kernbench2

ywkang/kernbench2

Fork 0

Commit Graph

Author	SHA1	Message	Date
ywkang	fca24feac5	Fix all remaining test failures: single-cube allreduce + matplotlib dep - intercube_allreduce: add single-cube fast path that skips intra-SIP mesh reduce and goes directly to inter-SIP exchange. Fixes IPCQ deadlock when TP launches kernel on one cube per SIP. - distributed.py: derive effective cube dims from tensor shard placement instead of hardcoding topology mesh size. - pyproject.toml: add matplotlib>=3.7 to dependencies. - pe_dma.py (prior commit): add MMU translation in pipeline DMA path. 577 passed, 0 failed (was 529 passed, 10 failed). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-27 21:25:31 -07:00
mukesh	04c912f53e	Allreduce sweep: parametrized + xdist parallelism + topology diagram Refactor the latency sweep from one giant test into 36 parametrized cases that run in parallel under xdist (~6-8x faster: 1:49 instead of ~10 min). Each case writes a JSON row to a staging dir; conftest sessionfinish hook aggregates rows on the controller node into summary.csv and the per-topology + overview plots. Aggregator gains a CSV fallback so plot-only tweaks no longer require re-running the sweep. Overview plot updates: - 96 KB explicit x-axis marker with vertical dotted line - horizontal theoretical 2D-torus reference (10600 ns) - annotation showing both theoretical and simulated values at 96 KB - drop overlapping 128 KB tick New topology.png: 2x2 panel diagram showing device-level topology (ring, torus 2x3, mesh 2x3) and the cube-level reduction inside SIP 0. Wrap arrows anchor on box edges and arc outside rows/columns so they do not overlap any SIP. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>	2026-04-27 16:43:19 -07:00

Author

SHA1

Message

Date

ywkang

fca24feac5

Fix all remaining test failures: single-cube allreduce + matplotlib dep

- intercube_allreduce: add single-cube fast path that skips intra-SIP
  mesh reduce and goes directly to inter-SIP exchange. Fixes IPCQ
  deadlock when TP launches kernel on one cube per SIP.
- distributed.py: derive effective cube dims from tensor shard placement
  instead of hardcoding topology mesh size.
- pyproject.toml: add matplotlib>=3.7 to dependencies.
- pe_dma.py (prior commit): add MMU translation in pipeline DMA path.

577 passed, 0 failed (was 529 passed, 10 failed).

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

2026-04-27 21:25:31 -07:00

mukesh

04c912f53e

Allreduce sweep: parametrized + xdist parallelism + topology diagram

Refactor the latency sweep from one giant test into 36 parametrized
cases that run in parallel under xdist (~6-8x faster: 1:49 instead of
~10 min). Each case writes a JSON row to a staging dir; conftest
sessionfinish hook aggregates rows on the controller node into
summary.csv and the per-topology + overview plots.

Aggregator gains a CSV fallback so plot-only tweaks no longer require
re-running the sweep.

Overview plot updates:
- 96 KB explicit x-axis marker with vertical dotted line
- horizontal theoretical 2D-torus reference (10600 ns)
- annotation showing both theoretical and simulated values at 96 KB
- drop overlapping 128 KB tick

New topology.png: 2x2 panel diagram showing device-level topology
(ring, torus 2x3, mesh 2x3) and the cube-level reduction inside SIP 0.
Wrap arrows anchor on box edges and arc outside rows/columns so they
do not overlap any SIP.

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

2026-04-27 16:43:19 -07:00

2 Commits