OpenBLAS 0.3.8 Brings More AVX2/AVX512 Kernels, Other Optimizations

[phoronix]

Phoronix: OpenBLAS 0.3.8 Brings More AVX2/AVX512 Kernels, Other Optimizations

For those using OpenBLAS as your BLAS (Basic Linear Algebra Subprograms) implementation, OpenBLAS 0.3.8 was released this weekend and coming with it are more AVX2/AVX-512 kernels and other optimizations...

http://www.phoronix.com/scan.php?page=news_item&px=OpenBLAS-0.3.8-Released

[pegasus]

Are avx512 kernels finally producing correct results?

[Lycanthropist]

Is there an up-to-date comparison of the different BLAS implementations regarding correctness and performance?

[milkylainen]

So why not replace MKL-DNN tests with something more vendor agnostic?