ywkang/kernbench2
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
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>
This commit is contained in:
Yangwook Kang
2026-04-08 23:35:31 -07:00
parent 161132cdcb
commit b6eb97c49a
40 changed files with 4055 additions and 214 deletions
Download Patch File Download Diff File Expand all files Collapse all files
topology.yaml
+15 -6
View File
@@ -63,19 +63,28 @@ cube:
pe_cpu: { kind: pe_cpu, impl: pe_cpu_v1, attrs: { overhead_ns: 2.0 } }
pe_scheduler: { kind: pe_scheduler, impl: pe_scheduler_v2, attrs: { overhead_ns: 1.0 } }
pe_dma: { kind: pe_dma, impl: pe_dma_v1, attrs: { rd_engines: 1, wr_engines: 1 } }
pe_gemm: { kind: pe_gemm, impl: pe_gemm_v1, attrs: { overhead_ns: 0.0, shared_resource: accel_slot, peak_tflops_f16: 8.0 } }
pe_math: { kind: pe_math, impl: pe_math_v1, attrs: { overhead_ns: 0.0, shared_resource: accel_slot } }
pe_mmu: { kind: pe_mmu, impl: pe_mmu_v1, attrs: { tlb_overhead_ns: 0.5, page_size: 4096 } }
pe_tcm: { kind: pe_tcm, impl: pe_tcm_v1, attrs:
{ size_mb: 16 } }
pe_gemm: { kind: pe_gemm, impl: pe_gemm_v1, attrs: { overhead_ns: 0.0, shared_resource: accel_slot, peak_tflops_f16: 8.0 } }
pe_math: { kind: pe_math, impl: pe_math_v1, attrs: { overhead_ns: 0.0, shared_resource: accel_slot } }
pe_fetch_store: { kind: pe_fetch_store, impl: pe_fetch_store_v1, attrs: { overhead_ns: 0.0 } }
pe_mmu: { kind: pe_mmu, impl: pe_mmu_v1, attrs: { tlb_overhead_ns: 0.5, page_size: 4096 } }
pe_tcm: { kind: pe_tcm, impl: pe_tcm_v1, attrs: { size_mb: 16, read_bw_gbs: 512.0, write_bw_gbs: 512.0 } }
links:
pe_cpu_to_scheduler_mm: 0.5
scheduler_to_dma_mm: 0.5
scheduler_to_gemm_mm: 0.5
scheduler_to_math_mm: 0.5
scheduler_to_fetch_store_mm: 0.5
dma_to_tcm_bw_gbs: 512.0
dma_to_tcm_mm: 0.5
gemm_to_tcm_bw_gbs: 512.0 # GEMM reads inputs from TCM (ADR-0014 D5)
dma_to_fetch_store_mm: 0.0 # DMA → fetch_store chaining (ADR-0021)
fetch_store_to_tcm_bw_gbs: 512.0
fetch_store_to_tcm_mm: 0.0
fetch_store_to_gemm_mm: 0.0 # fetch → GEMM chaining (ADR-0021)
fetch_store_to_math_mm: 0.0 # fetch → MATH chaining (ADR-0021)
gemm_to_fetch_store_mm: 0.0 # GEMM → store chaining (ADR-0021)
math_to_fetch_store_mm: 0.0 # MATH → store chaining (ADR-0021)
fetch_store_to_dma_mm: 0.0 # store → DMA writeback chaining (ADR-0021)
gemm_to_tcm_bw_gbs: 512.0
gemm_to_tcm_mm: 0.5
math_to_tcm_bw_gbs: 512.0
math_to_tcm_mm: 0.5