#pragma kernel Conv2D
#pragma kernel Conv2D_RegisterBlock4x2
#pragma kernel Conv2D_L1Cached64_RegisterBlock4x4
#pragma kernel Conv2D_L1Cached32_RegisterBlock4x4
//#pragma kernel Conv2D_L1Cached64_RegisterBlock4x4
//#pragma kernel Conv2D_L1Cached32_RegisterBlock4x4
#pragma kernel DepthwiseConv2D
#pragma kernel Dense_L1Cached64
#pragma kernel DenseTiled16x16
#pragma kernel DenseTiled32x32
#pragma kernel DenseTiled64x64
//#pragma kernel DenseTiled32x32
//#pragma kernel DenseTiled64x64
#include "Tensor.cginc"