: use BLAS" OFF)
option(LLAMA_BLAS_VENDOR "llama: BLA_VENDOR from https://cmake.org/cmake/help/latest/module/FindBLAS.html#blas-lapack-vendors" Generic)
option(LLAMA_OPENBLAS "llama: use OpenBLAS" OFF)
option(LLAMA_CUBLAS "llama: use cuBLAS" OFF)
option(LLAMA_CLBLAST "llama: use CLBlast" OFF)
@ -146,28 +145,36 @@ if (APPLE AND LLAMA_ACCELERATE)
endif()
endif()
if (LLAMA_BLAS)
if (LLAMA_OPENBLAS)
if (LLAMA_STATIC)
set(BLA_STATIC ON)
endif()
if ($(CMAKE_VERSION) VERSION_GREATER_EQUAL 3.22)
set(BLA_SIZEOF_INTEGER 8)
endif()
set(BLA_VENDOR ${LLAMA_BLAS_VENDOR})
set(BLA_VENDOR OpenBLAS)
find_package(BLAS)
if (BLAS_FOUND)
message(STATUS "BLAS found, Libraries: ${BLAS_LIBRARIES}")
message(STATUS "OpenBLAS found")
add_compile_options(${BLAS_LINKER_FLAGS})
add_compile_definitions(GGML_USE_OPENBLAS)
set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} ${BLAS_LIBRARIES})
add_link_options(${BLAS_LIBRARIES})
set(LLAMA_EXTRA_LIBS ${LLAMA_EXTRA_LIBS} openblas)
message("${BLAS_LIBRARIES}")
include_directories(${BLAS_INCLUDE_DIRS})
# find header file
set(OPENBLAS_INCLUDE_SEARCH_PATHS
/usr/include
/usr/include/openblas
/usr/include/openblas-base
/usr/local/include
/usr/local/include/openblas
/usr/local/include/openblas-base
/opt/OpenBLAS/include
$ENV{OpenBLAS_HOME}
$ENV{OpenBLAS_HOME}/include
)
find_path(OPENBLAS_INC NAMES cblas.h PATHS ${OPENBLAS_INCLUDE_SEARCH_PATHS})
add_compile_options(-I${OPENBLAS_INC})
else()
message(WARNING "BLAS not found, please refer to "
"https://cmake.org/cmake/help/latest/module/FindBLAS.html#blas-lapack-vendors"
" to set correct LLAMA_BLAS_VENDOR")
message(WARNING "OpenBLAS not found")
endif()
endif()

View file

@ -122,10 +122,6 @@ ifdef LLAMA_OPENBLAS
LDFLAGS += -lopenblas
endif
endif
ifdef LLAMA_BLIS
CFLAGS += -DGGML_USE_OPENBLAS -I/usr/local/include/blis -I/usr/include/blis
LDFLAGS += -lblis -L/usr/local/lib
endif
ifdef LLAMA_CUBLAS
CFLAGS += -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I$(CUDA_PATH)/targets/x86_64-linux/include
CXXFLAGS += -DGGML_USE_CUBLAS -I/usr/local/cuda/include -I/opt/cuda/include -I$(CUDA_PATH)/targets/x86_64-linux/include

View file

@ -56,7 +56,7 @@ The main goal of `llama.cpp` is to run the LLaMA model using 4-bit integer quant
- Mixed F16 / F32 precision
- 4-bit, 5-bit and 8-bit integer quantization support
- Runs on the CPU
- Supports OpenBLAS/Apple BLAS/ARM Performance Lib/ATLAS/BLIS/Intel MKL/NVHPC/ACML/SCSL/SGIMATH and [more](https://cmake.org/cmake/help/latest/module/FindBLAS.html#blas-lapack-vendors) in BLAS
- OpenBLAS support
- cuBLAS and CLBlast support
The original implementation of `llama.cpp` was [hacked in an evening](https://github.com/ggerganov/llama.cpp/issues/33#issuecomment-1465108022).
@ -274,25 +274,10 @@ Building the program with BLAS support may lead to some performance improvements
```bash
mkdir build
cd build
cmake .. -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=OpenBLAS
cmake .. -DLLAMA_OPENBLAS=ON
cmake --build . --config Release
```
- BLIS
Check [BLIS.md](BLIS.md) for more information.
- Intel MKL
By default, `LLAMA_BLAS_VENDOR` is set to `Generic`, so if you already sourced intel environment script and assign `-DLLAMA_BLAS=ON` in cmake, the mkl version of Blas will automatically been selected. You may also specify it by:
```bash
mkdir build
cd build
cmake .. -DLLAMA_BLAS=ON -DLLAMA_BLAS_VENDOR=Intel10_64lp -DCMAKE_C_COMPILER=icx -DCMAKE_CXX_COMPILER=icpx
cmake --build . -config Release
```
- cuBLAS
This provides BLAS acceleration using the CUDA cores of your Nvidia GPU. Make sure to have the CUDA toolkit installed. You can download it from your Linux distro's package manager or from here: [CUDA Toolkit](https://developer.nvidia.com/cuda-downloads).