aboutsummaryrefslogtreecommitdiff
path: root/arm_compute/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h
diff options
context:
space:
mode:
authorGeorgios Pinitas <georgios.pinitas@arm.com>2018-09-21 16:33:15 +0100
committerAnthony Barbier <anthony.barbier@arm.com>2018-11-02 16:55:19 +0000
commit932491f44d51940d82514417a82e43cb11b06bd4 (patch)
treecbd5a422dcc0650c0163c7db93792c42e40e3886 /arm_compute/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h
parenteb027e933758b1e749f0f6bd2817ee8979ef903c (diff)
downloadComputeLibrary-932491f44d51940d82514417a82e43cb11b06bd4.tar.gz
COMPMID-1519: Add support for 3D input/output in CLGEMMLowpOutputStage
Change-Id: I637add70310d2da4d82b236a6352af9d33be17a1 Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/149706 Reviewed-by: Isabella Gottardi <isabella.gottardi@arm.com> Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com> Tested-by: bsgcomp <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h')
-rw-r--r--arm_compute/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h25
1 files changed, 12 insertions, 13 deletions
diff --git a/arm_compute/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h b/arm_compute/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h
index 6ebb515af7..8412fa229f 100644
--- a/arm_compute/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h
+++ b/arm_compute/core/NEON/kernels/NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel.h
@@ -72,24 +72,24 @@ public:
* @param[in] min (Optional) Min value used to saturate down the output result before converting back to QASYMM8
* @param[in] max (Optional) Max value used to saturate up the output result before converting back to QASYMM8,
* Along with @p min, this value can be used to implement "rectified linear unit" activation functions
- * @param[in] gemm_3d_depth (Optional) Depth of GEMM 3D (Defaults to 1)
+ * @param[in] output_3d_depth (Optional) Depth of output in 3D (Defaults to 1)
*/
void configure(const ITensor *input, const ITensor *bias, ITensor *output, int result_fixedpoint_multiplier, int result_shift, int result_offset_after_shift,
- int min = 0, int max = 0, unsigned int gemm_3d_depth = 1);
+ int min = 0, int max = 0, unsigned int output_3d_depth = 1);
/** Static function to check if given info will lead to a valid configuration of @ref NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPointKernel
*
- * @param[in] input Input tensor. Data type supported: S32
- * @param[in] bias Biases tensor. Only shared biases supported and it can be a nullptr if the biases addition is not required.
- * Biases are 1D tensor with dimensions [OFM]. Data type supported: Same as @p input.
- * @param[in] output Output tensor. Data type supported: Data type supported: QASYMM8
- * @param[in] min (Optional) Min value used to saturate down the output result before converting back to QASYMM8
- * @param[in] max (Optional) Max value used to saturate up the output result before converting back to QASYMM8,
- * Along with @p min, this value can be used to implement "rectified linear unit" activation functions
- * @param[in] gemm_3d_depth (Optional) Depth of GEMM 3D (Defaults to 1)
+ * @param[in] input Input tensor. Data type supported: S32
+ * @param[in] bias Biases tensor. Only shared biases supported and it can be a nullptr if the biases addition is not required.
+ * Biases are 1D tensor with dimensions [OFM]. Data type supported: Same as @p input.
+ * @param[in] output Output tensor. Data type supported: Data type supported: QASYMM8
+ * @param[in] min (Optional) Min value used to saturate down the output result before converting back to QASYMM8
+ * @param[in] max (Optional) Max value used to saturate up the output result before converting back to QASYMM8,
+ * Along with @p min, this value can be used to implement "rectified linear unit" activation functions
+ * @param[in] output_3d_depth (Optional) Depth of output in 3D (Defaults to 1)
*
* @return a status
*/
- static Status validate(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, int min = 0, int max = 0, unsigned int gemm_3d_depth = 1);
+ static Status validate(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, int min = 0, int max = 0, unsigned int output_3d_depth = 1);
// Inherited methods overridden:
void run(const Window &window, const ThreadInfo &info) override;
@@ -117,8 +117,7 @@ private:
int _result_offset_after_shift;
int _min;
int _max;
- unsigned int _gemm_3d_depth;
+ unsigned int _output_3d_depth;
};
} // namespace arm_compute
-
#endif /* __ARM_COMPUTE_NEGEMMLOWPQUANTIZEDOWNINT32TOUINT8SCALEBYFIXEDPOINTKERNEL_H__ */