Hacker News new | ask | show | jobs
by JonChesterfield 1431 days ago
Slightly, the older tech is 64 threads/lanes per warp/wavefront. Newer ones are 32 by default but 64 if desired.

Bigger differences are the instruction counter per thread since volta on nvidia (which I think is a terrible feature) and that forward progress guarantees are stronger on nvidia (those are _really_ helpful but expensive).
2 comments
TomVDB 1431 days ago
Nvidia GPUs were 32 threads per warps eight from the start of CUDA with the 8800 GTX.

> which I think is a terrible feature <> those are _really_ helpful but expensive

Guaranteed forward progress is a direct consequence of having an instruction counter per thread???

Or so I thought. How else would an SM be able to know the PC of a group of threads that wasn’t stuck?

link
dragontamer 1431 days ago
> Slightly, the older tech is 64 threads/lanes per warp/wavefront. Newer ones are 32 by default but 64 if desired.

AMD GCN was 64 threads/wavefront. NVidia always was 32 threads/warp.

AMD's newest consumer cards RDNA and RDNA2 are 32 threads/wavefront. However, GCN lives on with CDNA (MI200 supercomputer chips), with 64 threads/wavefront architecture.

link