mirror of
https://github.com/paboyle/Grid.git
synced 2026-08-06 02:43:29 +01:00
Replaces one thread per outer site calling Reduce() (sequential Nsimd-wide loop) with one thread per lane calling extractLane() — O(1) per thread. CUB now reduces over osites*Nsimd elements. Avoids serial lane reduction but leaves the per-lane sobjD store stride as a known remaining concern. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>