add 256x256x32 tile for conv2d bwd-weight

library/src/tensor_operation_instance/gpu/conv2d_bwd_weight/device_conv2d_bwd_weight_xdl_nhwc_kyxc_nhwk_f16_instance.cpp

@@ -24,6 +24,7 @@ using device_conv2d_bwd_weight_xdl_nhwc_kyxc_nhwk_f16_instances = std::tuple<
         //#################################################################################|   Type|    Type|    Type|    Type| Elementwise| Elementwise| Elementwise|   Size| Block| Block| Block|   |  XDL|  XDL|  Per|  Per|   ThreadCluster|    ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|    ThreadCluster|   ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave|    ClusterLengths|ScalarPerVector|
         //#################################################################################|       |        |        |        |   Operation|   Operation|   Operation|       |      |      |      |   |     |     | Wave| Wave| Lengths_K0_M_K1|     ArrangeOrder|               |               |      PerVector|   PerVector_K1|          |  Lengths_K0_N_K1|    ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |  PerShuffle|  PerShuffle|  MBlock_MPerBlock|   NWaveNPerXdl|
         //#################################################################################|       |        |        |        |            |            |            |       |      |      |      |   |     |     |     |     |                |                 |               |               |               |               |          |                 |                |               |              |               |               |          |            |            |  NBlock_NPerBlock|               |
+        DeviceConv2dBwdWeightXdl_C_Shuffle_Input_N_Hi_Wi_C_Weight_K_Y_X_C_Output_N_Ho_Wo_K<    F16,     F16,     F16,     F32,  PassThrough, PassThrough, PassThrough,    256,   256,   256,    4,  8,   32,   32,    4,    4,  S<1, 4, 32, 2>,   S<0, 3, 1, 2>,   S<0, 2, 1, 3>,             2,              8,              4,    true,     S<1, 4, 32, 2>,   S<0, 3, 1, 2>,   S<0, 2, 1, 3>,             2,              8,              4,      true,        1,            1,     S<1, 32, 1, 8>,        8>,
         DeviceConv2dBwdWeightXdl_C_Shuffle_Input_N_Hi_Wi_C_Weight_K_Y_X_C_Output_N_Ho_Wo_K<    F16,     F16,     F16,     F32,  PassThrough, PassThrough, PassThrough,    256,   256,   128,    4,  8,   32,   32,    4,    2,  S<1, 4, 32, 2>,   S<0, 3, 1, 2>,   S<0, 2, 1, 3>,             2,              8,              4,    true,     S<1, 4, 16, 4>,   S<0, 3, 1, 2>,   S<0, 2, 1, 3>,             2,              8,              2,      true,        1,            1,     S<1, 32, 1, 8>,        8>,
         //DeviceConv2dBwdWeightXdl_C_Shuffle_Input_N_Hi_Wi_C_Weight_K_Y_X_C_Output_N_Ho_Wo_K<    F16,     F16,     F16,     F32,  PassThrough, PassThrough, PassThrough,    256,   256,   128,    4,  8,   32,   32,    4,    2,  S<1, 4, 64, 1>,   S<0, 3, 1, 2>,   S<0, 2, 1, 3>,             2,              4,              8,    true,     S<1, 4, 32, 2>,   S<0, 3, 1, 2>,   S<0, 2, 1, 3>,             2,              4,              4,      true,        1,            1,     S<1, 32, 1, 8>,        8>,