Erik Rigtorp

@rigtorp

Joined January 2009

Erik Rigtorp
@rigtorp
Sep 3, 2020
@glcst @penberg Thread-per-core is great when you can dedicate a machine or subset of cores to an application. When needing to share cores the thread-per-core architecture gives less information to the scheduler. Any work on quantifying the trade-offs?
Erik Rigtorp
@rigtorp
Aug 24, 2020
@AMD #ROCm version 3.7 finally supports Navi 10! I've tested it on my 5700XT card. Hopefully @PyTorch will run on Navi 10 now. Steps to reproduce on @fedora: rigtorp.se/notes/rocm/
Erik Rigtorp
@rigtorp
Jun 26, 2020
On the latest CPU microarchitectures (Skylake and Zen 2) AVX/AVX2 128b/256b aligned loads and stores are atomic. I wrote a small program isatomic that I used to verify this. rigtorp.se/isatomic/ #AVX #SIMD #x86
rigtorp.se
Aligned AVX loads and stores are atomic
On the latest CPU microarchitectures (Skylake and Zen 2) AVX/AVX2 128b/256b aligned loads and stores are atomic even though Intel and AMD officially doesn’t guarantee this.
Erik Rigtorp
@rigtorp
Apr 7, 2020
A full task-isolation mode for the kernel: lwn.net/Articles/81629… #Linux #kernel
lwn.net
A full task-isolation mode for the kernel
Some applications require guaranteed access to the CPU without even brief interruptions; realti [...]
Erik Rigtorp
@rigtorp
Feb 13, 2020
@Xfinity doesn't honor marketing email opt-out requests. This is in violation of the #canspam act and I will report it to the @FTC if not fixed!