Kiran
Kiran
@banskt When running pure MPI based HPL using MKL or OpenBLAS - Did you set OMP_NUM_THREADS=1 ?. These libraries by default run multi-threaded and when you set OMP_NUM_THREADS=1, the pure...
@banskt - can you write a mail to [email protected]. They will help you.
BLIS and MKL support standard BLAS interfaces. So interface is definitely not the reason. Let me check with my team, they tried it in the past. @shrutiramesh1988 can you help...
I came to know that its difficult to link BLIS directly with TensorFlow since MKLDNN path takes MKL by default. It was suggested to use ZENDNN with TF in order...
@markbmuller, @ajz34 - you can post the issue at https://github.com/amd/blis . Thanks for reporting, will look into this issue.
Hi @AmperesAvengement , which gcc version used ? .Did you try this fork: https://github.com/amd/blis ?
can you try zen2 config ./configure CC=clang CXX=clang++ FC=flang --prefix=$PWD/install --enable-threading=pthreads **zen2** Latest blis code optimized for AMD EPYC processors you can find at : https://github.com/amd/blis - you can select...