diff options
author | Michele Di Giorgio <michele.digiorgio@arm.com> | 2020-06-04 15:05:38 +0100 |
---|---|---|
committer | Michele Di Giorgio <michele.digiorgio@arm.com> | 2020-06-15 13:59:04 +0000 |
commit | 4a61653202afb018f4f259d3c144a735d73f0a20 (patch) | |
tree | 082fd42e91cc0914dcacc0746bbe3e117d74210c /arm_compute/runtime/NEON/functions/NEArithmeticAddition.h | |
parent | ccd94966cc58ef5148577e71ba1a4ff5aae1f3bb (diff) | |
download | ComputeLibrary-4a61653202afb018f4f259d3c144a735d73f0a20.tar.gz |
COMPMID-3480: Perform in-place computations in NEArithmeticAdditionKernel
Change-Id: I0089657dd95d7c7b8592984def8e8de1d7e6d085
Signed-off-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3308
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/runtime/NEON/functions/NEArithmeticAddition.h')
-rw-r--r-- | arm_compute/runtime/NEON/functions/NEArithmeticAddition.h | 16 |
1 files changed, 8 insertions, 8 deletions
diff --git a/arm_compute/runtime/NEON/functions/NEArithmeticAddition.h b/arm_compute/runtime/NEON/functions/NEArithmeticAddition.h index bf8f2cc14b..5b430ce397 100644 --- a/arm_compute/runtime/NEON/functions/NEArithmeticAddition.h +++ b/arm_compute/runtime/NEON/functions/NEArithmeticAddition.h @@ -25,14 +25,14 @@ #define ARM_COMPUTE_NEARITHMETICADDITION_H #include "arm_compute/core/Types.h" -#include "arm_compute/runtime/NEON/INESimpleFunction.h" +#include "arm_compute/runtime/NEON/INESimpleFunctionNoBorder.h" namespace arm_compute { class ITensor; /** Basic function to run @ref NEArithmeticAdditionKernel */ -class NEArithmeticAddition : public INESimpleFunction +class NEArithmeticAddition : public INESimpleFunctionNoBorder { public: /** Initialise the kernel's inputs, output and conversion policy. @@ -51,18 +51,18 @@ public: * - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED * - (QSYMM16,QSYMM16) -> QSYMM16 * - * @param[in] input1 First tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32 - * @param[in] input2 Second tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32 - * @param[out] output Output tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32 - * @param[in] policy Policy to use to handle overflow. - * @param[in] act_info (Optional) Activation layer information in case of a fused activation. Currently not supported. + * @param[in, out] input1 First tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32 + * @param[in] input2 Second tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32 + * @param[out] output (Optional) Output tensor. Can be nullptr. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32 + * @param[in] policy Policy to use to handle overflow. + * @param[in] act_info (Optional) Activation layer information in case of a fused activation. Currently not supported. */ void configure(ITensor *input1, ITensor *input2, ITensor *output, ConvertPolicy policy, const ActivationLayerInfo &act_info = ActivationLayerInfo()); /** Static function to check if given info will lead to a valid configuration of @ref NEArithmeticAddition * * @param[in] input1 First tensor input info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32 * @param[in] input2 Second tensor input info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32 - * @param[in] output Output tensor info. Data types supported: U8/SQASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32 + * @param[in] output (Optional) Output tensor info. Can be nullptr. Data types supported: U8/SQASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/S32/F32 * @param[in] policy Policy to use to handle overflow * @param[in] act_info (Optional) Activation layer information in case of a fused activation. Currently not supported. * |