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>

1 files changed, 14 insertions, 11 deletions

diff --git a/arm_compute/runtime/CL/functions/CLGEMMLowpOutputStage.h b/arm_compute/runtime/CL/functions/CLGEMMLowpOutputStage.h
index 7446ff4b3f..dca00f027e 100644
--- a/arm_compute/runtime/CL/functions/CLGEMMLowpOutputStage.h
+++ b/arm_compute/runtime/CL/functions/CLGEMMLowpOutputStage.h
@@ -1,5 +1,5 @@
 /*
- * Copyright (c) 2017 ARM Limited.
+ * Copyright (c) 2017-2018 ARM Limited.
  *
  * SPDX-License-Identifier: MIT
  *
@@ -131,21 +131,24 @@ 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]  output_3d_depth              (Optional) Depth of output in 3D (Defaults to 1)
      */
-    void configure(const ICLTensor *input, const ICLTensor *bias, ICLTensor *output, int result_fixedpoint_multiplier, int result_shift, int result_offset_after_shift, int min = 0, int max = 0);
+    void configure(const ICLTensor *input, const ICLTensor *bias, ICLTensor *output, int result_fixedpoint_multiplier, int result_shift, int result_offset_after_shift,
+                   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 CLGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPoint
      *
-     * @param[in] input  Input tensor. It is the output of @ref CLGEMMLowpMatrixMultiplyCore function. Data type supported: S32
-     * @param[in] bias   Biases tensor. Only shared biases supported and it can be a nullptr if the addition of biases 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] input           Input tensor. It is the output of @ref CLGEMMLowpMatrixMultiplyCore function. Data type supported: S32
+     * @param[in] bias            Biases tensor. Only shared biases supported and it can be a nullptr if the addition of biases 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);
+    static Status validate(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, int min = 0, int max = 0, unsigned int output_3d_depth = 1);
 };
-}
+} // namespace arm_compute
 #endif /*__ARM_COMPUTE_CLGEMMLOWPOUTPUTSTAGE_H__ */
\ No newline at end of file