News for hackers. Stuff that matters.

A comment on Fortran. Parent comment

Re:Fortran by WanderPanda on Monday August 28, 2023 @06:37PM (#37301278)
I wonder why the cascaded triple for loop for GEMM is not just hardcoded in assembly for each architecture. And while we are at it, why is MKL > 5GB again?
[ Parent | on HN ]
Re:Fortran by tomrod on Monday August 28, 2023 @10:05PM (#37302675)
Does this address your MKL question?[1] If so, sounds like we're two of today's lucky 10,000![0] Although for this esoterica, I'd probably reduce that to 10.

[0] https://xkcd.com/1053/

[1] https://community.intel.com/t5/Intel-oneAPI-Math-Kernel-Libr...

[ Parent | on HN ]
Re:Fortran by zzzoom on Thursday September 07, 2023 @09:47PM (#37428275)
Most decent BLAS implementations use some variation of the kernels in K. Goto et al. "Anatomy of High-Performance Matrix Multiplication" written in assembly.
[ Parent | on HN ]