Intercube allreduce: center root + bidirectional reduce

Browse Source

Move the algorithmic root cube from the corner (cube_w-1,
cube_h-1) to the geometric center (cube_w//2, cube_h//2) and
have each phase converge bidirectionally so the intra-SIP
critical path drops from ~12 hops to ~8 hops on a 4×4 mesh
(left half W→E + right half E→W in row reduce; top half N→S +
bottom half S→N in col reduce; mirrored on broadcast).

Result on torus_2d 6 SIPs at 96 KB / PE on TCM:
  before (corner root)  : 22.0 µs
  after  (center root)  : 17.2 µs   (−22%)

Same shape on ring_1d (−7%) and mesh_2d_no_wrap (−12%); also
holds across SRAM and HBM (~−20% each).

Phase 1 test (test_intercube_root_center.py) asserts the
torus_2d 96 KB latency drops below 20.5 µs and that all 96
cubes still validate (correctness preserved).

Plot updates:
- overview.png: replace constant 10.6 µs theoretical line with
  user-supplied hand-derived curve (per-cube packet count =
  bytes_per_pe × 8 PEs ÷ 128 B; 1346 ns startup + 1.20 ns/pkt).
- All summary.csv numbers and per-topology PNGs regenerated.
- pe2pe_latency_plots and ipcq diagram emitter PNGs refreshed.

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

...

This commit is contained in:

Mukesh Garg

2026-04-27 21:28:58 -07:00

parent 84a1325e5c

commit 1c5752a9ec

16 changed files with 324 additions and 157 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/diagrams/pe2pe_latency_plots/h1_intra_horizontal.png

BIN

Binary file not shown.

Side by Side Swipe Overlay Before Width:  |  Height:  |  Size: 48 KiB After Width:  |  Height:  |  Size: 45 KiB