218 warpsize patch #2916
Open
218 warpsize patch #2916
+1,914
−11,512
Conversation
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
There was a check in place that works around a performance bug in ptxas from CUDA 12.1. This check has various problems: 1. It's untested and the way it's implemented it can't be easily test. 2. The version check doesn't work library compilation which we transition towards as it's checking the version of a local ptxas binary 3. It's unclear whether the workaround is still needed with the new MLIR emitters. So I'm removing it here since it blocks me from making more refactoring around PTX compilation. PiperOrigin-RevId: 698720761
i-chaochen
requested review from
draganmladjenovic,
zoranjovanovic-ns and
amd-jianli12
Imported from GitHub PR openxla/xla#17814 This PR openxla/xla#11880 created a latent bug on ROCM side which was really hard to track. Due to [gemm_algorithm_picker](https://github.com/ROCm/xla/blob/58cd0e78dc19075e7c935d7cdb31676ce868e64c/xla/service/gpu/autotuning/gemm_algorithm_picker.cc#L299), the problem occurs only for non-zero beta when the output matrix is large enough (so it cannot be filled with two first runs). This results in buffer comparator errors like: ``` [ RUN ] CublasLtGemmRewriteTest.LargerBiasMultipleUsersNoRewrite WARNING: All log messages before absl::InitializeLog() is called are written to STDERR E0000 00:00:1727688442.093248 2145761 buffer_comparator.cc:157] Difference at 10069: -522.617, expected -261.495 E0000 00:00:1727688442.093370 2145761 buffer_comparator.cc:157] Difference at 10070: -520.456, expected -260.414 E0000 00:00:1727688442.093376 2145761 buffer_comparator.cc:157] Difference at 10071: -523.774, expected -262.073 E0000 00:00:1727688442.093381 2145761 buffer_comparator.cc:157] Difference at 10072: -524.935, expected -262.654 E0000 00:00:1727688442.093385 2145761 buffer_comparator.cc:157] Difference at 10073: -520.083, expected -260.228 E0000 00:00:1727688442.093389 2145761 buffer_comparator.cc:157] Difference at 10074: -522.771, expected -261.572 E0000 00:00:1727688442.093393 2145761 buffer_comparator.cc:157] Difference at 10075: -519.994, expected -260.183 E0000 00:00:1727688442.093396 2145761 buffer_comparator.cc:157] Difference at 10076: -524.838, expected -262.605 E0000 00:00:1727688442.093400 2145761 buffer_comparator.cc:157] Difference at 10077: -520.376, expected -260.374 E0000 00:00:1727688442.093404 2145761 buffer_comparator.cc:157] Difference at 10078: -521.808, expected -261.09 2024-09-30 09:27:22.093423: E xla/service/gpu/autotuning/gemm_algorithm_picker.cc:348] Results mismatch between different GEMM algorithms. This is likely a bug/unexpected loss of precision. E0000 00:00:1727688442.095749 2145761 buffer_comparator.cc:157] Difference at 10069: -783.74, expected -261.495 E0000 00:00:1727688442.095766 2145761 buffer_comparator.cc:157] Difference at 10070: -780.498, expected -260.414 E0000 00:00:1727688442.095770 2145761 buffer_comparator.cc:157] Difference at 10071: -785.475, expected -262.073 E0000 00:00:1727688442.095774 2145761 buffer_comparator.cc:157] Difference at 10072: -787.216, expected -262.654 E0000 00:00:1727688442.095778 2145761 buffer_comparator.cc:157] Difference at 10073: -779.939, expected -260.228 E0000 00:00:1727688442.095782 2145761 buffer_comparator.cc:157] Difference at 10074: -783.97, expected -261.572 E0000 00:00:1727688442.095785 2145761 buffer_comparator.cc:157] Difference at 10075: -779.805, expected -260.183 E0000 00:00:1727688442.095789 2145761 buffer_comparator.cc:157] Difference at 10076: -787.071, expected -262.605 E0000 00:00:1727688442.095793 2145761 buffer_comparator.cc:157] Difference at 10077: -780.378, expected -260.374 E0000 00:00:1727688442.095797 2145761 buffer_comparator.cc:157] Difference at 10078: -782.526, expected -261.09 ``` but in fact it was just because of uninitialized buffers. @xla-rotation could you please take a look ? Copybara import of the project: -- 58cd0e78dc19075e7c935d7cdb31676ce868e64c by Pavel Emeliyanenko <[email protected]>: buffer_comparator init fix Merging this change closes tensorflow#17814 PiperOrigin-RevId: 683569591
…hardware limit per dim. PiperOrigin-RevId: 691903035
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.
backported two big commits for fixing warp size