Prefix sums at gigabytes per second with ARM NEON(lemire.me)

55 points by mfiguiere 7 months ago | 8 comments

An optimizing compiler doesn't help much with long instruction dependencies(johnnysswlab.com)

25 points by ingve 1 year ago | 4 comments

Decreasing the number of memory accesses(johnnysswlab.com)

73 points by g0xA52A2A 3 years ago | 43 comments

Beating the compiler (2024)(mattkeeter.com)

57 points by andsoitis 25 days ago | 38 comments

Matt Keeter's blog post on writing an interpreter for the Uxn stack-based CPU in hand-written assembly to outperform compiler-generated code.

Growing Buffers to Avoid Copying Data(johnnysswlab.com)

30 points by ingve 1 year ago | 20 comments

The messy reality of SIMD (vector) functions(johnnysswlab.com)

86 points by mfiguiere 1 year ago | 55 comments