sweep+plot: add primitive hand-tiled (16×16×16) variant to Case-6 decode composite study

Browse Source

Wires a fourth variant into the Cube-SP × PE-SP long-context decode
composite command-form study to surface the worst-case PE_CPU dispatch
inflation that the coarse composite forms delegate to PE_SCHEDULER
(ADR-0065): per-block DMA of Q/K/V slices, tl.dot per 16³ block,
deferred K-inner sum outside the K loop.

Renamed _tiled.py → _hand_tiled_16x16x16.py; coarse-primitive kernel
retained for the 4-cases bench, paper scripts, and the golden byte-equal
regression guard.

New breakdown bar chart at S_kv=128K shows engine (~460 μs) dominates
all three variants; hand-tiled adds ~68 μs PE_CPU dispatch on top —
composite forms sit essentially on the memory-bound floor.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

...

This commit is contained in:

Mukesh Garg

2026-07-13 09:28:57 -07:00

parent f8caf2e16c

commit eec61838b5

11 changed files with 540 additions and 135 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

docs/report/1H-codesign-paper/figures/gqa_decode_long_ctx_composite.png

BIN

Binary file not shown.

Side by Side Swipe Overlay Before Width:  |  Height:  |  Size: 136 KiB After Width:  |  Height:  |  Size: 151 KiB

docs/report/1H-codesign-paper/figures/gqa_decode_long_ctx_composite_breakdown.png

BIN

Binary file not shown.

Side by Side After Width:  |  Height:  |  Size: 75 KiB