Revert "fix(ck): prevent int32 overflow in tensor descriptor element space size" (#10547) - #10947
Closed
ozturkosu wants to merge 1 commit into
Closed
Revert "fix(ck): prevent int32 overflow in tensor descriptor element space size" (#10547)#10947ozturkosu wants to merge 1 commit into
ozturkosu wants to merge 1 commit into
Conversation
JiaLuo-CAN
approved these changes
Aug 18, 2026
✅ All Checks Passed — Ready for Review
📖 Need help? See the Policy FAQ for details on every check and how to fix failures. |
|
🎉 All checks passed! This PR is ready for review. |
Contributor
|
Close the revert PR. Fixes required has been done in PR #10043. |
auto-merge was automatically disabled
August 18, 2026 23:48
Pull request was closed
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Revert of #10547
Reverts #10547 ("fix(ck): prevent int32 overflow in tensor descriptor element space size", squash commit
235faade) ondevelop, per team direction due to a CI test failure introduced by that change.#10547 fixed ROCM‑29071 (bug-bounty): a signed int32 overflow in
calculate_element_space_size_impl()/make_naive_tensor_descriptor()that causes an out-of-bounds GPU write (CWE‑787) in grouped conv bwd-weight whenK·C > INT32_MAX. Reverting restores that vulnerability.A re-fix must follow — track under ROCM‑29071. The original fix's own note explains the constraint (a blanket
static_cast<long_index_t>broke the gfx950/gfx1201/Windows math-libs build by flippingIsKnownAtCompileTime()to false; the merged version usedwiden_runtime_index_to_long()to widen only runtime operands). The re-fix should preserve that behavior while resolving the CI test failure that triggered this revert.Files reverted
include/ck/tensor_description/tensor_descriptor_helper.hpptest/util/CMakeLists.txttest/util/unit_tensor_descriptor_element_space_size.cpp(removed)cc the ROCM‑29071 owners.