Skip to content

[webgpu] Get data from bias with GetByOffset() in gemm_utils.cc #26679

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
+3 −9
Open

[webgpu] Get data from bias with GetByOffset() in gemm_utils.cc #26679

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
5 changes: 3 additions & 2 deletions onnxruntime/core/providers/webgpu/math/gemm_utils.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,7 +34,7 @@ void HandleMaybeHaveBiasForGEMM(ShaderHelper& shader,
} else if (c_is_scalar) {
shader.AdditionalImplementation() << "output_value_t(C[0]);\n";
} else {
shader.AdditionalImplementation() << "output_value_t(C[row]);\n";
shader.AdditionalImplementation() << "output_value_t(" << C.GetByOffset("row") << ");\n";
}
}
shader.AdditionalImplementation() << output.SetByIndices("coords", "value") << "\n";
Expand All @@ -47,7 +47,8 @@ void HandleMaybeBiasForMatMul(ShaderHelper& shader,
bool is_channels_last) {
shader.AdditionalImplementation() << " let coords = vec3(u32(batch), u32(row), u32(colIn));\n";
if (has_bias) {
shader.AdditionalImplementation() << " value = value + output_value_t(" << (is_channels_last ? "bias[colIn]" : "bias[row]") << ");\n";
const ShaderVariableHelper& bias = shader.AddInput("bias", ShaderUsage::UseUniform);
shader.AdditionalImplementation() << " value = value + output_value_t(" << (is_channels_last ? bias.GetByOffset("colIn") : bias.GetByOffset("row")) << ");\n";
}
shader.AdditionalImplementation() << " " << activation_snippet << "\n"
<< output.SetByIndices("coords", "value") << "\n";
Expand Down
7 changes: 0 additions & 7 deletions onnxruntime/core/providers/webgpu/math/matmul_packed.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -26,9 +26,6 @@ Status MatMulProgram::GenerateShaderCode(ShaderHelper& shader) const {

const auto& batch_dims = shader.AddIndices("batch_dims", ShaderUsage::UseUniform | ShaderUsage::UseIndicesTypeAlias);

if (has_bias_) {
shader.AddInput("bias", ShaderUsage::UseUniform);
}
std::string apply_activation = GetActivationSnippet(activation_, "output_value_t", "output_element_t");
ProgramVariableDataType output_var_type = this->Outputs()[0].var_type;
// declare the read and write functions
Expand All @@ -54,10 +51,6 @@ bool MatMulProgram::NeedSplitK() const {
Status MatMulFillBiasOrZeroBeforeSplitKProgram::GenerateShaderCode(ShaderHelper& shader) const {
const auto& output = shader.AddOutput("output", ShaderUsage::UseUniform | ShaderUsage::UseIndicesTypeAlias | ShaderUsage::UseValueTypeAlias | ShaderUsage::UseElementTypeAlias);

if (has_bias_) {
shader.AddInput("bias", ShaderUsage::UseUniform);
}

// Handle bias with `MatMulWriteFnSource()`.
// Here `use_split_k` is false because we just initialize `output` with bias.
// `use_split_k` is true only when we do the actual MatMul with Split-K.
Expand Down