__popc counts set bits: Lori's 31 beats Alice's single high bit
cfregly · x · 2026-11-11
cfregly illustrates CUDA's popc intrinsic: Alice's mask 0x80000000 holds only the high bit (larger unsigned value), while Lori's 0x7FFFFFFF has 31 set bits — popc counts each once, so Lori wins 31 to 1. Links to NVIDIA's CUDA Math API Integer Intrinsics docs (brev, clz, dp2a, etc.).
More from Infra
- Apple reportedly building Harbor app to turn Macs into private AI inference servers with Thunderbolt 5 clustering — BenBajarin · 2026-11-11
- Agent Arena: Gemini 4 Carbon Gets More Cost-Competitive as Tasks Get Harder — rseroter · 2026-11-11
- AMD Zen 6 deep dive: cheaper branch mispredicts and a return to Zen 3/4 integer scheduling — jedisct1 · 2026-11-11
- Together AI SVP Dan Fu on kernels, serving 3T-param models day zero, and self-improving inference — togethercompute · 2026-11-11
- ExecuTorch adds WebGPU backend: run PyTorch models in-browser, up to 10x faster than CPU — PyTorch · 2026-11-11
- Hedra runs training experiments with AI agents steered by human researchers — testingcatalog · 2026-11-11