aboutsummaryrefslogtreecommitdiff
path: root/src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp
diff options
context:
space:
mode:
Diffstat (limited to 'src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp')
-rw-r--r--src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp8
1 files changed, 7 insertions, 1 deletions
diff --git a/src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp b/src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp
index 8e764033e0..9587a042be 100644
--- a/src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp
@@ -307,6 +307,12 @@ CLGEMMMatrixMultiplyKernel::CLGEMMMatrixMultiplyKernel()
void CLGEMMMatrixMultiplyKernel::configure(const ICLTensor *input0, const ICLTensor *input1, const ICLTensor *input2, ICLTensor *output, float alpha, float beta,
bool is_interleaved_transposed, const GEMMReshapeInfo &reshape_info, bool fp_mixed_precision, const ActivationLayerInfo &activation_info)
{
+ configure(CLKernelLibrary::get().get_compile_context(), input0, input1, input2, output, alpha, beta, is_interleaved_transposed, reshape_info, fp_mixed_precision, activation_info);
+}
+
+void CLGEMMMatrixMultiplyKernel::configure(CLCompileContext &compile_context, const ICLTensor *input0, const ICLTensor *input1, const ICLTensor *input2, ICLTensor *output, float alpha, float beta,
+ bool is_interleaved_transposed, const GEMMReshapeInfo &reshape_info, bool fp_mixed_precision, const ActivationLayerInfo &activation_info)
+{
ARM_COMPUTE_ERROR_ON_NULLPTR(input0, input1, output);
// Perform validate step
@@ -430,7 +436,7 @@ void CLGEMMMatrixMultiplyKernel::configure(const ICLTensor *input0, const ICLTen
}
// Create kernel
- _kernel = static_cast<cl::Kernel>(CLKernelLibrary::get().create_kernel(kernel_name, build_opts.options()));
+ _kernel = create_kernel(compile_context, kernel_name, build_opts.options());
// Set config_id for enabling LWS tuning
_config_id = "gemm_";