Top all-time · #20605
Alex Armbruster
Personal blog · alexarmbr.github.ioprogrammingsystems
Alex Armbruster's personal blog at alexarmbr.github.io covers programming and systems. Since 2024, 3 different Hacker News readers have linked it 4 times, most often “How to Write a Fast Matrix Multiplication from Scratch with Tensor Cores (2024)”. The last post was in 2024, but the archive is still widely read.
Too few sampled comments (1) to say how often HN recommends it.?
Why HN links it
HN readers link Alex Armbruster's blog for GPU programming posts, such as one on writing a fast matrix multiply. This comment thread discusses SIMD versus tensor cores in GPU code.
Summarised by Claude from a sample of 1 HN comments that link here. Each comment is marked recommending, critical or neutral (citing without judging); how this works.
This is my blog
Most-linked posts?
- How to Write a Fast Matrix Multiplication from Scratch with Tensor Cores (2024)2 people · 3 mentions · first linked 2024-08-21
What Hacker News says?
I believe these are SIMD. Tensor cores require MMA family of instructions. Ask me how I know. :) https://github.com/m4rs-mt/ILGPU/compare/master...lostmsu:IL... Good article: https://alexarmbr.github.io/2024/08/10/How-To-Write-A-Fast-M...
Comment linking /2024/08/10/How-To-Write-A-Fast-Matrix-Multiplication-From-Scratch-With-Tensor-Cores.html
on “Show HN: GPULlama3.java Llama Compilied to PTX/OpenCL Now Integrated in Quarkus”Submitted How to Write a Fast Matrix Multiplication from Scratch with Tensor Cores (2024) as a story · 147 points
HN discussionSubmitted How to Write a Fast Matrix Multiplication from Scratch with Tensor Cores as a story · 2 points
HN discussionSubmitted How to Write a Fast CUDA Matrix Multiplication with Nvidia Tensor Cores as a story · 2 points
HN discussion