COMPMID-1096 - Add fast_math flag to CLConvolutionLayer

COMPMID-1103 - CLWinogradConvolutionLayer mismatches

Change-Id: Iceaa9482a1790ec39d2720c220261aaea8043978
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/129398
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Giorgio Arena <giorgio.arena@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>

1 files changed, 44 insertions, 37 deletions

diff --git a/arm_compute/runtime/CL/functions/CLConvolutionLayer.h b/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
index a1cd15515f..5c05334a56 100644
--- a/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
+++ b/arm_compute/runtime/CL/functions/CLConvolutionLayer.h
@@ -37,6 +37,7 @@ namespace arm_compute
 /** Basic function to compute the convolution layer. This function calls the following OpenCL kernels/functions:
  *
  * -# @ref CLGEMMConvolutionLayer
+ * -# @ref CLWinogradConvolutionLayer
  * -# @ref CLDirectConvolutionLayer
  */
 class CLConvolutionLayer : public IFunction
@@ -46,57 +47,63 @@ public:
     CLConvolutionLayer(std::shared_ptr<IMemoryManager> memory_manager = nullptr);
     /** Set the input and output tensors.
      *
-     * @param[in]  input        Source tensor. 3 lower dimensions represent a single input [width, height, IFM],
-     *                          while every optional dimension from 4 and above represent a batch of inputs.
-     *                          Data types supported: QS8/QASYMM8/QS16/F16/F32.
-     * @param[in]  weights      Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported: Same as @p input.
-     * @param[in]  biases       Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM].
-     *                          Data type supported: Should match @p input data type, except for input of QASYMM8 type where biases should be of S32 type.
-     * @param[out] output       Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
-     *                          Data types supported: Same as @p input.
-     * @param[in]  conv_info    Contains padding and stride information described in @ref PadStrideInfo.
-     * @param[in]  weights_info Specifies if the weights tensor has been reshaped with CLWeightsReshapeKernel. Data type supported: Same as @p input.
-     * @param[in]  dilation     (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
-     * @param[in]  act_info     (Optional) Activation layer information in case of a fused activation.
+     * @param[in]  input            Source tensor. 3 lower dimensions represent a single input [width, height, IFM],
+     *                              while every optional dimension from 4 and above represent a batch of inputs.
+     *                              Data types supported: QS8/QASYMM8/QS16/F16/F32.
+     * @param[in]  weights          Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported: Same as @p input.
+     * @param[in]  biases           Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM].
+     *                              Data type supported: Should match @p input data type, except for input of QASYMM8 type where biases should be of S32 type.
+     * @param[out] output           Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
+     *                              Data types supported: Same as @p input.
+     * @param[in]  conv_info        Contains padding and stride information described in @ref PadStrideInfo.
+     * @param[in]  weights_info     Specifies if the weights tensor has been reshaped with CLWeightsReshapeKernel. Data type supported: Same as @p input.
+     * @param[in]  dilation         (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
+     * @param[in]  act_info         (Optional) Activation layer information in case of a fused activation.
+     * @param[in]  enable_fast_math (Optional) Enable fast math computation. In case this flag were set, the function could dispatch the fastest implementation
+     *                                available which may introduce a drop of accuracy as well. Default is false
      */
     void configure(ICLTensor *input, const ICLTensor *weights, const ICLTensor *biases, ICLTensor *output, const PadStrideInfo &conv_info, const WeightsInfo &weights_info = WeightsInfo(),
-                   const Size2D &dilation = Size2D(1U, 1U), const ActivationLayerInfo &act_info = ActivationLayerInfo());
+                   const Size2D &dilation = Size2D(1U, 1U), const ActivationLayerInfo &act_info = ActivationLayerInfo(), bool enable_fast_math = false);
     /** Static function to check if given info will lead to a valid configuration of @ref CLConvolutionLayer
      *
-     * @param[in] input        Source tensor. 3 lower dimensions represent a single input [width, height, IFM],
-     *                         while every optional dimension from 4 and above represent a batch of inputs.
-     *                         Data types supported: QS8/QASYMM8/QS16/F16/F32.
-     * @param[in] weights      Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported:Same as @p input.
-     * @param[in] biases       Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM]. Data type supported:Same as @p input.
-     * @param[in] output       Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
-     *                         Data types supported: Same as @p input.
-     * @param[in] conv_info    Contains padding and stride information described in @ref PadStrideInfo.
-     * @param[in] weights_info Specifies if the weights tensor has been reshaped with CLWeightsReshapeKernel. Data type supported: Same as @p input.
-     * @param[in] dilation     (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
-     * @param[in] act_info     (Optional) Activation layer information in case of a fused activation.
+     * @param[in] input            Source tensor. 3 lower dimensions represent a single input [width, height, IFM],
+     *                             while every optional dimension from 4 and above represent a batch of inputs.
+     *                             Data types supported: QS8/QASYMM8/QS16/F16/F32.
+     * @param[in] weights          Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported:Same as @p input.
+     * @param[in] biases           Biases tensor. Shared biases supported. Biases are 1D tensor with dimensions [OFM]. Data type supported:Same as @p input.
+     * @param[in] output           Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
+     *                             Data types supported: Same as @p input.
+     * @param[in] conv_info        Contains padding and stride information described in @ref PadStrideInfo.
+     * @param[in] weights_info     Specifies if the weights tensor has been reshaped with CLWeightsReshapeKernel. Data type supported: Same as @p input.
+     * @param[in] dilation         (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
+     * @param[in] act_info         (Optional) Activation layer information in case of a fused activation.
+     * @param[in] enable_fast_math (Optional) Enable fast math computation. In case this flag were set, the function could dispatch the fastest implementation
+     *                             available which may introduce a drop of accuracy as well. Default is false
      *
      * @return a status
      */
     static Status validate(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *output, const PadStrideInfo &conv_info,
-                           const WeightsInfo &weights_info = WeightsInfo(), const Size2D &dilation = Size2D(1U, 1U), const ActivationLayerInfo &act_info = ActivationLayerInfo());
+                           const WeightsInfo &weights_info = WeightsInfo(), const Size2D &dilation = Size2D(1U, 1U), const ActivationLayerInfo &act_info = ActivationLayerInfo(), bool enable_fast_math = false);
     /** Static function to check if given info will return the convolution called by @ref CLConvolutionLayer
      *
-     * @param[in] input        Source tensor. 3 lower dimensions represent a single input [width, height, IFM],
-     *                         while every optional dimension from 4 and above represent a batch of inputs.
-     *                         Data types supported: QS8/QASYMM8/QS16/F16/F32.
-     * @param[in] weights      Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported:Same as @p input.
-     * @param[in] output       Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
-     *                         Data types supported: Same as @p input.
-     * @param[in] conv_info    Contains padding and stride information described in @ref PadStrideInfo.
-     * @param[in] weights_info Specifies if the weights tensor has been reshaped with CLWeightsReshapeKernel. Data type supported: Same as @p input.
-     * @param[in] act_info     (Optional) Activation layer information in case of a fused activation.
-     * @param[in] gpu_target   Specifies the @p GPUTarget.
-     * @param[in] dilation     (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
+     * @param[in] input            Source tensor. 3 lower dimensions represent a single input [width, height, IFM],
+     *                             while every optional dimension from 4 and above represent a batch of inputs.
+     *                             Data types supported: QS8/QASYMM8/QS16/F16/F32.
+     * @param[in] weights          Weights tensor. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported:Same as @p input.
+     * @param[in] output           Destination tensor. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
+     *                             Data types supported: Same as @p input.
+     * @param[in] conv_info        Contains padding and stride information described in @ref PadStrideInfo.
+     * @param[in] weights_info     Specifies if the weights tensor has been reshaped with CLWeightsReshapeKernel. Data type supported: Same as @p input.
+     * @param[in] act_info         (Optional) Activation layer information in case of a fused activation.
+     * @param[in] gpu_target       Specifies the @p GPUTarget.
+     * @param[in] dilation         (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
+     * @param[in] enable_fast_math (Optional) Enable fast math computation. In case this flag were set, the function could dispatch the fastest implementation
+     *                             available which may introduce a drop of accuracy as well. Default is false
      *
      * @return a status
      */
     static ConvolutionMethod get_convolution_method(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *output, const PadStrideInfo &conv_info,
-                                                    const WeightsInfo &weights_info, const ActivationLayerInfo &act_info, const GPUTarget gpu_target, const Size2D &dilation = Size2D(1U, 1U));
+                                                    const WeightsInfo &weights_info, const ActivationLayerInfo &act_info, const GPUTarget gpu_target, const Size2D &dilation = Size2D(1U, 1U), bool enable_fast_math = false);
     // Inherited methods overridden:
     void run() override;