2 Commits

Author	SHA1	Message	Date
mukesh	19dfc86dc3	Allreduce latency sweep across topologies and data sizes ... Adds test_allreduce_latency_sweep that runs the existing intercube allreduce kernel under three SIP topologies (ring_1d, torus_2d, mesh_2d_no_wrap, all at n_sips=4) across 11 data sizes from 256 B/SIP up to 1 MB/SIP. For each point, captures max(pe_exec_ns) — the critical-path kernel time — and emits CSV plus log-x and linear-x plots, both per-topology and combined overview, with KB/MB-formatted tick labels. Reuses run_allreduce + _write_temp_configs and adds a slot_size auto-bump when n_elem*2 exceeds the default IPCQ slot. Sweep skips n_elem=16 because the runtime's dim_map scalar-arg remapping (context.py:761) collides any int-valued kernel scalar that matches a global tensor dim with its local shard size. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>	2026-04-27 10:16:29 -07:00
mukesh	1d8b9401e5	Intercube allreduce: pe0 cube-mesh reduce + multi-SIP ring/torus/mesh ... New intercube allreduce kernel replacing the old flat ring algorithms. Reduces across the 4x4 cube mesh within each SIP (pe0-only, same-lane), then inter-SIP exchange on root cube, then broadcast back. Supports ring_1d, torus_2d, and mesh_2d_no_wrap SIP topologies driven by topology.yaml. Integrated with dist.init_process_group / dist.all_reduce. New files: - src/kernbench/ccl/algorithms/intercube_allreduce.py (kernel) - src/kernbench/ccl/sfr_config.py (configure_sfr_intercube_multisip) - tests/test_allreduce_multidevice.py (config-driven, 3 topologies) - tests/test_distributed_intercube_allreduce.py (full distributed path) - tests/test_intercube_sfr_config.py (SFR wiring verification) Modified: - distributed.py: AhbmCCLBackend uses configure_sfr_intercube_multisip - topologies.py: added torus_2d, mesh_2d_no_wrap - install.py: global_E/W/N/S in _OPPOSITE_DIR - topology.yaml: added system.sips.topology - ccl.yaml: single intercube_allreduce algorithm - benches/ccl_allreduce.py: row_wise cube-mesh tensor layout Removed old flat-ring algorithms and their tests. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>	2026-04-16 17:33:42 -07:00