[webgpu] support arbitrary input_channel size for im2col #27038
+38
−21
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
Contributor
Author
qjia7
reviewed
Jan 16, 2026
| // If the status of this condition is uncertain, the feature must be disabled. | ||
| const bool use_subgroup = false; | ||
| Im2ColMatMulProgram im2col_mm_program{has_bias, tile_m, tile_n, use_subgroup}; | ||
| const uint32_t vec_size = channel_input % 4 == 0 ? 4 : 1; |
Contributor
There was a problem hiding this comment.
How about extending it into 1, 2 or 4? const uint32_t vec_size = GetMaxComponents(channel_input);
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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Outdated suggestions cannot be applied.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.
Description
This PR supports
vec1for arbitraryinput_channelinim2colkernel, which could bring performance gain to more models.Like for
yolov8n_posemodel, there is about ~7% gain for whole model, and ~50% for thoseconv2dop whichinput_sizeare not multiple of 4.Motivation and Context