COMPMID-1226 Extend CLMeanStdDev to support FP32 / FP16
- Extend support for FP16 in CLReduction.
- For F16/F32 MeanStdDev we perform one reduction operation for mean
and one for stddev and we calculate the final result in the host CPU.
Change-Id: Iad2099f26c0ba7969737d22f00c6c275634d875c
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/135870
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
diff --git a/arm_compute/core/CL/kernels/CLMeanStdDevKernel.h b/arm_compute/core/CL/kernels/CLMeanStdDevKernel.h
index a6898fd..46e266e 100644
--- a/arm_compute/core/CL/kernels/CLMeanStdDevKernel.h
+++ b/arm_compute/core/CL/kernels/CLMeanStdDevKernel.h
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2016, 2017 ARM Limited.
+ * Copyright (c) 2016-2018 ARM Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -59,6 +59,17 @@
* @param[out] global_sum_squared (Optional if stddev is not set, required if stddev is set) Keeps global sum of squared pixel values (Buffer size: 1 cl_ulong).
*/
void configure(const ICLImage *input, float *mean, cl::Buffer *global_sum, float *stddev = nullptr, cl::Buffer *global_sum_squared = nullptr);
+ /** Static function to check if given info will lead to a valid configuration of @ref CLMeanStdDevKernel.
+ *
+ * @param[in] input Input image info. Data types supported: U8.
+ * @param[in] mean Input average pixel value.
+ * @param[in] global_sum Keeps global sum of pixel values.
+ * @param[in] stddev (Optional) Output standard deviation of pixel values.
+ * @param[in] global_sum_squared (Optional if stddev is not set, required if stddev is set) Keeps global sum of squared pixel values.
+ *
+ * @return a status
+ */
+ static Status validate(const ITensorInfo *input, float *mean, cl::Buffer *global_sum, float *stddev = nullptr, cl::Buffer *global_sum_squared = nullptr);
// Inherited methods overridden:
void run(const Window &window, cl::CommandQueue &queue) override;