test(miopen): add ReduceTensor numel>INT_MAX scale coverage (ALMIOPEN-2150) - #10253
Open
peymanr wants to merge 2 commits into
Open
test(miopen): add ReduceTensor numel>INT_MAX scale coverage (ALMIOPEN-2150)#10253peymanr wants to merge 2 commits into
peymanr wants to merge 2 commits into
Conversation
…-2150)
Add GetCasesReduceScaleLargeNumel() with shape {1,1,46342,46342}
(numel = 46342^2 = 2,147,580,964 > INT_MAX) exercising the MAX and ADD
operators over a full 4-D reduction to a scalar.
The MAX case is registered as DISABLED_Standard pending the fix tracked
in ALMIOPEN-2152: ReduceTensor MAX silently returns all-0.0 output with
status SUCCESS when numel exceeds INT_MAX. The ADD case is included so
both ops land in the same suite and are unfrozen together once fixed.
JIRA ID: ALMIOPEN-2150
✅ All Checks Passed — Ready for Review
📖 Need help? See the Policy FAQ for details on every check and how to fix failures. |
Pre-commit check failed⛔ pre-commit failed Please run locally:
This repo uses |
Fix clang-format violations in reduce.cpp flagged by pre-commit CI. Resolves: ALMIOPEN-2150
peymanr
force-pushed
the
users/prazaghi/almiopen-2150-reduce-scale
branch
from
August 1, 2026 00:01
035e00f to
a36636d
Compare
|
🎉 All checks passed! This PR is ready for review. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add scale-tier coverage for
ReduceTensorat numel > INT_MAX(
ALMIOPEN-2150).What
GetCasesReduceScaleLargeNumel()inside the existingreduce.cppanonymous namespace.{1, 1, 46342, 46342}(numel = 46342² = 2,147,580,964 >INT_MAX = 2,147,483,647) reduces all four dims to a scalar, targeting
the int32 index/workspace-size overflow path.
GPU_reduce_scale_large_numel_FP32fixture andDISABLED_Standardtest are wired up and instantiated in theStandardtier.Why DISABLED_Standard
A probe confirmed (ALMIOPEN-2152) that
ReduceTensorwith theMAXopsilently returns all-zero output with
miopenStatusSuccesswhennumel > INT_MAX. The test is therefore disabled pending the fix;remove the
DISABLED_prefix once ALMIOPEN-2152 is resolved. TheADDcase is included in the same suite so both ops are unfrozentogether.
JIRA ID: ALMIOPEN-2150
🤖 Assisted by PR Pundit