Engineer calls megakernel hype a psyop: CUDA graphs already express a strict superset
mike64_t · x · 2026-11-10
mike64t pushes back on megakernel hype, arguing a CUDA graph of co-designed kernels expresses a strict superset of what a single megakernel can do, citing cuGraphAddBatchMemOpNode (analog of cuStreamWaitValue64) enabling SM-free waiting. A substantive debate in the GPU kernel engineering community on megakernel vs. multi-kernel orchestration.
More from Infra
- "Biblically accurate" low-loss waveguide crossing looks majestic, performs terribly — jwt0625 · 2026-11-10
- RBA gives LLaVA-OneVision-2 a 3x lossless training speed-up, merged upstream — liuziwei7 · 2026-11-10
- Comet 60B (A12B) gets GGUF quants with MTP head for speculative decoding in llama.cpp — Felladrin · 2026-11-10
- Nvidia lobbied hard against rules on remote access to restricted chips, officials say — rohanpaul_ai · 2026-11-10
- AI daily: Fable 5.2 tops evals, orchestrates 1000 agents for 8 days to build a prototype OS — jiqizhixin · 2026-11-10
- Senate advances energy permitting bill 73-25, requiring data centers to pay more grid costs — firstadopter · 2026-11-10