The art of high performance computing

Re:The art of high performance computing by bee_rider on Saturday December 30, 2023 @10:58AM (#38816198)

Every BLAS you want to use has at least some connection to UT Austin’s TACC.

[ Parent | on HN ]

Re:The art of high performance computing by mgaunard on Saturday December 30, 2023 @11:20AM (#38816385)

aren't the lapack people in tennessee?

[ Parent | on HN ]

Re:The art of high performance computing by bee_rider on Saturday December 30, 2023 @11:48AM (#38816610)

Sort of like BLAS, LAPACK is more than just one implementation. Dongarra described what everybody should do from Tennesse, but other places implemented it elsewhere.

[ Parent | on HN ]

Re:The art of high performance computing by mgaunard on Saturday December 30, 2023 @06:16PM (#38820255)

plasma and magma are also from there.

I'm not aware of any other significant lapack-related developments, but I might just not know about them.

[ Parent | on HN ]

Re:The art of high performance computing by victotronics on Saturday December 30, 2023 @02:06PM (#38817930)

Not quite. Every modern BLAS is (likely) based on Kazushige Goto's implementation, and he was indeed at TACC for a while. But probably the best open source implementation "BLIS" is from UT Austin, but not connected to TACC.

[ Parent | on HN ]

Re:The art of high performance computing by bee_rider on Saturday December 30, 2023 @02:12PM (#38818021)

Oh really? I thought BLIS was from TACC. Oops, mea culpa.

[ Parent | on HN ]

Re:The art of high performance computing by RhysU on Saturday December 30, 2023 @02:35PM (#38818261)

https://github.com/flame/blis/

Field et al, recent winners of the James H. Wilkinson Prize for Numerical Software.

Field and Goto both collaborated with Robert van de Geijn. Lots of TACC interaction in that broader team.

[ Parent | on HN ]