diff options
| author | Michalis Spyrou <michalis.spyrou@arm.com> | 2019-12-03 15:11:09 +0000 |
|---|---|---|
| committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2019-12-04 11:15:51 +0000 |
| commit | bc4d7c2d0c3484152256d5c9dbb61e6a149bdc20 (patch) | |
| tree | 902210cf313111112b43f35c290e5a4def599001 /arm_compute | |
| parent | 1f332d4a41393ed30a4e9df841eb4b545fa87486 (diff) | |
| download | ComputeLibrary-bc4d7c2d0c3484152256d5c9dbb61e6a149bdc20.tar.gz | |
COMPMID-2797 Add support for QASYMM8_SIGNED in NEArithmeticAddition
Change-Id: Ie1abf7839d40ffcdc9748c5a3baee7c00cabad21
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2413
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute')
| -rw-r--r-- | arm_compute/core/NEON/kernels/NEArithmeticAdditionKernel.h | 13 | ||||
| -rw-r--r-- | arm_compute/runtime/NEON/functions/NEArithmeticAddition.h | 12 |
2 files changed, 13 insertions, 12 deletions
diff --git a/arm_compute/core/NEON/kernels/NEArithmeticAdditionKernel.h b/arm_compute/core/NEON/kernels/NEArithmeticAdditionKernel.h index 958c02d516..716ffcf373 100644 --- a/arm_compute/core/NEON/kernels/NEArithmeticAdditionKernel.h +++ b/arm_compute/core/NEON/kernels/NEArithmeticAdditionKernel.h @@ -64,19 +64,20 @@ public: * - (F16,F16) -> F16 * - (F32,F32) -> F32 * - (QASYMM8,QASYMM8) -> QASYMM8 + * - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED * - (QSYMM16,QSYMM16) -> QSYMM16 * - * @param[in] input1 An input tensor. Data types supported: U8/QASYMM8/S16/QSYMM16/F16/F32 - * @param[in] input2 An input tensor. Data types supported: U8/QASYMM8/S16/QSYMM16/F16/F32 - * @param[out] output The output tensor. Data types supported: U8/QASYMM8/S16/QSYMM16/F16/F32. + * @param[in] input1 An input tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32 + * @param[in] input2 An input tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32 + * @param[out] output The output tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32. * @param[in] policy Overflow policy. */ void configure(const ITensor *input1, const ITensor *input2, ITensor *output, ConvertPolicy policy); /** Static function to check if given info will lead to a valid configuration of @ref NEArithmeticAdditionKernel * - * @param[in] input1 An input tensor. Data types supported: U8/QASYMM8/S16/QSYMM16/F16/F32 - * @param[in] input2 An input tensor. Data types supported: U8/QASYMM8/S16/QSYMM16/F16/F32 - * @param[in] output The output tensor. Data types supported: U8/QASYMM8/S16/QSYMM16/F16/F32. + * @param[in] input1 An input tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32 + * @param[in] input2 An input tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32 + * @param[in] output The output tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32. * @param[in] policy Overflow policy. * * @return a status diff --git a/arm_compute/runtime/NEON/functions/NEArithmeticAddition.h b/arm_compute/runtime/NEON/functions/NEArithmeticAddition.h index b9312441f0..6ec135f0e5 100644 --- a/arm_compute/runtime/NEON/functions/NEArithmeticAddition.h +++ b/arm_compute/runtime/NEON/functions/NEArithmeticAddition.h @@ -37,17 +37,17 @@ class NEArithmeticAddition : public INESimpleFunction public: /** Initialise the kernel's inputs, output and conversion policy. * - * @param[in] input1 First tensor input. Data types supported: U8/QASYMM8/S16/QSYMM16/F16/F32 - * @param[in] input2 Second tensor input. Data types supported: U8/QASYMM8/S16/QSYMM16/F16/F32 - * @param[out] output Output tensor. Data types supported: U8/QASYMM8/S16/QSYMM16/F16/F32 + * @param[in] input1 First tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32 + * @param[in] input2 Second tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32 + * @param[out] output Output tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32 * @param[in] policy Policy to use to handle overflow. */ 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 NEArithmeticAddition * - * @param[in] input1 First tensor input. Data types supported: U8/QASYMM8/S16/QSYMM16/F16/F32 - * @param[in] input2 Second tensor input. Data types supported: U8/QASYMM8/S16/QSYMM16/F16/F32 - * @param[in] output Output tensor. Data types supported: U8/SQASYMM8/S16/QSYMM16/F16/F32 + * @param[in] input1 First tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32 + * @param[in] input2 Second tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32 + * @param[in] output Output tensor. Data types supported: U8/SQASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32 * @param[in] policy Policy to use to handle overflow. * * @return a status |