Add metal_profiler to profile gpu on macos #63
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
junjihashimoto
force-pushed
the
feature/metal-profile
branch
from
a3cea26 to
22d91c8
Compare
|
When you call startCapture and endCapture, the file gpu.cpp.gputrace is output. |
junjihashimoto
force-pushed
the
feature/metal-profile
branch
from
22d91c8 to
bea9a3b
Compare
junjihashimoto
commented
Sep 28, 2024
| @@ -799,7 +803,11 @@ void runTest(int version, size_t M, size_t K, size_t N, | |||
| Tensor input = createTensor(ctx, Shape{M, K}, numtype, inputPtr.get()); | |||
| Tensor weights = createTensor(ctx, Shape{N, K}, numtype, weightsPtr.get()); // column-major | |||
|
|
|||
| #ifdef METAL_PROFILER | |||
| constexpr size_t nIter = 1; | |||
There was a problem hiding this comment.
Replaying gpu trace is slow.
Reduce the number of repetitions to reduce the load.
junjihashimoto
force-pushed
the
feature/metal-profile
branch
2 times, most recently
from
5ef2f10 to
93d1cd0
Compare
junjihashimoto
force-pushed
the
feature/metal-profile
branch
from
93d1cd0 to
0d40a07
Compare
|
Thx! |
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Outdated suggestions cannot be applied.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.
This PR adds start/stopCapture functions to profile metal shader functions.
#61
To call metal-functions on C++, we need to use objective-c++ or metal-cpp.
It simply provides C APIs using Objective-C.