diff options
| author | Manuel Bottini <manuel.bottini@arm.com> | 2019-02-25 13:50:11 +0000 |
|---|---|---|
| committer | Manuel Bottini <manuel.bottini@arm.com> | 2019-03-05 09:46:16 +0000 |
| commit | 6a2b6e835459ee91dbdf86be8dfdec0bc2421a84 (patch) | |
| tree | f9324f478f293a5d76a9c8bcc23d10814f406809 /arm_compute/runtime/NEON/functions/NEArithmeticSubtraction.h | |
| parent | fc1da1391679c51209c611e95d60569ce4da15cb (diff) | |
| download | ComputeLibrary-6a2b6e835459ee91dbdf86be8dfdec0bc2421a84.tar.gz | |
COMPMID-2010: Add support for QASYMM8 in NEArithmeticSubtractionKernel
Change-Id: Ica65d5a13f5670d525bbb961a870b23a21d093d9
Signed-off-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/807
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Pablo Marquez <pablo.tello@arm.com>
Diffstat (limited to 'arm_compute/runtime/NEON/functions/NEArithmeticSubtraction.h')
| -rw-r--r-- | arm_compute/runtime/NEON/functions/NEArithmeticSubtraction.h | 20 |
1 files changed, 10 insertions, 10 deletions
diff --git a/arm_compute/runtime/NEON/functions/NEArithmeticSubtraction.h b/arm_compute/runtime/NEON/functions/NEArithmeticSubtraction.h index 541756cd2c..e6ff4458f0 100644 --- a/arm_compute/runtime/NEON/functions/NEArithmeticSubtraction.h +++ b/arm_compute/runtime/NEON/functions/NEArithmeticSubtraction.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2016-2018 ARM Limited. + * Copyright (c) 2016-2019 ARM Limited. * * SPDX-License-Identifier: MIT * @@ -33,7 +33,7 @@ class ITensor; /** Basic function to run @ref NEArithmeticSubtractionKernel * - * @note The tensor data type for the inputs must be U8/S16/F16/F32. + * @note The tensor data type for the inputs must be U8/QASYMM8/S16/F16/F32. * @note The function performs an arithmetic subtraction between two tensors. * * This function calls the following kernels: @@ -45,18 +45,18 @@ class NEArithmeticSubtraction : public INESimpleFunction public: /** Initialise the kernel's inputs, output and conversion policy. * - * @param[in] input1 First tensor input. Data types supported: U8/S16/F16/F32 - * @param[in] input2 Second tensor input. Data types supported: U8/S16/F16/F32 - * @param[out] output Output tensor. Data types supported: U8/S16/F16/F32 - * @param[in] policy Policy to use to handle overflow. + * @param[in] input1 First tensor input. Data types supported: U8/QASYMM8/S16/F16/F32 + * @param[in] input2 Second tensor input. Data types supported: U8/QASYMM8/S16/F16/F32 + * @param[out] output Output tensor. Data types supported: U8/QASYMM8/S16/F16/F32 + * @param[in] policy Policy to use to handle overflow. Convert policy cannot be WRAP if datatype is QASYMM8. */ void configure(ITensor *input1, ITensor *input2, ITensor *output, ConvertPolicy policy); /** Static function to check if given info will lead to a valid configuration of @ref NEArithmeticSubtraction * - * @param[in] input1 First tensor input. Data types supported: U8/S16/F16/F32 - * @param[in] input2 Second tensor input. Data types supported: U8/S16/F16/F32 - * @param[in] output Output tensor. Data types supported: U8/S16/F16/F32 - * @param[in] policy Policy to use to handle overflow. + * @param[in] input1 First tensor input. Data types supported: U8/QASYMM8/S16/F16/F32 + * @param[in] input2 Second tensor input. Data types supported: U8/QASYMM8/S16/F16/F32 + * @param[in] output Output tensor. Data types supported: U8/QASYMM8/S16/F16/F32 + * @param[in] policy Policy to use to handle overflow. Convert policy cannot be WRAP if datatype is QASYMM8 * * @return a status */ |