Skip to content
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.

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

Retire legacy preprocessing patterns which are already modeled by fusion. #14410

Closed
wants to merge 1 commit into from

Conversation

hanhanW
Copy link
Contributor

@hanhanW hanhanW commented Jul 14, 2023

No description provided.

@hanhanW hanhanW added benchmarks:cuda Run default CUDA benchmarks benchmarks:x86_64 Run default x86_64 benchmarks benchmarks:comp-stats Run default compilation statistics benchmarks benchmarks:android-cpu Run default Android CPU benchmarks benchmarks:android-gpu Run default Android GPU benchmarks and removed benchmarks:comp-stats Run default compilation statistics benchmarks labels Jul 14, 2023
@github-actions
Copy link

github-actions bot commented Jul 14, 2023

Abbreviated Benchmark Summary

@ commit d299ace6f95d90670f27cb222cf63d83ef166e48 (vs. base 49335b7ee56d3d3b58b0850a3dbba3e179524739)

Regressed Latencies 🚩

Benchmark Name Average Latency (ms) Median Latency (ms) Latency Standard Deviation (ms)
MobileNetV3Small\_fp32(tflite) [arm-valhall-vulkan\_android31-vulkan\_spirv][default-flags] vulkan(none)[full-inference,default-flags] with zeros @ pixel-6-pro[gpu] 9.140 (vs. 7.381, 23.83%↑) 9.193 0.285
MobileBertSquad\_int8(tflite) [arm-valhall-vulkan\_android31-vulkan\_spirv][default-flags] vulkan(none)[full-inference,default-flags] with zeros @ pixel-6-pro[gpu] 100.675 (vs. 87.382, 15.21%↑) 101.622 2.615
MobileNetV3Small\_fp32(tflite) [arm-valhall-vulkan\_android31-vulkan\_spirv][experimental-flags,fuse-padding,max-concurrency] vulkan(none)[full-inference,default-flags] with zeros @ pixel-6-pro[gpu] 8.672 (vs. 7.929, 9.37%↑) 8.632 0.133

[Top 3 out of 10 results showed]

Improved Latencies 🎉

Benchmark Name Average Latency (ms) Median Latency (ms) Latency Standard Deviation (ms)
MobileNetV2\_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags] local\_task(vmvx\_module)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 4698.424 (vs. 5017.274, 6.36%↓) 4736.794 130.781
DeepLabV3\_fp32(tflite) [x86\_64-cascadelake-linux\_gnu-llvm\_cpu][default-flags] local\_task(embedded\_elf)[1-thread,full-inference,default-flags] with zeros @ c2-standard-16[cpu] 33.894 (vs. 36.030, 5.93%↓) 33.925 0.194
MobileNetV3Small\_fp32(tflite) [vmvx-generic-vmvx-vmvx][experimental-flags] local\_task(vmvx\_module)[4-thread,full-inference,system-scheduling] with zeros @ pixel-6-pro[big-core] 952.656 (vs. 1012.464, 5.91%↓) 960.969 37.459

[Top 3 out of 6 results showed]

No improved or regressed compilation metrics 🏖️

For more information:

Source Workflow Run

@hanhanW hanhanW changed the title DNS -- Remove lagecy preprocessing patterns. Remove legacy preprocessing patterns which are modeled by Linalg fusion. Jul 14, 2023
@hanhanW hanhanW changed the title Remove legacy preprocessing patterns which are modeled by Linalg fusion. Retire legacy preprocessing patterns which are modeled by Linalg fusion. Jul 14, 2023
@hanhanW hanhanW marked this pull request as ready for review July 14, 2023 23:10
@hanhanW hanhanW requested a review from benvanik July 14, 2023 23:10
@hanhanW
Copy link
Contributor Author

hanhanW commented Jul 17, 2023

There were no regressions from the previous reports; the binary sizes are not changed. The regression seems to be noise.

@hanhanW hanhanW changed the title Retire legacy preprocessing patterns which are modeled by Linalg fusion. Retire legacy preprocessing patterns which are already modeled by fusion. Jul 17, 2023
@hanhanW hanhanW closed this Jul 21, 2023
@hanhanW hanhanW deleted the clean-out-dated branch July 21, 2023 18:06
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
benchmarks:android-cpu Run default Android CPU benchmarks benchmarks:android-gpu Run default Android GPU benchmarks benchmarks:comp-stats Run default compilation statistics benchmarks benchmarks:cuda Run default CUDA benchmarks benchmarks:x86_64 Run default x86_64 benchmarks
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant