COMPMID-1446 : Add support for 3D output in NEGEMMLowpOutputStage

Change-Id: I61e7d39d09a9936b1128ec04038fa2d8dfe6a2c8
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/149211
Reviewed-by: Isabella Gottardi <isabella.gottardi@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Tested-by: bsgcomp <bsgcomp@arm.com>

2 files changed, 15 insertions, 13 deletions

diff --git a/arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h b/arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h
index dc00b17efc..ae2563cfc7 100644
--- a/arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h
+++ b/arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h
@@ -188,7 +188,6 @@ private:
     NECol2ImKernel                                      _col2im_kernel;
     NEActivationLayer                                   _activationlayer_function;
     NEArithmeticAdditionKernel                          _add_bias_kernel;
-    NEReshapeLayer                                      _reshape_layer;
 
     const ITensor *_original_weights;
 
@@ -206,5 +205,5 @@ private:
     bool _is_activationlayer_enabled;
     bool _is_prepared;
 };
-}
+} // namespace arm_compute
 #endif /* __ARM_COMPUTE_NECONVOLUTIONGEMMLAYER_H__ */
diff --git a/arm_compute/runtime/NEON/functions/NEGEMMLowpOutputStage.h b/arm_compute/runtime/NEON/functions/NEGEMMLowpOutputStage.h
index 7da0d2359a..d006929996 100644
--- a/arm_compute/runtime/NEON/functions/NEGEMMLowpOutputStage.h
+++ b/arm_compute/runtime/NEON/functions/NEGEMMLowpOutputStage.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]  gemm_3d_depth                (Optional)     Depth of GEMM 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);
+    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);
     /** Static function to check if given info will lead to a valid configuration of @ref NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPoint
      *
-     * @param[in] input  Input tensor. It is the output of @ref NEGEMMLowpMatrixMultiplyCore 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 NEGEMMLowpMatrixMultiplyCore 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] gemm_3d_depth (Optional) Depth of GEMM 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 gemm_3d_depth = 1);
 };
-}
+} // namespace arm_compute
 #endif /*__ARM_COMPUTE_NEGEMMLOWPOUTPUTSTAGE_H__ */
\ No newline at end of file