Hackernews posts about AVX-512

AVX-512 is a set of instructions for processing data in computer chips that provides significant performance improvements and expanded capabilities for handling large datasets and complex calculations.

1. The Evolution of x86 SIMD: From SSE to AVX-512 (bgslabs.org)
   4 points by todsacerdoti 2 days ago | discuss
2. Show HN: Evolved x86 AVX-512 kernels for NF4 LLM inference (github.com)
   2 points by Anuar81 3 days ago | discuss
3. Strassen's Matmul with AVX 512 (martianlantern.github.io)
   1 points by martianlantern 21 days ago | discuss
4. Show HN: I built a CSV parser to try Go 1.26's new SIMD package (github.com)
   8 points by tokkyokky 23 days ago | 5 comments
5. Show HN: A Zero-Copy 1.58-bit LLM Engine hitting 117 Tokens/s on single CPU core (github.com)
   4 points by dhilipsiva 25 days ago | discuss
6. Show HN: Axiom – C++ tensor library with NumPys API, optimized for Apple Silicon (github.com)
   3 points by noahkay13 13 days ago | 2 comments
7. Show HN: SC-NeuroCore – Rust neuromorphic compiler, 512× speedup (github.com)
   2 points by anulum 7 days ago | discuss
8. Show HN: A Deployable Cross-Platform SIMD RNG Library for C++ (With Bnchmks)
   1 points by whisprer 5 days ago | discuss
9. Beating Google's kernelCTF PoW using AVX512 (anemato.de)
   337 points by anematode 9 months ago | 94 comments
10. tolower() with AVX-512 (dotat.at)
    275 points by fanf2 over 1 year ago | 153 comments
11. Using the most unhinged AVX-512 instruction to make fastest phrase search algo (gab-menezes.github.io)
    231 points by cmcollier about 1 year ago | 61 comments
12. Full Unicode Search at 50× ICU Speed with AVX‑512 (ashvardanian.com)
    217 points by ashvardanian 2 months ago | 77 comments
13. Zen 5's AVX-512 Frequency Behavior (chipsandcheese.com)
    213 points by matt_d 12 months ago | 66 comments
14. Zen5's AVX512 Teardown and More (www.numberworld.org)
    143 points by todsacerdoti over 1 year ago | 87 comments
15. AVX-512: First Impressions on Performance and Programmability (shihab-shahriar.github.io)
    125 points by shihab about 1 month ago | 53 comments
16. Llamafile 0.7 Brings AVX-512 Support: 10x Faster Prompt Eval Times for AMD Zen 4 (www.phoronix.com)
    91 points by mfiguiere almost 2 years ago | 17 comments
17. Bit-permuting 16 u32s at once with AVX-512 (bitmath.blogspot.com)
    51 points by dist1ll about 1 year ago | 4 comments
18. Zen5's AVX512 Teardown and More (Without Redacted Content) (numberworld.org)
    29 points by abhinavk over 1 year ago | 2 comments
19. Bit-permuting 16 u32s at once with AVX-512 (bitmath.blogspot.com)
    24 points by mfiguiere about 1 year ago | 1 comments
20. Making the fastest phrase search algo with the most unhinged AVX512 instruction (gab-menezes.github.io)
    17 points by pcstl about 1 year ago | discuss
21. x86 amd64 SIMD instruction list: SSE to AVX512 (www.officedaytime.com)
    16 points by fanf2 over 1 year ago | 3 comments
22. Converting ASCII strings to lower case at crazy speeds with AVX-512 (lemire.me)
    15 points by kristianp over 1 year ago | 1 comments
23. Emulating AVX-512 intrinsics in Miri (trifectatech.org)
    14 points by ashvardanian 2 months ago | discuss
24. Converting ASCII strings to lower case at crazy speeds with AVX-512 (lemire.me)
    11 points by usdogu over 1 year ago | 4 comments
25. Boosting Vector Search Speed by 40% with AVX512 on Emerald Rapids (weaviate.io)
    9 points by zainhasan12 almost 2 years ago | 3 comments
26. No, AVX 512 is power efficient [video] (www.youtube.com)
    9 points by paulsen 5 months ago | discuss
27. Chinese chipmaker readies 128-core, 512-thread CPU with AVX-512 (www.tomshardware.com)
    8 points by ksec 10 months ago | 2 comments
28. Benchmarking Division and Libdivide on Apple M1 and Intel AVX512 (2021) (ridiculousfish.com)
    6 points by fanf2 over 1 year ago | 1 comments
29. AVX-512 gotcha: avoid compressing words to memory with AMD Zen 4 processors (lemire.me)
    6 points by ibobev about 1 year ago | discuss
30. GNU Coreutils 9.6 Released with Changes for POSIX 2024, More AVX2, AVX-512 use (www.phoronix.com)
    6 points by rbanffy about 1 year ago | discuss
31. Zen5's AVX512 Uplift (www.phoronix.com)
    6 points by Remnant44 over 1 year ago | discuss
32. The most unhinged AVX-512 instruction to make the fastest phrase search algo (gab-menezes.github.io)
    5 points by mpweiher about 1 year ago | 1 comments
33. Hygon readies 128-core, 512-thread CPU with AVX-512 and 16-channel DDR5-5600 (www.tomshardware.com)
    5 points by rbanffy 10 months ago | discuss
34. Intel Demonstrates Up to 48% Improvement for AVX-512 Optimized PostgreSQL (www.phoronix.com)
    5 points by rbanffy over 1 year ago | discuss
35. Sparse-ternary-fma – 23x faster AVX-512 kernel for FHE&AI, from my ePrint paper (github.com)
    4 points by HyperFoldUK about 2 months ago | 1 comments
36. New FFmpeg AVX-512 Optimizations Hit Up to 36x the Performance of Plain C Code (www.phoronix.com)
    4 points by rbanffy 7 months ago | 1 comments
37. Zen4's AVX512 Teardown (www.mersenneforum.org)
    4 points by fanf2 over 1 year ago | 1 comments
38. Intel Nova Lake May Abandon AVX-512 and These Other CPU Instruction Sets (hothardware.com)
    4 points by rbanffy 4 months ago | discuss