ywkang b6eb97c49a Implement ADR-0021: PE pipeline refactor with token self-routing ...

Step 1-2: Backup existing code
- builtin/ → builtin_legacy/ (unchanged backup)
- custom/pe_accel/ → custom/pe_accel_legacy/ (unchanged backup)

Step 3-4: New pipeline types and tiling
- pe_types.py: StageType, Stage, TilePlan, PipelinePlan, PipelineContext, TileToken
- tiling.py: generate_gemm_plan, generate_math_plan (ported from pe_accel)

Step 5: Component implementations (ADR-0021 D4-D6)
- PE_SCHEDULER: _feed_loop (singleton FIFO feeder) + plan generation
- PE_FETCH_STORE: new component — TCM ↔ Register File
- PE_GEMM: TileToken pipeline + legacy PeInternalTxn dual-mode
- PE_MATH: TileToken pipeline + legacy dual-mode
- PE_DMA: TileToken pipeline + legacy + fabric Transaction triple-mode
- PE_TCM: TcmRequest handler with dual-channel BW serialization

Step 6: Infrastructure
- topology.yaml: pe_fetch_store component + chaining edges
- components.yaml: pe_fetch_store_v1 registration
- builder.py: PE_COMP_OFFSETS, _add_pe_internal_edges, PE view positions
- Tests: node/edge counts, PE component sets updated

All components handle both TileToken (pipeline) and PeInternalTxn (legacy).
Token self-routing: components read next stage from token.plan, chain via out_port.
366 tests passing.

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

2026-04-08 23:35:31 -07:00

..

custom

Add SIP-level tensor parallelism, component registry YAML, VA offset verification

2026-03-26 01:13:17 -07:00

test_bw_occupancy.py

Replace xbar/bridge/single-NOC with explicit router mesh (ADR-0019)

2026-04-04 17:51:28 -07:00

test_cli.py

Fix cross-SIP PE_TCM access by scoping deploy to target_device SIP

2026-04-04 18:03:11 -07:00

test_component_registry.py

Remove xbar/noc remnants, rule-based cube-view connectors

2026-04-06 23:59:12 -07:00

test_data_executor.py

Implement ADR-0020: 2-pass data execution with greenlet kernel runner

2026-04-08 00:22:44 -07:00

test_engine.py

Add probe CLI improvements, D2H read, UCIe/HBM tuning, BW sweep

2026-03-19 01:16:18 -07:00

test_iochiplet_noc_d2h.py

Add probe CLI improvements, D2H read, UCIe/HBM tuning, BW sweep

2026-03-19 01:16:18 -07:00

test_kernel_runner.py

Implement ADR-0020: 2-pass data execution with greenlet kernel runner

2026-04-08 00:22:44 -07:00

test_memory_store.py

Implement ADR-0020: 2-pass data execution with greenlet kernel runner

2026-04-08 00:22:44 -07:00

test_mmu_component.py

Add SIP-level tensor parallelism, component registry YAML, VA offset verification

2026-03-26 01:13:17 -07:00

test_mmu_fabric.py

Wire PE_MMU to router mesh for MmuMapMsg delivery

2026-04-04 18:10:42 -07:00

test_noc_mesh.py

Remove xbar/noc remnants, rule-based cube-view connectors

2026-04-06 23:59:12 -07:00

test_op_log.py

Implement ADR-0020: 2-pass data execution with greenlet kernel runner

2026-04-08 00:22:44 -07:00

test_pe_components.py

Fix cross-SIP PE_TCM access by scoping deploy to target_device SIP

2026-04-04 18:03:11 -07:00

test_pe_mmu.py

Add virtual memory support: PE_MMU, VA allocator, fabric MmuMapMsg

2026-03-26 00:01:47 -07:00

test_phase_a_components.py

Remove xbar/noc remnants, rule-based cube-view connectors

2026-04-06 23:59:12 -07:00

test_phyaddr.py

commit - release 1

2026-03-18 11:47:48 -07:00

test_probe.py

Remove xbar/noc remnants, rule-based cube-view connectors

2026-04-06 23:59:12 -07:00

test_routing.py

Replace xbar/bridge/single-NOC with explicit router mesh (ADR-0019)

2026-04-04 17:51:28 -07:00

test_sip_parallel.py

Add SIP-level tensor parallelism, component registry YAML, VA offset verification

2026-03-26 01:13:17 -07:00

test_tensor_free.py

Wire PE_MMU to router mesh for MmuMapMsg delivery

2026-04-04 18:10:42 -07:00

test_tensor.py

commit - release 1

2026-03-18 11:47:48 -07:00

test_topology_compile.py

Implement ADR-0021: PE pipeline refactor with token self-routing

2026-04-08 23:35:31 -07:00

test_topology_load.py

Implement ADR-0021: PE pipeline refactor with token self-routing

2026-04-08 23:35:31 -07:00

test_topology_visualize.py

Cube-view SVG: detailed topology validation rendering

2026-04-04 22:03:38 -07:00

test_triton_emu.py

Add virtual memory support: PE_MMU, VA allocator, fabric MmuMapMsg

2026-03-26 00:01:47 -07:00

test_va_allocator.py

Add virtual memory support: PE_MMU, VA allocator, fabric MmuMapMsg

2026-03-26 00:01:47 -07:00

test_va_integration.py

Add SIP-level tensor parallelism, component registry YAML, VA offset verification

2026-03-26 01:13:17 -07:00

test_va_offset.py

Fix cross-SIP PE_TCM access by scoping deploy to target_device SIP

2026-04-04 18:03:11 -07:00