webgpu: Reduce binary ops shader variants #5791
Open
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
|
@xhcao @axinging @haoyunfeix @gyagp PTAL, thanks. |
PERF This PR aims to reduce the warmup time by reducing binary ops shader variants. It may slightly hurt the inference time, but can greatly improve the warmup time. bodypix-mobilenet reduced ~300ms in the first pass on CFL.
qjia7
force-pushed
the
simplify_binary
branch
from
3b87b97 to
b9d2e24
Compare
axinging
reviewed
Nov 15, 2021
| const userCode = ` | ||
| fn binaryOperation(a : f32, b : f32) -> f32 { | ||
| ${opStr} | ||
| ${getBinaryOpString(this.op, false)} |
There was a problem hiding this comment.
LGTM. Do you have warmup and perf data?
nit, false can be removed.
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Outdated suggestions cannot be applied.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.
PERF
This PR aims to reduce the warmup time by reducing binary ops shader variants.
It may slightly hurt the inference time, but can greatly improve the warmup time.
bodypix-mobilenet reduced ~300ms in the first pass on CFL.
To see the logs from the Cloud Build CI, please join either our discussion or announcement mailing list.
This change is