PR #47472: [oneDNN][TSL] Add AMX_FP8 CPU feature definition and CPUID detection - #3619
Open
copybara-service[bot] wants to merge 1 commit into
Open
PR #47472: [oneDNN][TSL] Add AMX_FP8 CPU feature definition and CPUID detection#3619copybara-service[bot] wants to merge 1 commit into
copybara-service[bot] wants to merge 1 commit into
Conversation
… detection Imported from GitHub PR openxla/xla#47472 This PR is part 1 and pre-requisite for PR openxla/xla#43318 . The upstreamed openxla/xla#43318 has errors. Penporn suggested to break into two, with first PR just adding the CPU feature definition and this PR just carves out the first part from PR43318. 🎯 Justification The CI for TensorFlow uses its own pinned copy of TSL, not the one inside XLA's third_party/tsl/. Orig PR#43318 adds AMX_FP8 = 48 to XLA's local TSL copy and immediately references it in XLA code (cpu_features.cc, onednn_util.h, etc.). But when TF CI builds XLA, it resolves tsl::port::CPUFeature from its own TSL — which doesn't have AMX_FP8 yet — causing: error: no member named 'AMX_FP8' in 'tsl::port::CPUFeature' causing build failures. Once this PR gets merged, PR43318 can be rebased, we won't see the CI errors. Copybara import of the project: -- d4d9cecfa9bd4ff858603cb41de4533b206c55d6 by Gauri Deshpande <gauri1.deshpande@intel.com>: [TSL] Add AMX_FP8 CPU feature definition and CPUID detection Merging this change closes #47472 FUTURE_COPYBARA_INTEGRATE_REVIEW=openxla/xla#47472 from Intel-tensorflow:gaurides/amx_fp8_cpu_info d4d9cecfa9bd4ff858603cb41de4533b206c55d6 PiperOrigin-RevId: 970436099
copybara-service
Bot
force-pushed
the
test_970436099
branch
from
August 28, 2026 18:51
182047c to
fa94c04
Compare
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.
PR #47472: [oneDNN][TSL] Add AMX_FP8 CPU feature definition and CPUID detection
Imported from GitHub PR openxla/xla#47472
This PR is part 1 and pre-requisite for PR openxla/xla#43318 .
The upstreamed openxla/xla#43318 has errors. Penporn suggested to break into two, with first PR just adding the CPU feature definition and this PR just carves out the first part from PR43318.
🎯 Justification
The CI for TensorFlow uses its own pinned copy of TSL, not the one inside XLA's third_party/tsl/. Orig PR#43318 adds AMX_FP8 = 48 to XLA's local TSL copy and immediately references it in XLA code (cpu_features.cc, onednn_util.h, etc.). But when TF CI builds XLA, it resolves tsl::port::CPUFeature from its own TSL — which doesn't have AMX_FP8 yet — causing:
error: no member named 'AMX_FP8' in 'tsl::port::CPUFeature' causing build failures.
Once this PR gets merged, PR43318 can be rebased, we won't see the CI errors.
Copybara import of the project:
--
d4d9cecfa9bd4ff858603cb41de4533b206c55d6 by Gauri Deshpande gauri1.deshpande@intel.com:
[TSL] Add AMX_FP8 CPU feature definition and CPUID detection
Merging this change closes #47472
FUTURE_COPYBARA_INTEGRATE_REVIEW=openxla/xla#47472 from Intel-tensorflow:gaurides/amx_fp8_cpu_info d4d9cecfa9bd4ff858603cb41de4533b206c55d6