diff options
| author | eunhhu <[email protected]> | 2026-10-08 15:52:44 +0100 |
|---|---|---|
| committer | eunhhu <[email protected]> | 2026-10-08 15:52:44 +0100 |
| commit | 6828a7d07f9de815c858a295124f6bcde9bd861a (patch) | |
| tree | 7a7ae86228c20ff8dd041588614d2d58b81fc3fc /research/experiments/041-batches/2026-10-08-counts.jsonl | |
| parent | bdcc6f66e3addf1980b3b065609cc0f5075a4194 (diff) | |
| download | pure-6828a7d07f9de815c858a295124f6bcde9bd861a.tar.gz pure-6828a7d07f9de815c858a295124f6bcde9bd861a.zip | |
Research 135: batch plans' stage 2 measured (b11 = 7959885 against b10, interleaved): matmul 38.18 to 36.10 ms with 4.5% fewer instructions (segments in its nested rounds), knapsack's per-batch cost 0.68 to 0.63 us but knapsack 10.35 to 10.51 ms with 1% fewer instructions (its per-element loops placed elsewhere), sum0 1,743 instructions a batch: short of 025's stage-2 bars (9.2 ms, 0.45 us, 33 ms): 025 priced a segment's instruction at 50 cycles, the counts show about 25 instructions, and a batch's cost sits in finds, bounds, read records, lane setup, masks and the deferred store's check; a list's cells once a batch measured at 3% and not made; next, per element: stage 3's four-byte MUL (matmul 21 ms)
Diffstat (limited to 'research/experiments/041-batches/2026-10-08-counts.jsonl')
| -rw-r--r-- | research/experiments/041-batches/2026-10-08-counts.jsonl | 10 |
1 files changed, 10 insertions, 0 deletions
diff --git a/research/experiments/041-batches/2026-10-08-counts.jsonl b/research/experiments/041-batches/2026-10-08-counts.jsonl index 546030b..0e89a46 100644 --- a/research/experiments/041-batches/2026-10-08-counts.jsonl +++ b/research/experiments/041-batches/2026-10-08-counts.jsonl @@ -36,3 +36,13 @@ {"version":"b10","way":"rounds","work":"roots","instructions":2755945365,"cycles":989112526} {"version":"b10","way":"batches","work":"join","instructions":1868533943,"cycles":1049050190} {"version":"b10","way":"rounds","work":"join","instructions":7669661641,"cycles":3314577656} +{"version":"b11","way":"batches","work":"bfs","instructions":3381283015,"cycles":1683369887} +{"version":"b11","way":"rounds","work":"bfs","instructions":4715633866,"cycles":2086008861} +{"version":"b11","way":"batches","work":"knapsack","instructions":373838059,"cycles":121140642} +{"version":"b11","way":"rounds","work":"knapsack","instructions":21688102965,"cycles":7548998383} +{"version":"b11","way":"batches","work":"matmul","instructions":924133786,"cycles":313909094} +{"version":"b11","way":"rounds","work":"matmul","instructions":21436716024,"cycles":6624677320} +{"version":"b11","way":"batches","work":"roots","instructions":166257657,"cycles":113412601} +{"version":"b11","way":"rounds","work":"roots","instructions":2755945430,"cycles":987962207} +{"version":"b11","way":"batches","work":"join","instructions":1862305226,"cycles":1068457401} +{"version":"b11","way":"rounds","work":"join","instructions":7669661824,"cycles":3430154017} |