Re:Why We Need SIMD
by taktoa on Wednesday October 08, 2025 @11:30PM
(#45523191)
I think what you're describing is SPMD, which is a compilation strategy, not a hardware architecture. I am not sure but I think SIMT is SIMD but with multiple program counters (1 per N lanes) to enable some limited control flow divergence between lane groups.
[ Parent
| on HN ]
Re:Why We Need SIMD
by AlotOfReading on Wednesday October 08, 2025 @11:50PM
(#45523295)
The PC is shared in traditional SIMT, but diverging branches are masked out until they execute. Nvidia introduced per-thread PCs with Volta. I think AMD still uses a shared PC across each wavefront?