Fix overflow and stride>1 fallback in cadence::quantized_conv1d HiFi kernels (#19193)#19193
Open
hsharma35 wants to merge 1 commit intopytorch:mainfrom
Open
Fix overflow and stride>1 fallback in cadence::quantized_conv1d HiFi kernels (#19193)#19193hsharma35 wants to merge 1 commit intopytorch:mainfrom
hsharma35 wants to merge 1 commit intopytorch:mainfrom
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19193
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ✅ You can merge normally! (2 Unrelated Failures)As of commit de7fb48 with merge base d9688da ( FLAKY - The following job failed but was likely due to flakiness present on trunk:
BROKEN TRUNK - The following job failed but was present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
Contributor
|
@hsharma35 has exported this pull request. If you are a Meta employee, you can view the originating Diff in D102821209. |
meta-cla
Bot
added
the
CLA Signed
This PR needs a
|
mcremon-meta
approved these changes
Apr 28, 2026
hsharma35
force-pushed
the
export-D102821209
branch
from
b223e7d to
2564f71
Compare
zonglinpeng
approved these changes
Apr 28, 2026
hsharma35
added a commit
to hsharma35/executorch
that referenced
this pull request
Apr 28, 2026
…kernels Summary: PR pytorch#19193 Fixes two correctness bugs in the HiFi kernels for cadence::quantized_conv1d_ncl.out and cadence::quantized_conv1d_nlc.out. The int8 path (xa_nn_conv2d_per_chan_sym8sxasym8s) produces incorrect results with stride > 1 on some backends (e.g., Artemis HiFi4) and is now redirected to the generic fallback for that case. The uint8 path overflowed WORD32 when computing out_multiplier32 if eff_scale >= 1.0 (i.e., output_scale > bias_scale), which is now clamped to INT32_MAX. Reviewed By: zonglinpeng Differential Revision: D102821209
hsharma35
force-pushed
the
export-D102821209
branch
from
2564f71 to
fa8c00c
Compare
hsharma35
added a commit
to hsharma35/executorch
that referenced
this pull request
Apr 28, 2026
…kernels (pytorch#19193) Summary: PR pytorch#19193 Fixes two correctness bugs in the HiFi kernels for cadence::quantized_conv1d_ncl.out and cadence::quantized_conv1d_nlc.out. The int8 path (xa_nn_conv2d_per_chan_sym8sxasym8s) produces incorrect results with stride > 1 on some backends (e.g., Artemis HiFi4) and is now redirected to the generic fallback for that case. The uint8 path overflowed WORD32 when computing out_multiplier32 if eff_scale >= 1.0 (i.e., output_scale > bias_scale), which is now clamped to INT32_MAX. Reviewed By: zonglinpeng Differential Revision: D102821209
hsharma35
added a commit
to hsharma35/executorch
that referenced
this pull request
Apr 29, 2026
…kernels (pytorch#19193) Summary: PR pytorch#19193 Fixes two correctness bugs in the HiFi kernels for cadence::quantized_conv1d_ncl.out and cadence::quantized_conv1d_nlc.out. The int8 path (xa_nn_conv2d_per_chan_sym8sxasym8s) produces incorrect results with stride > 1 on some backends (e.g., Artemis HiFi4) and is now redirected to the generic fallback for that case. The uint8 path overflowed WORD32 when computing out_multiplier32 if eff_scale >= 1.0 (i.e., output_scale > bias_scale), which is now clamped to INT32_MAX. Reviewed By: zonglinpeng Differential Revision: D102821209
…kernels (pytorch#19193) Summary: PR pytorch#19193 Fixes two correctness bugs in the HiFi kernels for cadence::quantized_conv1d_ncl.out and cadence::quantized_conv1d_nlc.out. The int8 path (xa_nn_conv2d_per_chan_sym8sxasym8s) produces incorrect results with stride > 1 on some backends (e.g., Artemis HiFi4) and is now redirected to the generic fallback for that case. The uint8 path overflowed WORD32 when computing out_multiplier32 if eff_scale >= 1.0 (i.e., output_scale > bias_scale), which is now clamped to INT32_MAX. Reviewed By: zonglinpeng Differential Revision: D102821209
meta-codesync
Bot
changed the title
hsharma35
force-pushed
the
export-D102821209
branch
from
fa8c00c to
de7fb48
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
3 participants
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.
Fixes two correctness bugs in the HiFi kernels for cadence::quantized_conv1d_ncl.out and cadence::quantized_conv1d_nlc.out. The int8 path (xa_nn_conv2d_per_chan_sym8sxasym8s) produces incorrect results with stride > 1 on some backends (e.g., Artemis HiFi4) and is now redirected to the generic fallback for that case. The uint8 path overflowed WORD32 when computing out_multiplier32 if eff_scale >= 1.0 (i.e., output_scale > bias_scale), which is now clamped to INT32_MAX.
Reviewed By: zonglinpeng
Differential Revision: D102821209