test: use block_dim=0 (auto) instead of hardcoded platform max#1309
Open
doraemonmj wants to merge 1 commit into
Open
test: use block_dim=0 (auto) instead of hardcoded platform max#1309doraemonmj wants to merge 1 commit into
doraemonmj wants to merge 1 commit into
Conversation
Many scene tests hardcoded the runtime config block_dim to the platform maximum (24 on a2a3, 36 on a5). That value is exactly what block_dim=0 resolves to: DeviceRunner treats 0 as the CallConfig auto sentinel and resolves it at run() time to the stream's max capacity (onboard queries the actual cube/vector core counts via aclrtGetStreamResLimit and caps at PLATFORM_MAX_BLOCKDIM; sim uses PLATFORM_MAX_BLOCKDIM directly). Zero out the a2a3 (24) and a5 (36) config block_dim values so the tests follow the hardware's actual available core count instead of pinning a literal. Kernel-side params.block_dim (tiling arg) is left untouched.
|
Warning Gemini encountered an error creating the review. You can try again by commenting |
📝 WalkthroughWalkthroughThis change updates Changesblock_dim configuration reset
Estimated code review effort: 1 (Trivial) | ~5 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
🧹 Nitpick comments (1)
tests/st/a2a3/tensormap_and_ringbuffer/spmd_basic/test_spmd_basic.py (1)
74-86: 📐 Maintainability & Code Quality | 🔵 Trivial | 💤 Low valueCase1 and Case2_AutoBlockDim are now functionally equivalent.
Case1 explicitly sets
block_dim: 0and Case2_AutoBlockDim omitsblock_dim(defaulting to 0 via_build_config). Both resolve to the sameCallConfig, making the two cases redundant in terms of runtime configuration. If the intent is to test both the explicit-0 and omitted paths as distinct regression cases, consider adding a comment to Case1 clarifying that distinction. Otherwise, Case2_AutoBlockDim could be removed.🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@tests/st/a2a3/tensormap_and_ringbuffer/spmd_basic/test_spmd_basic.py` around lines 74 - 86, Case1 and Case2_AutoBlockDim are redundant because both end up using the same CallConfig through block_dim=0. Update the table entry in test_spmd_basic to either remove Case2_AutoBlockDim or add a clear comment near Case1 and Case2 explaining that one exercises the explicit block_dim=0 path and the other exercises the omitted-field path via _build_config, so the distinction is intentional.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Nitpick comments:
In `@tests/st/a2a3/tensormap_and_ringbuffer/spmd_basic/test_spmd_basic.py`:
- Around line 74-86: Case1 and Case2_AutoBlockDim are redundant because both end
up using the same CallConfig through block_dim=0. Update the table entry in
test_spmd_basic to either remove Case2_AutoBlockDim or add a clear comment near
Case1 and Case2 explaining that one exercises the explicit block_dim=0 path and
the other exercises the omitted-field path via _build_config, so the distinction
is intentional.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: 9a577d69-2578-4554-831e-3134c73b3635
📒 Files selected for processing (26)
examples/a2a3/tensormap_and_ringbuffer/benchmark_bgemm/test_benchmark_bgemm.pyexamples/a2a3/tensormap_and_ringbuffer/paged_attention/test_paged_attention.pyexamples/a2a3/tensormap_and_ringbuffer/paged_attention_manual_scope/test_paged_attention.pyexamples/a2a3/tensormap_and_ringbuffer/paged_attention_ringbuffer/test_paged_attention_ringbuffer.pyexamples/a2a3/tensormap_and_ringbuffer/paged_attention_unroll_manual_scope/test_paged_attention_unroll.pyexamples/a5/tensormap_and_ringbuffer/paged_attention_unroll_manual_scope/test_paged_attention_unroll.pytests/st/a2a3/host_build_graph/bgemm/test_bgemm.pytests/st/a2a3/host_build_graph/paged_attention/test_paged_attention.pytests/st/a2a3/tensormap_and_ringbuffer/alternating_matmul_add/test_alternating_matmul_add.pytests/st/a2a3/tensormap_and_ringbuffer/batch_paged_attention/test_batch_paged_attention.pytests/st/a2a3/tensormap_and_ringbuffer/fanin_lookup_perf/test_fanin_lookup_perf.pytests/st/a2a3/tensormap_and_ringbuffer/multi_round_paged_attention/test_multi_round_paged_attention.pytests/st/a2a3/tensormap_and_ringbuffer/paged_attention_unroll/test_paged_attention_unroll.pytests/st/a2a3/tensormap_and_ringbuffer/paged_attention_unroll_4dims/test_paged_attention_unroll_4dims.pytests/st/a2a3/tensormap_and_ringbuffer/spmd_basic/test_spmd_basic.pytests/st/a2a3/tensormap_and_ringbuffer/spmd_batch_dispatch_oob/test_spmd_batch_dispatch_oob.pytests/st/a2a3/tensormap_and_ringbuffer/spmd_multiblock_aiv/test_spmd_multiblock_aiv.pytests/st/a2a3/tensormap_and_ringbuffer/spmd_multiblock_mix/test_spmd_multiblock_mix.pytests/st/a2a3/tensormap_and_ringbuffer/spmd_paged_attention/test_spmd_paged_attention.pytests/st/a2a3/tensormap_and_ringbuffer/spmd_paged_attention_highperf/test_spmd_paged_attention_highperf.pytests/st/a2a3/tensormap_and_ringbuffer/spmd_starvation/test_spmd_starvation.pytests/st/a2a3/tensormap_and_ringbuffer/spmd_sync_start/test_spmd_sync_start.pytests/st/a2a3/tensormap_and_ringbuffer/spmd_sync_start_aiv/test_spmd_sync_start_aiv.pytests/st/a2a3/tensormap_and_ringbuffer/spmd_sync_start_edge/test_spmd_sync_start_edge.pytests/st/a2a3/tensormap_and_ringbuffer/spmd_sync_start_stress/test_spmd_sync_start_stress.pytests/st/a5/tensormap_and_ringbuffer/paged_attention_unroll/test_paged_attention_unroll.py
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
Many scene tests hardcoded the runtime
configblock_dimto the platformmaximum — 24 on a2a3, 36 on a5. That literal is exactly what
block_dim=0already resolves to.
block_dim=0is the CallConfig auto sentinel:DeviceRunnerresolves itat
run()time to the stream's max block capacity.aclrtGetStreamResLimitand caps atPLATFORM_MAX_BLOCKDIM.PLATFORM_MAX_BLOCKDIMdirectly (a2a3=24, a5=36).Change
Zero out the a2a3 (
24) and a5 (36)configblock_dimvalues so thesetests follow the hardware's actual available core count instead of pinning a
literal that happens to equal today's platform max.
CASES[*]["config"]["block_dim"].params.block_dim(a tiling arg, e.g. inspmd_paged_attention_highperf) is left untouched.9/3, a5 SPMD/PA cases pinned to24,block_dim1/2) are left untouched.26 files, 70 config values →
0.