Skip to content

Folded cache design for Insitu cache#13

Draft
Aquaticfuller wants to merge 26 commits intomainfrom
dev/cache-refactoring-multi-tile
Draft

Folded cache design for Insitu cache#13
Aquaticfuller wants to merge 26 commits intomainfrom
dev/cache-refactoring-multi-tile

Conversation

@Aquaticfuller
Copy link
Copy Markdown
Member

No description provided.

DiyouS and others added 26 commits November 21, 2025 09:43
- pass core wstrb into cachepool_cache_ctrl and use per-byte bank enables
- map wide line SRAMs to byte-wide BE slices in cachepool_tile
- bump 512b line tag/meta width to avoid truncation with byte masks
- update local build/sim overrides used to run the modified insitu-cache
- wire DataPartSplit/folded params through cluster/group/tile
- implement skewed folded data SRAM mapping in cachepool_tile
- adjust cluster wrapper tb for the new configuration
- add scalar cache tests that run basic and stress patterns without crossing 128-bit parts
- add vector cache tests that use RVV loads/stores on 128-bit chunks and verify data integrity
- integrate both tests into the test CMake and keep patterns aligned to folded-cache part size
Select a single part per column/bank per cycle and prioritize write parts over read parts to avoid clobbering bank signals.
  - cachepool_tile: use EffectiveCoalFactor=1 in folded mode; pass to cache ctrl.
  - cachepool_cc: size Spatz response FIFO with NumSpatzOutstandingLoads; add overflow assert.
  - tcdm_cache_interco: add non-synthesis outstanding scoreboard/asserts for req/rsp matching.
Bump insitu-cache to the folded/hash-way revision, thread
UseHashWaySelect through cluster/tile, and queue Spatz memory
responses through the local response FIFO instead of bypassing
write acks.
@Aquaticfuller Aquaticfuller requested a review from DiyouS March 27, 2026 14:06
@Aquaticfuller Aquaticfuller self-assigned this Mar 27, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants