from the article: "A low-level language for such processors would have native vector types of arbitrary lengths." Mojo has exactly this with the SIMD struct: https://mojolang.org/nightly/docs/std/builtin/simd/SIMD/
what is provably wrong ?
Most of the stuff you pointed out is addressed in a series of blog posts by Lattner : https://www.modular.com/democratizing-ai-compute
I think this might be good introduction to GPU programming: https://builds.modular.com/puzzles/introduction.html. It explains gpu concepts in an hardware agnostic way and verify understanding with implementation puzzle.…
from the article: "A low-level language for such processors would have native vector types of arbitrary lengths." Mojo has exactly this with the SIMD struct: https://mojolang.org/nightly/docs/std/builtin/simd/SIMD/
what is provably wrong ?
Most of the stuff you pointed out is addressed in a series of blog posts by Lattner : https://www.modular.com/democratizing-ai-compute
I think this might be good introduction to GPU programming: https://builds.modular.com/puzzles/introduction.html. It explains gpu concepts in an hardware agnostic way and verify understanding with implementation puzzle.…