Rework DepthwiseConvolution heuristic on OpenCL
Resolves COMPMID-5632
Change-Id: I2bdbe69a610ca2510fbd74d5d412842679299762
Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8365
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
diff --git a/arm_compute/core/CL/CLHelpers.h b/arm_compute/core/CL/CLHelpers.h
index edbc705..a162b1c 100644
--- a/arm_compute/core/CL/CLHelpers.h
+++ b/arm_compute/core/CL/CLHelpers.h
@@ -242,13 +242,13 @@
*/
void set_wbsm(cl::Kernel &kernel, cl_int wbsm_hint);
-/* Helper function to check if we can export the weights to cl_image
+/* Helper function to check if we can export the tensor to cl_image
*
- * @param[in] tensor Weights tensor
+ * @param[in] input tensor
*
- * @return true if we can export the weights to cl_image
+ * @return true if we can export the tensor to cl_image
*/
-bool export_weights_to_cl_image(const ITensorInfo *tensor);
+bool export_to_cl_image(const ITensorInfo *tensor);
/* Helper function to force unroll with pragma when any of the input values (iterations) are greater than @ref max_manual_loop_unrolling
*
diff --git a/arm_compute/core/KernelDescriptors.h b/arm_compute/core/KernelDescriptors.h
index c45be9c..cacbef2 100644
--- a/arm_compute/core/KernelDescriptors.h
+++ b/arm_compute/core/KernelDescriptors.h
@@ -106,6 +106,7 @@
{
unsigned int n0{ 0 }; /**< Number of columns processed by each thread */
unsigned int m0{ 0 }; /**< Number of rows processed by each thread */
+ bool export_input_to_cl_image{ false }; /**< Export input to cl_image */
bool export_weights_to_cl_image{ false }; /**< Export the weights to cl_image */
};