Skip to content

[Benchmarks][CI] add UR SubmitGraph benchmark #17853

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 1 commit into from
Apr 7, 2025
Merged

[Benchmarks][CI] add UR SubmitGraph benchmark #17853

merged 1 commit into from
Apr 7, 2025

Conversation

pbalcer
Copy link
Contributor

@pbalcer pbalcer commented Apr 4, 2025 

running graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 0 measureCompletion 0, iteration 0... 
graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 0 measureCompletion 0 complete (graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 0 measureCompletion 0: 14.738 μs).
running graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 0 measureCompletion 1, iteration 0... 
graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 0 measureCompletion 1 complete (graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 0 measureCompletion 1: 15.132 μs).
running graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 0 measureCompletion 0, iteration 0... 
graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 0 measureCompletion 0 complete (graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 0 measureCompletion 0: 29.481 μs).
running graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 0 measureCompletion 1, iteration 0... 
graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 0 measureCompletion 1 complete (graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 0 measureCompletion 1: 30.309 μs).
running graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 0 measureCompletion 0, iteration 0... 
graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 0 measureCompletion 0 complete (graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 0 measureCompletion 0: 85.288 μs).
running graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 0 measureCompletion 1, iteration 0... 
graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 0 measureCompletion 1 complete (graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 0 measureCompletion 1: 85.948 μs).
running graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 1 measureCompletion 0, iteration 0... 
graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 1 measureCompletion 0 complete (graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 1 measureCompletion 0: 15.483 μs).
running graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 1 measureCompletion 1, iteration 0... 
graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 1 measureCompletion 1 complete (graph_api_benchmark_sycl SubmitGraph numKernels:4 ioq 1 measureCompletion 1: 16.589 μs).
running graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 1 measureCompletion 0, iteration 0... 
graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 1 measureCompletion 0 complete (graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 1 measureCompletion 0: 31.217 μs).
running graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 1 measureCompletion 1, iteration 0... 
graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 1 measureCompletion 1 complete (graph_api_benchmark_sycl SubmitGraph numKernels:10 ioq 1 measureCompletion 1: 31.615 μs).
running graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 1 measureCompletion 0, iteration 0... 
graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 1 measureCompletion 0 complete (graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 1 measureCompletion 0: 86.204 μs).
running graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 1 measureCompletion 1, iteration 0... 
graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 1 measureCompletion 1 complete (graph_api_benchmark_sycl SubmitGraph numKernels:32 ioq 1 measureCompletion 1: 86.468 μs).
running graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 0 measureCompletion 0, iteration 0... 
graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 0 measureCompletion 0 complete (graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 0 measureCompletion 0: 11.087 μs).
running graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 0 measureCompletion 1, iteration 0... 
graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 0 measureCompletion 1 complete (graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 0 measureCompletion 1: 11.178 μs).
running graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 0 measureCompletion 0, iteration 0... 
graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 0 measureCompletion 0 complete (graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 0 measureCompletion 0: 21.347 μs).
running graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 0 measureCompletion 1, iteration 0... 
graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 0 measureCompletion 1 complete (graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 0 measureCompletion 1: 22.886 μs).
running graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 0 measureCompletion 0, iteration 0... 
graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 0 measureCompletion 0 complete (graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 0 measureCompletion 0: 61.907 μs).
running graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 0 measureCompletion 1, iteration 0... 
graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 0 measureCompletion 1 complete (graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 0 measureCompletion 1: 63.073 μs).
running graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 1 measureCompletion 0, iteration 0... 
graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 1 measureCompletion 0 complete (graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 1 measureCompletion 0: 11.016 μs).
running graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 1 measureCompletion 1, iteration 0... 
graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 1 measureCompletion 1 complete (graph_api_benchmark_ur SubmitGraph numKernels:4 ioq 1 measureCompletion 1: 14.501 μs).
running graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 1 measureCompletion 0, iteration 0... 
graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 1 measureCompletion 0 complete (graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 1 measureCompletion 0: 21.556 μs).
running graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 1 measureCompletion 1, iteration 0... 
graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 1 measureCompletion 1 complete (graph_api_benchmark_ur SubmitGraph numKernels:10 ioq 1 measureCompletion 1: 21.254 μs).
running graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 1 measureCompletion 0, iteration 0... 
graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 1 measureCompletion 0 complete (graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 1 measureCompletion 0: 67.115 μs).
running graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 1 measureCompletion 1, iteration 0... 
graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 1 measureCompletion 1 complete (graph_api_benchmark_ur SubmitGraph numKernels:32 ioq 1 measureCompletion 1: 63.078 μs).

@pbalcer pbalcer requested a review from a team as a code owner April 4, 2025 11:14
@pbalcer pbalcer temporarily deployed to WindowsCILock April 4, 2025 11:14 — with GitHub Actions Inactive
@pbalcer
Copy link
Contributor Author

pbalcer commented Apr 4, 2025

@reble @EwanC ping

@EwanC
Copy link
Contributor

EwanC commented Apr 4, 2025

Cool, thanks 👍 We've started working on #17734 and I think that has the potential to change some of these numbers, not that we should hold up merging this because of that.

@pbalcer pbalcer temporarily deployed to WindowsCILock April 4, 2025 11:35 — with GitHub Actions Inactive
@pbalcer pbalcer temporarily deployed to WindowsCILock April 4, 2025 11:35 — with GitHub Actions Inactive
@pbalcer
Copy link
Contributor Author

pbalcer commented Apr 7, 2025

@intel/llvm-reviewers-benchmarking ping

@pbalcer
Copy link
Contributor Author

pbalcer commented Apr 7, 2025

@intel/llvm-gatekeepers please merge. The CI failure is unrelated (system is dead).

@martygrant martygrant merged commit 1b2b55c into intel:sycl Apr 7, 2025
24 of 25 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@PatKamin PatKamin PatKamin approved these changes

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

4 participants

@pbalcer @EwanC @PatKamin @martygrant