Add weights_info as optional input for NEDeconvolutionLayer
This is so that we can leverage fixed format kernel when
using gemm convolution method.
Partially resolves: [ONCPUML-1129]
Change-Id: I61ffa74f5cd9d75579dbc1f9aa187371f855e932
Signed-off-by: Annop Wongwathanarat <annop.wongwathanarat@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9248
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
diff --git a/arm_compute/runtime/NEON/functions/NEDeconvolutionLayer.h b/arm_compute/runtime/NEON/functions/NEDeconvolutionLayer.h
index 869df69..cdc3a63 100644
--- a/arm_compute/runtime/NEON/functions/NEDeconvolutionLayer.h
+++ b/arm_compute/runtime/NEON/functions/NEDeconvolutionLayer.h
@@ -110,12 +110,14 @@
* @param[in] bias Optional, ignored if NULL. The biases have one dimension.
* Data type supported: Data types supported: S32 for QASYMM8/QASYMM8_SIGNED input, F32 for F32 input, F16 for F16 input.
* @param[out] output Output tensor. The output has the same number of dimensions as the @p input.
- * @param[in] info Contains padding and policies to be used in the deconvolution, this is decribed in @ref PadStrideInfo.
+ * @param[in] info Contains padding and policies to be used in the deconvolution, this is described in @ref PadStrideInfo.
* @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
+ * available which may introduce a drop of accuracy as well. Default is false
+ * @param[in] weights_info (Optional) Specifies the weight format. Default is unspecified. This parameter can be used to specify the weight format that is optimal for
+ * the GEMM convolution.
*
*/
- void configure(ITensor *input, const ITensor *weights, const ITensor *bias, ITensor *output, const PadStrideInfo &info, bool enable_fast_math = false);
+ void configure(ITensor *input, const ITensor *weights, const ITensor *bias, ITensor *output, const PadStrideInfo &info, bool enable_fast_math = false, const WeightsInfo &weights_info = WeightsInfo());
/** Static function to check if given info will lead to a valid configuration of @ref NEDeconvolutionLayer
*
* @param[in] input Input tensor info. 3 lower dimensions represent a single input, and an optional 4th dimension for batch of inputs.
@@ -124,13 +126,16 @@
* Data type supported: Same as @p input, also could be QSYMM8_PER_CHANNEL if input is QASYMM8/QASYMM8_SIGNED.
* @param[in] bias (Optional) The biases have one dimension. Data type supported: Data types supported: S32 for QASYMM8/QASYMM8_SIGNED input, F32 for F32 input, F16 for F16 input.
* @param[in] output Output tensor info. The output has the same number of dimensions as the @p input.
- * @param[in] info Contains padding and policies to be used in the deconvolution, this is decribed in @ref PadStrideInfo.
+ * @param[in] info Contains padding and policies to be used in the deconvolution, this is described in @ref PadStrideInfo.
* @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
+ * available which may introduce a drop of accuracy as well. Default is false
+ * @param[in] weights_info (Optional) Specifies the weight format. Default is unspecified. This parameter can be used to specify the weight format that is optimal for
+ * the GEMM convolution.
*
* @return a status
*/
- static Status validate(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *bias, const ITensorInfo *output, const PadStrideInfo &info, bool enable_fast_math = false);
+ static Status validate(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *bias, const ITensorInfo *output, const PadStrideInfo &info,
+ bool enable_fast_math = false, const WeightsInfo &weights_info = WeightsInfo());
// Inherited methods overridden:
void run() override;
@@ -150,5 +155,5 @@
bool _is_prepared;
bool _do_upsampling;
};
-} // arm_compute
+} // namespace arm_compute
#endif /* ARM_COMPUTE_NEDECONVOLUTIONLAYER_H */