diff options
| author | eunhhu <[email protected]> | 2026-10-08 11:47:34 +0100 |
|---|---|---|
| committer | eunhhu <[email protected]> | 2026-10-08 11:47:34 +0100 |
| commit | ee4e1510819a916bf84cd4b560b05f520d32e86b (patch) | |
| tree | 50f3702b07f990579f385164f2b6e0b820e77a92 /docs/research/037-build-time-prepared-runner.md | |
| parent | 6b6fbc29d809911ba8313e74eb429195f900f52a (diff) | |
| download | pure-ee4e1510819a916bf84cd4b560b05f520d32e86b.tar.gz pure-ee4e1510819a916bf84cd4b560b05f520d32e86b.zip | |
Research 131: the batch executor's general cuts, by the user's choice of the general way over a table of fused operations: values computed by the same code taken from the first, if !c one branch, selections (an arm's few lanes alone), keys as bits asked in one loop, L.first + i affine, a slice's bounds at once: the suite's BFS 211 to 112 instructions an edge, 41 to 24 ms (the compiled code 38.5, 7.7); where the rest goes and the floor of the general way (about twice the compiled code); knapsack and matmul 10% slower, cause not fully told; 024 and CHECKPOINT say so
Diffstat (limited to 'docs/research/037-build-time-prepared-runner.md')
0 files changed, 0 insertions, 0 deletions
