Skip to content

Latest commit

 

History

History
67 lines (45 loc) · 1.7 KB

BLIS.md

File metadata and controls

67 lines (45 loc) · 1.7 KB
Raw

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:

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:

sudo make install

We recommend using openmp since it's easier to modify the cores being used.

llama.cpp compilation

Makefile:

make GGML_BLIS=1 -j
# make GGML_BLIS=1 llama-benchmark-matmult

CMake:

mkdir build
cd build
cmake -DGGML_BLAS=ON -DGGML_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_CPU_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.

Reference:

  1. https://github.com/flame/blis#getting-started
  2. https://github.com/flame/blis/blob/master/docs/Multithreading.md