@Jonathan_Blow @rflaherty71 In my experience writing optimized numerical routines the "generic builtins" approach doesn't work well because the underlying data shape and algo is also influenced by the available instructions and bitwidths of the simd impl.

Source

• URL: https://x.com/ken__maples/status/1871644807279661159
• Author: Ken Maples (@ken__maples)
• Posted: 2024-12-24 19:51:10

Branch

1/ @ken__maples

@Jonathan_Blow @rflaherty71

In my experience writing optimized numerical routines the “generic builtins” approach doesn’t work well because the underlying data shape and algo is also influenced by the available instructions and bitwidths of the simd impl. so you have separate routines per impl anyway

Related

• Spine: 2024-12-24-i-have-a-moral-dilemma-in-the-design-of-the