Skip to content

[WebGPU EP] fix for reduce min/max error on MacOS CI #24077

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

Merged
guschmue merged 6 commits into from
Mar 18, 2025
Merged

[WebGPU EP] fix for reduce min/max error on MacOS CI #24077

Show file tree
Hide file tree
Changes from 4 commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
71b0c18
bug fix
prathikr Mar 18, 2025
2a1c212
don't support empty set
prathikr Mar 18, 2025
b2cf108
don't support empty set
prathikr Mar 18, 2025
69f5370
rename
prathikr Mar 18, 2025
13de604
rename
prathikr Mar 18, 2025
084a0ff
lint
prathikr Mar 18, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 11 additions & 2 deletions onnxruntime/core/providers/webgpu/reduction/reduction_ops.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,15 @@ namespace webgpu {
(*KernelDefBuilder::Create()).TypeConstraint("T", WebGpuSupportedNumberTypes()), \
ReduceOp);

#define REGISTER_UNARY_ELEMENTWISE_VERSIONED_KERNEL_WITH_AXIS_IN_INPUT(ReduceOp, begin, end) \
ONNX_OPERATOR_VERSIONED_KERNEL_EX( \
Comment thread
prathikr marked this conversation as resolved.
ReduceOp, \
kOnnxDomain, \
begin, end, \
kWebGpuExecutionProvider, \
(*KernelDefBuilder::Create()).TypeConstraint("T", WebGpuSupportedNumberTypes()).InputMemoryType(OrtMemTypeCPUInput, 1), \
ReduceOp);

#define REGISTER_UNARY_ELEMENTWISE_KERNEL(ReduceOp, version) \
ONNX_OPERATOR_KERNEL_EX( \
ReduceOp, \
Expand All @@ -38,14 +47,14 @@ REGISTER_UNARY_ELEMENTWISE_VERSIONED_KERNEL(ReduceMax, 1, 10);
REGISTER_UNARY_ELEMENTWISE_VERSIONED_KERNEL(ReduceMax, 11, 11);
REGISTER_UNARY_ELEMENTWISE_VERSIONED_KERNEL(ReduceMax, 12, 12);
REGISTER_UNARY_ELEMENTWISE_VERSIONED_KERNEL(ReduceMax, 13, 17);
REGISTER_UNARY_ELEMENTWISE_VERSIONED_KERNEL(ReduceMax, 18, 19);
REGISTER_UNARY_ELEMENTWISE_VERSIONED_KERNEL_WITH_AXIS_IN_INPUT(ReduceMax, 18, 19);
REGISTER_UNARY_ELEMENTWISE_KERNEL(ReduceMax, 20);

REGISTER_UNARY_ELEMENTWISE_VERSIONED_KERNEL(ReduceMin, 1, 10);
REGISTER_UNARY_ELEMENTWISE_VERSIONED_KERNEL(ReduceMin, 11, 11);
REGISTER_UNARY_ELEMENTWISE_VERSIONED_KERNEL(ReduceMin, 12, 12);
REGISTER_UNARY_ELEMENTWISE_VERSIONED_KERNEL(ReduceMin, 13, 17);
REGISTER_UNARY_ELEMENTWISE_VERSIONED_KERNEL(ReduceMin, 18, 19);
REGISTER_UNARY_ELEMENTWISE_VERSIONED_KERNEL_WITH_AXIS_IN_INPUT(ReduceMin, 18, 19);
REGISTER_UNARY_ELEMENTWISE_KERNEL(ReduceMin, 20);

REGISTER_UNARY_ELEMENTWISE_VERSIONED_KERNEL(ReduceSum, 1, 10);
Expand Down
4 changes: 3 additions & 1 deletion onnxruntime/test/testdata/onnx_backend_test_series_filters.jsonc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -694,7 +694,9 @@
"^test_gelu_tanh_2_expanded_cpu",
"^test_dynamicquantizelinear_expanded_cpu",
"^test_center_crop_pad_crop_negative_axes_hwc*", // failed due to new types or shape infer with negative axis for CenterCropPad.
"^test_center_crop_pad_crop_negative_axes_hwc_expanded*" // failed due to new types or shape infer with negative axis for CenterCropPad.
"^test_center_crop_pad_crop_negative_axes_hwc_expanded*", // failed due to new types or shape infer with negative axis for CenterCropPad.
"^test_reduce_max_empty_set",
"^test_reduce_min_empty_set"
],
"current_failing_tests_pure_DML": [
"^test_negative_log_likelihood_loss_input_shape_is_NCd1d2d3_none_no_weight_negative_ignore_index_cpu",
Expand Down