[GPU] Use onednn impl for dynamic gemm #27212
Merged
Conversation
This file contains 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
sshlyapn
reviewed
Oct 24, 2024
| OV_GPU_GET_INSTANCE_OCL(gemm, shape_types::dynamic_shape) | ||
| OV_GPU_GET_INSTANCE_OCL(gemm, shape_types::dynamic_shape, | ||
| [](const program_node& node) { | ||
| return !node.can_use(impl_types::onednn); |
There was a problem hiding this comment.
Does oneDNN support efficient kernels caching for gemm? If not, this could cause runtime kernel recompilation and drop performance in some cases. This change probably requires wider performance check
There was a problem hiding this comment.
Checked on LNL with qwen2 and llama3, no performance drops were detected (with and w/o sdpa)
Lyamin-Roman
force-pushed
the
use_gemm_onednn_impl
branch
3 times, most recently
from
cb044a5
to
6025088
Compare
Lyamin-Roman
force-pushed
the
use_gemm_onednn_impl
branch
from
6025088
to
f57f45d
Compare
vladimir-paramuzov
approved these changes
Oct 31, 2024
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Outdated suggestions cannot be applied.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.
Details: