COMPMID-3101 Fuse activation with floating point elementwise operation layers in CL
Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Change-Id: I1693f8664ba7c0dc8c076bbe7365cef1e667bd25
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/2718
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
diff --git a/arm_compute/core/CL/kernels/CLPixelWiseMultiplicationKernel.h b/arm_compute/core/CL/kernels/CLPixelWiseMultiplicationKernel.h
index 58471ab..eacdb44 100644
--- a/arm_compute/core/CL/kernels/CLPixelWiseMultiplicationKernel.h
+++ b/arm_compute/core/CL/kernels/CLPixelWiseMultiplicationKernel.h
@@ -55,9 +55,10 @@
* Scale must be positive and its value must be either 1/255 or 1/2^n where n is between 0 and 15.
* @param[in] overflow_policy Overflow policy. Supported overflow policies: Wrap, Saturate
* @param[in] rounding_policy Rounding policy. Supported rounding modes: to zero, to nearest even.
+ * @param[in] act_info (Optional) Activation layer information in case of a fused activation.
*/
void configure(const ICLTensor *input1, const ICLTensor *input2, ICLTensor *output, float scale,
- ConvertPolicy overflow_policy, RoundingPolicy rounding_policy);
+ ConvertPolicy overflow_policy, RoundingPolicy rounding_policy, const ActivationLayerInfo &act_info = ActivationLayerInfo());
/** Static function to check if given info will lead to a valid configuration of @ref CLPixelWiseMultiplicationKernel
*
* @param[in] input1 An input tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
@@ -67,11 +68,12 @@
* Scale must be positive and its value must be either 1/255 or 1/2^n where n is between 0 and 15.
* @param[in] overflow_policy Overflow policy. Supported overflow policies: Wrap, Saturate
* @param[in] rounding_policy Rounding policy. Supported rounding modes: to zero, to nearest even.
+ * @param[in] act_info (Optional) Activation layer information in case of a fused activation.
*
* @return a status
*/
static Status validate(const ITensorInfo *input1, const ITensorInfo *input2, const ITensorInfo *output, float scale,
- ConvertPolicy overflow_policy, RoundingPolicy rounding_policy);
+ ConvertPolicy overflow_policy, RoundingPolicy rounding_policy, const ActivationLayerInfo &act_info = ActivationLayerInfo());
// Inherited methods overridden:
void run(const Window &window, cl::CommandQueue &queue) override;
@@ -99,20 +101,22 @@
CLComplexPixelWiseMultiplicationKernel &operator=(CLComplexPixelWiseMultiplicationKernel &&) = default;
/** Initialise the kernel's input, output and border mode.
*
- * @param[in] input1 An input tensor. Data types supported: F32. Number of channels supported: 2.
- * @param[in] input2 An input tensor. Data types supported: same as @p input1. Number of channels supported: same as @p input1.
- * @param[out] output The output tensor, Data types supported: same as @p input1. Number of channels supported: same as @p input1.
+ * @param[in] input1 An input tensor. Data types supported: F32. Number of channels supported: 2.
+ * @param[in] input2 An input tensor. Data types supported: same as @p input1. Number of channels supported: same as @p input1.
+ * @param[out] output The output tensor, Data types supported: same as @p input1. Number of channels supported: same as @p input1.
+ * @param[in] act_info (Optional) Activation layer information in case of a fused activation.
*/
- void configure(const ICLTensor *input1, const ICLTensor *input2, ICLTensor *output);
+ void configure(const ICLTensor *input1, const ICLTensor *input2, ICLTensor *output, const ActivationLayerInfo &act_info = ActivationLayerInfo());
/** Static function to check if given info will lead to a valid configuration of @ref CLComplexPixelWiseMultiplicationKernel
*
- * @param[in] input1 An input tensor info. Data types supported: F32. Number of channels supported: 2.
- * @param[in] input2 An input tensor info. Data types supported: same as @p input1. Number of channels supported: same as @p input1.
- * @param[in] output The output tensor info. Data types supported: same as @p input1. Number of channels supported: same as @p input1.
+ * @param[in] input1 An input tensor info. Data types supported: F32. Number of channels supported: 2.
+ * @param[in] input2 An input tensor info. Data types supported: same as @p input1. Number of channels supported: same as @p input1.
+ * @param[in] output The output tensor info. Data types supported: same as @p input1. Number of channels supported: same as @p input1.
+ * @param[in] act_info (Optional) Activation layer information in case of a fused activation.
*
* @return a status
*/
- static Status validate(const ITensorInfo *input1, const ITensorInfo *input2, const ITensorInfo *output);
+ static Status validate(const ITensorInfo *input1, const ITensorInfo *input2, const ITensorInfo *output, const ActivationLayerInfo &act_info = ActivationLayerInfo());
// Inherited methods overridden:
void run(const Window &window, cl::CommandQueue &queue) override;