diff options
| author | morgolock <pablo.tello@arm.com> | 2020-01-13 11:53:20 +0000 |
|---|---|---|
| committer | Pablo Marquez <pablo.tello@arm.com> | 2020-01-14 11:42:00 +0000 |
| commit | 6427c8233661f81053d1ad486b5914c612cef3d6 (patch) | |
| tree | 283fd7a4bf331d3a687aba33e1705f92047c324d /arm_compute | |
| parent | 9c700378f2227cb9d51455ed4a5086daaac5532a (diff) | |
| download | ComputeLibrary-6427c8233661f81053d1ad486b5914c612cef3d6.tar.gz | |
COMPMID-2994: Add support QASYMM8_SIGNED in NEElementwiseSquareDiff
Updated interface documention and added precommit tests.
Change-Id: I6d4fe250eb72d3daff977e5a98c1086692e3654a
Signed-off-by: morgolock <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2580
Reviewed-by: Georgios Pinitas <georgios.pinitas@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/runtime/NEON/functions/NEElementwiseOperations.h | 12 |
1 files changed, 6 insertions, 6 deletions
diff --git a/arm_compute/runtime/NEON/functions/NEElementwiseOperations.h b/arm_compute/runtime/NEON/functions/NEElementwiseOperations.h index 9499867f81..eec9bb9fa9 100644 --- a/arm_compute/runtime/NEON/functions/NEElementwiseOperations.h +++ b/arm_compute/runtime/NEON/functions/NEElementwiseOperations.h @@ -33,7 +33,7 @@ class ITensor; /** Basic function to run @ref NEArithmeticOperationKernel for max * - * @note The tensor data type for the inputs must be QASYMM8/S16/F16/S32/F32. + * @note The tensor data type for the inputs must be QASYMM8/QASYMM8_SIGNED/S16/F16/S32/F32. * @note The function performs a max operation between two tensors. */ class NEElementwiseMax : public INESimpleFunction @@ -59,8 +59,8 @@ public: /** Basic function to run @ref NEArithmeticOperationKernel for min * - * @note The tensor data type for the inputs must be QASYMM8/S16/F16/S32/F32. - * @note The function performs a max operation between two tensors. + * @note The tensor data type for the inputs must be QASYMM8/QASYMM8_SIGNED/S16/F16/S32/F32. + * @note The function performs a min operation between two tensors. */ class NEElementwiseMin : public INESimpleFunction { @@ -85,7 +85,7 @@ public: /** Basic function to run @ref NEArithmeticOperationKernel for squared difference * - * @note The tensor data type for the inputs must be QASYMM8/S16/F16/S32/F32. + * @note The tensor data type for the inputs must be QASYMM8/QASYMM8_SIGNED/S16/F16/S32/F32. * @note The function performs a squared different operation between two tensors (i.e., out[i] = (in1[i] - in2[i])^2 */ class NEElementwiseSquaredDiff : public INESimpleFunction @@ -93,14 +93,14 @@ class NEElementwiseSquaredDiff : public INESimpleFunction public: /** Initialise the kernel's inputs, output and conversion policy. * - * @param[in, out] input1 First tensor input. Data types supported: QASYMM8/S16/F16/S32/F32. + * @param[in, out] input1 First tensor input. Data types supported: QASYMM8/QASYMM8_SIGNED/S16/F16/S32/F32. * @param[in, out] input2 Second tensor input. Data types supported: Same as @p input1. * @param[out] output Output tensor. Data types supported: Same as @p input1. */ void configure(ITensor *input1, ITensor *input2, ITensor *output); /** Static function to check if given info will lead to a valid configuration of @ref NEArithmeticOperationKernel for squared difference * - * @param[in] input1 First tensor input info. Data types supported: QASYMM8/S16/F16/S32/F32. + * @param[in] input1 First tensor input info. Data types supported: QASYMM8/QASYMM8_SIGNED/S16/F16/S32/F32. * @param[in] input2 Second tensor input info. Data types supported: Same as @p input1. * @param[in] output Output tensor info. Data types supported: Same as @p input1. * |