first version that can run

example/14_conv2d_backward_weight_xdl/README.md

-# Instructions for ```conv2d_fwd_xdl``` Example
+# Instructions for ```conv2d_wrw_xdl``` Example
 
 ## Docker script
 ```bash
@@ -13,7 +13,7 @@ rocm/tensorflow:rocm4.3.1-tf2.6-dev                                          \
 /bin/bash
 ```
 
-## Build ```conv2d_fwd_xdl```
+## Build ```conv2d_wrw_xdl```
 ```bash
 mkdir build && cd build
 ```
@@ -30,28 +30,29 @@ cmake                                                                  \
 ```
 
 ```bash
- make -j conv2d_fwd_xdl
+ make -j conv2d_wrw_xdl
 ```
 
-## Run ```conv2d_fwd_xdl```
+## Run ```conv2d_wrw_xdl```
 ```bash
 #arg1: verification (0=no, 1=yes)
 #arg2: initialization (0=no init, 1=integer value, 2=decimal value)
 #arg3: run kernel # of times (>1)
-#arg4 to 18: N, K, C, Y, X, Hi, Wi, Sy, Sx, Dy, Dx, LeftPy, LeftPx, RightPy, RightPx
-./example/conv2d_fwd_xdl 0 1 5
+#arg4: is show log (0=no, 1=yes)
+#arg5 to 19: N, K, C, Y, X, Hi, Wi, Sy, Sx, Dy, Dx, LeftPy, LeftPx, RightPy, RightPx, split-k
+./example/conv2d_fwd_xdl 0 1 5 1
 ```
 
-Result (MI100 @ 1087Mhz, 133.5TFlops peak FP16)
+Result 
 ```
-in_n_c_hi_wi: dim 4, lengths {128, 192, 71, 71}, strides {967872, 1, 13632, 192}
-wei_k_c_y_x: dim 4, lengths {256, 192, 3, 3}, strides {1728, 1, 576, 192}
+in_n_c_hi_wi: dim 4, lengths {128, 128, 71, 71}, strides {645248, 1, 9088, 128}
+wei_k_c_y_x: dim 4, lengths {256, 128, 3, 3}, strides {1152, 1, 384, 128}
 out_n_k_ho_wo: dim 4, lengths {128, 256, 36, 36}, strides {331776, 1, 9216, 256}
-arg.a_grid_desc_k0_m_k1_{216, 165888, 8}
-arg.b_grid_desc_k0_n_k1_{216, 256, 8}
-arg.c_grid_desc_m_n_{ 165888, 256}
-launch_and_time_kernel: grid_dim {1296, 1, 1}, block_dim {256, 1, 1}
+arg.a_grid_desc_kbatch_k0_m_k1_{1, 20736, 256}
+arg.b_grid_desc_kbatch_k0_n_k1_{1, 20736, 1152}
+arg.c_grid_desc_m_n_{ 256, 1152}
+launch_and_time_kernel: grid_dim {18, 1, 1}, block_dim {256, 1, 1} 
 Warm up
 Start running 5 times...
-Perf: 1.43206 ms, 102.486 TFlops, 232.947 GB/s
+Perf: 12.0997 ms, 8.08653 TFlops, 20.7201 GB/s
 ```

example/14_conv2d_backward_weight_xdl/main.cpp

@@ -78,6 +78,7 @@ int main(int argc, char* argv[])
     bool do_verification = 0;
     int init_method      = 0;
     int nrepeat          = 5;
+    int do_log           = 0;
 
     // Conv shape
     ck::index_t N               = 128;
@@ -97,42 +98,45 @@ int main(int argc, char* argv[])
     ck::index_t in_right_pad_w  = 1;
     ck::index_t split_k         = 1;
 
-    if(argc == 4)
+    if(argc == 5)
     {
         do_verification = std::stoi(argv[1]);
         init_method     = std::stoi(argv[2]);
         nrepeat         = std::stoi(argv[3]);
+        do_log          = std::stoi(argv[4]);
     }
-    else if(argc == 20)
+    else if(argc == 21)
     {
         do_verification = std::stoi(argv[1]);
         init_method     = std::stoi(argv[2]);
         nrepeat         = std::stoi(argv[3]);
-
-        N               = std::stoi(argv[4]);
-        K               = std::stoi(argv[5]);
-        C               = std::stoi(argv[6]);
-        Y               = std::stoi(argv[7]);
-        X               = std::stoi(argv[8]);
-        Hi              = std::stoi(argv[9]);
-        Wi              = std::stoi(argv[10]);
-        conv_stride_h   = std::stoi(argv[11]);
-        conv_stride_w   = std::stoi(argv[12]);
-        conv_dilation_h = std::stoi(argv[13]);
-        conv_dilation_w = std::stoi(argv[14]);
-        in_left_pad_h   = std::stoi(argv[15]);
-        in_left_pad_w   = std::stoi(argv[16]);
-        in_right_pad_h  = std::stoi(argv[17]);
-        in_right_pad_w  = std::stoi(argv[18]);
-        split_k         = std::stoi(argv[19]);
+        do_log          = std::stoi(argv[4]);
+
+        N               = std::stoi(argv[5]);
+        K               = std::stoi(argv[6]);
+        C               = std::stoi(argv[7]);
+        Y               = std::stoi(argv[8]);
+        X               = std::stoi(argv[9]);
+        Hi              = std::stoi(argv[10]);
+        Wi              = std::stoi(argv[11]);
+        conv_stride_h   = std::stoi(argv[12]);
+        conv_stride_w   = std::stoi(argv[13]);
+        conv_dilation_h = std::stoi(argv[14]);
+        conv_dilation_w = std::stoi(argv[15]);
+        in_left_pad_h   = std::stoi(argv[16]);
+        in_left_pad_w   = std::stoi(argv[17]);
+        in_right_pad_h  = std::stoi(argv[18]);
+        in_right_pad_w  = std::stoi(argv[19]);
+        split_k         = std::stoi(argv[20]);
     }
     else
     {
         printf("arg1: verification (0=no, 1=yes)\n");
         printf("arg2: initialization (0=no init, 1=integer value, 2=decimal value)\n");
         printf("arg3: run kernel # of times (>1)\n");
-        printf("arg4 to 18: N, K, C, Y, X, Hi, Wi, Sy, Sx, Dy, Dx, LeftPy, LeftPx, RightPy, "
-               "RightPx\n");
+        printf("arg4: is show log (0=no, 1=yes)\n");
+        printf("arg5 to 19: N, K, C, Y, X, Hi, Wi, Sy, Sx, Dy, Dx, LeftPy, LeftPx, RightPy, "
+               "RightPx, split-k\n");
         exit(0);
     }
 
@@ -267,7 +271,7 @@ int main(int argc, char* argv[])
 
         wei_device_buf.FromDevice(wei_k_c_y_x_device_result.mData.data());
 
-        if(1)
+        if(do_log)
         {
             LogRangeAsType<float>(std::cout << "out: ", out_n_k_ho_wo.mData, ",") << std::endl;
             LogRangeAsType<float>(std::cout << "in : ", in_n_c_hi_wi.mData, ",") << std::endl;