COMPMID-1276 - Allow GEMM to work with 3D input tensor
Skipped im2col in CLGEMMConvolutionLayer for 1x1 convolutions with NHWC data layout
Change-Id: I894e6b952ed8605e8f3ffc0ffc25c24730d4664c
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/141909
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Anthony Barbier <anthony.barbier@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
diff --git a/arm_compute/core/CL/kernels/CLGEMMInterleave4x4Kernel.h b/arm_compute/core/CL/kernels/CLGEMMInterleave4x4Kernel.h
index 7f8e766..4592fc2 100644
--- a/arm_compute/core/CL/kernels/CLGEMMInterleave4x4Kernel.h
+++ b/arm_compute/core/CL/kernels/CLGEMMInterleave4x4Kernel.h
@@ -67,17 +67,19 @@
* @param[in] input Input tensor. Data types supported: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32
* @param[out] output Output tensor. Data type supported: same as @p input
* @param[in] mult_interleave4x4_height (Optional) Multiplication factor for the height of the 4x4 interleave block
+ * @param[in] reinterpret_input_as_3d (Optional) True if the input has to be reinterpreted as 3D tensor
*/
- void configure(const ICLTensor *input, ICLTensor *output, int mult_interleave4x4_height = 1);
+ void configure(const ICLTensor *input, ICLTensor *output, int mult_interleave4x4_height = 1, bool reinterpret_input_as_3d = false);
/** Static function to check if given info will lead to a valid configuration of @ref CLGEMMInterleave4x4Kernel
*
* @param[in] input Input tensor info. Data types supported: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32
* @param[in] output Output tensor info which stores the interleaved matrix. Data type supported: same as @p input.
* @param[in] mult_interleave4x4_height Multiplication factor for the height of the 4x4 interleave block
+ * @param[in] reinterpret_input_as_3d (Optional) True if the input has to be reinterpreted as 3D tensor
*
* @return a status
*/
- static Status validate(const ITensorInfo *input, const ITensorInfo *output, int mult_interleave4x4_height);
+ static Status validate(const ITensorInfo *input, const ITensorInfo *output, int mult_interleave4x4_height, bool reinterpret_input_as_3d);
// Inherited methods overridden
void run(const Window &window, cl::CommandQueue &queue) override;
@@ -85,6 +87,7 @@
private:
const ICLTensor *_input;
ICLTensor *_output;
+ bool _reinterpret_input_as_3d;
};
} // namespace arm_compute
#endif /* __ARM_COMPUTE_CLGEMMINTERLEAVE4X4KERNEL_H__ */