Merge branch 'develop' of...

Merge branch 'develop' of https://github.com/ROCmSoftwarePlatform/composable_kernel into add_fp16_wmma_conv_instance

client_example/15_gemm_add_multiply/gemm_add_multiply.cpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
 #include <iomanip>
 #include <vector>

client_example/15_reduce/reduce_nhwc_c.cpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
 #include <functional>
 #include <numeric>

client_example/16_convnd_fwd/common.hpp

@@ -141,14 +141,10 @@ bool run_grouped_conv_fwd(std::array<ck::index_t, NumDimSpatial + NumNonSpatialD
                 std::next(rbegin(in_strides)),
                 std::next(rbegin(in_strides), NumDimSpatial + 1));
 
-    std::rotate(
-        std::next(rbegin(wei_lengths)), std::next(rbegin(wei_lengths), 2), rend(wei_lengths));
     std::rotate(rbegin(wei_lengths),
                 std::next(rbegin(wei_lengths)),
                 std::next(rbegin(wei_lengths), NumDimSpatial + 1));
 
-    std::rotate(
-        std::next(rbegin(wei_strides)), std::next(rbegin(wei_strides), 2), rend(wei_strides));
     std::rotate(rbegin(wei_strides),
                 std::next(rbegin(wei_strides)),
                 std::next(rbegin(wei_strides), NumDimSpatial + 1));

client_example/16_convnd_fwd/conv3d_fwd_fp16.cpp

@@ -11,7 +11,7 @@ using WeiDataType = ck::half_t;
 using OutDataType = ck::half_t;
 
 using InLayout  = ck::tensor_layout::convolution::NDHWGC;
-using WeiLayout = ck::tensor_layout::convolution::KZYXGC;
+using WeiLayout = ck::tensor_layout::convolution::GKZYXC;
 using OutLayout = ck::tensor_layout::convolution::NDHWGK;
 
 static constexpr ck::index_t NumDimSpatial = 3;
@@ -38,7 +38,7 @@ int main()
                                 InLayout,
                                 WeiLayout,
                                 OutLayout>(
-               {N, Di, Hi, Wi, G, C}, {K, Z, Y, X, G, C}, {N, Do, Ho, Wo, G, K})
+               {N, Di, Hi, Wi, G, C}, {G, K, Z, Y, X, C}, {N, Do, Ho, Wo, G, K})
                ? EXIT_SUCCESS
                : EXIT_FAILURE;
 }

client_example/16_convnd_fwd/conv3d_fwd_fp32.cpp

@@ -11,7 +11,7 @@ using WeiDataType = float;
 using OutDataType = float;
 
 using InLayout  = ck::tensor_layout::convolution::NDHWGC;
-using WeiLayout = ck::tensor_layout::convolution::KZYXGC;
+using WeiLayout = ck::tensor_layout::convolution::GKZYXC;
 using OutLayout = ck::tensor_layout::convolution::NDHWGK;
 
 static constexpr ck::index_t NumDimSpatial = 3;
@@ -38,7 +38,7 @@ int main()
                                 InLayout,
                                 WeiLayout,
                                 OutLayout>(
-               {N, Di, Hi, Wi, G, C}, {K, Z, Y, X, G, C}, {N, Do, Ho, Wo, G, K})
+               {N, Di, Hi, Wi, G, C}, {G, K, Z, Y, X, C}, {N, Do, Ho, Wo, G, K})
                ? EXIT_SUCCESS
                : EXIT_FAILURE;
 }

client_example/17_grouped_gemm_fastgelu/grouped_gemm_fastgelu.cpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
 #include <iomanip>
 #include <iostream>

client_example/18_groupnorm/groupnorm_swish.cpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
 #include <iomanip>
 #include <vector>
@@ -72,6 +72,30 @@ int main(int argc, char* argv[])
 
     std::cout << "found " << op_ptrs.size() << " instances" << std::endl;
 
+    const auto& generic_op_ptr = op_ptrs[0];
+
+    auto generic_argument_ptr =
+        generic_op_ptr->MakeArgumentPointer({N, H, W, G, C},    // lengths
+                                            xy_strides,         // xStrides
+                                            gamma_beta_strides, // gammaStrides
+                                            gamma_beta_strides, // betaStrides
+                                            xy_strides,         // yStrides
+                                            {1, 2, 4},          // reduceDims
+                                            1e-6,
+                                            x_device_buf.GetDeviceBuffer(),
+                                            gamma_device_buf.GetDeviceBuffer(),
+                                            beta_device_buf.GetDeviceBuffer(),
+                                            y_device_buf.GetDeviceBuffer(),
+                                            nullptr,
+                                            nullptr,
+                                            Swish{});
+
+    if(!generic_op_ptr->IsSupportedArgument(generic_argument_ptr.get()))
+    {
+        throw std::runtime_error(
+            "The generic kernel instance should be able to support any input shapes");
+    };
+
     std::string best_op_name;
     bool found            = false;
     int best_op_id        = -1;

client_example/19_pool_fwd/avg_pool3d_fwd.cpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
 #include <iomanip>
 #include <vector>

client_example/19_pool_fwd/max_pool2d_fwd.cpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
 #include <iomanip>
 #include <vector>

example/01_gemm/common.hpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
 #pragma once
 

example/01_gemm/gemm_dl_fp16.cpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "common.hpp"
 

example/01_gemm/gemm_dl_fp32.cpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "common.hpp"
 

example/01_gemm/gemm_dl_int4.cpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
 #ifndef CK_EXPERIMENTAL_BIT_INT_EXTENSION_INT4
 #error Should compile this file with ck::int4_t support

example/01_gemm/gemm_dl_int8.cpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "common.hpp"
 

example/01_gemm/gemm_wmma_fp16.cpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "common.hpp"
 

example/01_gemm/gemm_xdl_bf16.cpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "common.hpp"
 

example/01_gemm/gemm_xdl_fp16.cpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "common.hpp"
 

example/01_gemm/gemm_xdl_fp64.cpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "common.hpp"
 

example/01_gemm/gemm_xdl_int4.cpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
 #ifndef CK_EXPERIMENTAL_BIT_INT_EXTENSION_INT4
 #error Should compile this file with ck::int4_t support

example/01_gemm/gemm_xdl_int8.cpp

 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2022, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2023, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "common.hpp"