On Friday, 23 September 2016 at 13:25:30 UTC, Ilya Yaroshenko wrote:
Mir is LLVM-accelerated Generic Numerical Library for Science and Machine Learning.

Benchmark:
http://blog.mir.dlang.io/glas/benchmark/openblas/2016/09/23/glas-gemm-benchmark.html


Still time for a few edits of that post?

Please emphasize the equally impressive comparison of the code necessary for the matrix multiplication.

glas.gemm(alpha, a, b, beta, c);

vs.

cblas.gemm(
    cblas.Order.RowMajor,
    cblas.Transpose.NoTrans,
    cblas.Transpose.NoTrans,
    cast(cblas.blasint) m,
    cast(cblas.blasint) n,
    cast(cblas.blasint) k,
    & alpha,
    a.ptr,
    cast(cblas.blasint) a.stride,
    b.ptr,
    cast(cblas.blasint) b.stride,
    & beta,
    d.ptr,
    cast(cblas.blasint) d.stride);

Reply via email to