From df24618b53cffed1c574e11e9fd4ba7740f8c009 Mon Sep 17 00:00:00 2001 From: Pablo Tello Date: Mon, 3 Jul 2017 16:25:09 +0100 Subject: COMPMID-421: Added FP16 suppot to NENormalizationLayer and NEPixelWiseMultiplication. Change-Id: If174f8071502fc5cc94b27cd44a9b1d5e451a9e2 Reviewed-on: http://mpd-gerrit.cambridge.arm.com/79553 Tested-by: Kaizen Reviewed-by: Georgios Pinitas --- arm_compute/core/NEON/kernels/NENormalizationLayerKernel.h | 4 ++-- arm_compute/core/NEON/kernels/NEPixelWiseMultiplicationKernel.h | 6 +++--- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'arm_compute/core/NEON/kernels') diff --git a/arm_compute/core/NEON/kernels/NENormalizationLayerKernel.h b/arm_compute/core/NEON/kernels/NENormalizationLayerKernel.h index d4e36d5ff1..b1bc594e4c 100644 --- a/arm_compute/core/NEON/kernels/NENormalizationLayerKernel.h +++ b/arm_compute/core/NEON/kernels/NENormalizationLayerKernel.h @@ -73,8 +73,8 @@ private: * * @param[in] window Region on which to execute the kernel. */ - template - void normalize(const Window &window); + template + void normalize_float(const Window &window); /** Function to perform normalization for fixed-point values depending on * the given template dimension. The second template parameter specifies diff --git a/arm_compute/core/NEON/kernels/NEPixelWiseMultiplicationKernel.h b/arm_compute/core/NEON/kernels/NEPixelWiseMultiplicationKernel.h index 7e402cd220..433a20e48e 100644 --- a/arm_compute/core/NEON/kernels/NEPixelWiseMultiplicationKernel.h +++ b/arm_compute/core/NEON/kernels/NEPixelWiseMultiplicationKernel.h @@ -52,9 +52,9 @@ public: * @note For @p scale equal to 1/255 only round to nearest even (implemented as round half up) is supported. * For all other scale values only round to zero (implemented as round towards minus infinity) is supported. * - * @param[in] input1 An input tensor. Data types supported: U8/QS8/S16/F32. - * @param[in] input2 An input tensor. Data types supported: U8/QS8/S16/F32. - * @param[out] output The output tensor. Data types supported: U8 (Only if both inputs are U8) /S16/F32. + * @param[in] input1 An input tensor. Data types supported: U8/QS8/S16/F16/F32. + * @param[in] input2 An input tensor. Data types supported: U8/QS8/S16/F16/F32. + * @param[out] output The output tensor. Data types supported: U8 (Only if both inputs are U8) /S16/F16/F32. * @param[in] scale Scale to apply after multiplication. * 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. -- cgit v1.2.1