Skip to content

OCL_FP16 MatMul with large batch#24120

Merged
opencv-alalek merged 10 commits intoopencv:4.xfrom
dkurt:actualize_dnn_links
Aug 16, 2023
Merged

OCL_FP16 MatMul with large batch#24120
opencv-alalek merged 10 commits intoopencv:4.xfrom
dkurt:actualize_dnn_links

Conversation

@dkurt
Copy link
Copy Markdown
Member

@dkurt dkurt commented Aug 7, 2023

Pull Request Readiness Checklist

Merge with extra: opencv/opencv_extra#1080

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

  • I agree to contribute to the project under Apache 2 License.
  • To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
  • The PR is proposed to the proper branch
  • There is a reference to the original bug report and related work
  • There is accuracy test, performance test and test data in opencv_extra repository, if applicable
    Patch to opencv_extra has the same branch name.
  • The feature is well documented and sample code can be built with the project CMake
force_builders=Linux OpenCL,Win64 OpenCL
buildworker:Linux OpenCL=linux-1

@dkurt dkurt force-pushed the actualize_dnn_links branch from f5ddfa8 to 80130bb Compare August 9, 2023 11:13
@dkurt dkurt added the pr: needs test New functionality requires minimal tests set label Aug 9, 2023
@dkurt dkurt removed the pr: needs test New functionality requires minimal tests set label Aug 9, 2023
@dkurt dkurt force-pushed the actualize_dnn_links branch from f581f49 to ee87eac Compare August 9, 2023 14:59
}

INSTANTIATE_TEST_CASE_P(Layer_Test_Halide, FullyConnected, Combine(
/*batch*/ Values(1, 2, 4, 8, 24),
Copy link
Copy Markdown
Member Author

@dkurt dkurt Aug 10, 2023

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

24 batch size hangs locally but passed on CI. Batch size 16 is fine locally.

@dkurt dkurt marked this pull request as ready for review August 10, 2023 10:08
@opencv-alalek opencv-alalek added this to the 4.9.0 milestone Aug 10, 2023
Copy link
Copy Markdown
Contributor

@opencv-alalek opencv-alalek left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you 👍

@opencv-alalek opencv-alalek merged commit 8ad5eb5 into opencv:4.x Aug 16, 2023
@dkurt dkurt deleted the actualize_dnn_links branch August 16, 2023 12:48
@asmorkalov asmorkalov mentioned this pull request Sep 11, 2023
thewoz pushed a commit to thewoz/opencv that referenced this pull request Jan 4, 2024
OCL_FP16 MatMul with large batch

* Workaround FP16 MatMul with large batch

* Fix OCL reinitialization

* Higher thresholds for INT8 quantization

* Try fix gemm_buffer_NT for half (columns)

* Fix GEMM by rows

* Add batch dimension to InnerProduct layer test

* Fix Test_ONNX_conformance.Layer_Test/test_basic_conv_with_padding

* Batch 16

* Replace all vload4

* Version suffix for MobileNetSSD_deploy Caffe model
thewoz pushed a commit to thewoz/opencv that referenced this pull request May 29, 2024
OCL_FP16 MatMul with large batch

* Workaround FP16 MatMul with large batch

* Fix OCL reinitialization

* Higher thresholds for INT8 quantization

* Try fix gemm_buffer_NT for half (columns)

* Fix GEMM by rows

* Add batch dimension to InnerProduct layer test

* Fix Test_ONNX_conformance.Layer_Test/test_basic_conv_with_padding

* Batch 16

* Replace all vload4

* Version suffix for MobileNetSSD_deploy Caffe model
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Projects

None yet

Development

Successfully merging this pull request may close these issues.

DNN: OpenCL FP16 tests are broken (Test_ONNX_layers.MatMul_init_bcast) (2023-08-03)

2 participants