Merge branch 'develop' of...

Merge branch 'develop' of https://github.com/ROCmSoftwarePlatform/composable_kernel into e2e_kernellib

example/19_binary_elementwise/elementwise_add_1d.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 <iostream>
 #include <cstdlib>

example/19_binary_elementwise/elementwise_add_4d.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 <iostream>
 #include <cstdlib>

example/20_grouped_conv_bwd_weight/CMakeLists.txt

-add_custom_target(example_grouped_conv_bwd_weight)
+if(GPU_TARGETS MATCHES "gfx908" OR GPU_TARGETS MATCHES "gfx90a" OR GPU_TARGETS MATCHES "gfx940")
+   add_custom_target(example_grouped_conv_bwd_weight)
 
-add_example_executable(example_grouped_conv_bwd_weight_xdl_fp16 grouped_conv_bwd_weight_xdl_fp16.cpp)
-add_example_executable(example_grouped_conv_bwd_weight_xdl_bf16 grouped_conv_bwd_weight_xdl_bf16.cpp)
+   add_example_executable(example_grouped_conv_bwd_weight_xdl_fp16 grouped_conv_bwd_weight_xdl_fp16.cpp)
+   add_example_executable(example_grouped_conv_bwd_weight_xdl_bf16 grouped_conv_bwd_weight_xdl_bf16.cpp)
 
-
-add_dependencies(example_grouped_conv_bwd_weight example_grouped_conv_bwd_weight_xdl_fp16
+   add_dependencies(example_grouped_conv_bwd_weight example_grouped_conv_bwd_weight_xdl_fp16
                                                  example_grouped_conv_bwd_weight_xdl_bf16)
+endif()
 
 add_custom_target(example_grouped_conv_bwd_weight_dl)
 

example/20_grouped_conv_bwd_weight/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/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_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/20_grouped_conv_bwd_weight/grouped_conv_bwd_weight_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/20_grouped_conv_bwd_weight/run_grouped_conv_bwd_weight_example.inc

 // 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.
 
 template <ck::index_t NDimSpatial>
 using HostConvBwdWeightInstance = ck::tensor_operation::host::ReferenceConvBwdWeight<NDimSpatial,
@@ -18,7 +18,9 @@ bool run_grouped_conv_bwd_weight(const ExecutionConfig& config,
     // Set split_k = 2 for xdl op, split_k = 1 for dl
     // Dl op doesn't support split_k > 1
     // TODO: Add Dl op split_k > 1 support
-    if(!(ck::get_device_name() == "gfx906" || ck::get_device_name() == "gfx1030"))
+    if(!(ck::get_device_name() == "gfx906" || ck::get_device_name() == "gfx1030" ||
+         ck::get_device_name() == "gfx1100" || ck::get_device_name() == "gfx1101" ||
+         ck::get_device_name() == "gfx1102"))
     {
         split_k = 2;
     }

example/21_gemm_layernorm/CMakeLists.txt

-add_example_executable(example_gemm_bias_relu_add_layernorm_xdl_welford_fp16 gemm_bias_relu_add_layernorm_xdl_welford_fp16.cpp)
-add_example_executable(example_gemm_bias_relu_add_layernorm_xdl_naive_fp16 gemm_bias_relu_add_layernorm_xdl_naive_fp16.cpp)
-add_example_executable(example_gemm_layernorm_xdl_naive_fp16 gemm_layernorm_xdl_naive_fp16.cpp)
-add_example_executable(example_gemm_xdl_layernorm_naive_single_kernel_fp16 gemm_xdl_layernorm_naive_single_kernel_fp16.cpp)
+if(GPU_TARGETS MATCHES "gfx908" OR GPU_TARGETS MATCHES "gfx90a" OR GPU_TARGETS MATCHES "gfx940")
+   add_example_executable(example_gemm_bias_relu_add_layernorm_xdl_welford_fp16 gemm_bias_relu_add_layernorm_xdl_welford_fp16.cpp)
+   add_example_executable(example_gemm_bias_relu_add_layernorm_xdl_naive_fp16 gemm_bias_relu_add_layernorm_xdl_naive_fp16.cpp)
+   add_example_executable(example_gemm_layernorm_xdl_naive_fp16 gemm_layernorm_xdl_naive_fp16.cpp)
+   add_example_executable(example_gemm_xdl_layernorm_naive_single_kernel_fp16 gemm_xdl_layernorm_naive_single_kernel_fp16.cpp)
+endif()

example/21_gemm_layernorm/gemm_bias_relu_add_layernorm_xdl_naive_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 <iostream>
 #include <numeric>

example/21_gemm_layernorm/gemm_bias_relu_add_layernorm_xdl_welford_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 <iostream>
 #include <numeric>

example/21_gemm_layernorm/gemm_layernorm_xdl_naive_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 <iostream>
 #include <numeric>

example/21_gemm_layernorm/gemm_xdl_layernorm_naive_single_kernel_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 <iostream>
 #include <numeric>

example/22_cgemm/cgemm_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 <iostream>
 

example/22_cgemm/cgemm_xdl_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.
 
 #include <numeric>
 #include <initializer_list>

example/22_cgemm/cgemm_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 <iostream>
 

example/22_cgemm/cgemm_xdl_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 <iostream>
 

example/22_cgemm/cgemm_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.
 
 #include <iostream>
 

example/22_cgemm/cgemm_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 <iostream>
 

example/23_softmax/softmax_blockwise.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 <iostream>
 #include <numeric>

example/25_gemm_bias_e_permute/gemm_bias_e_permute_g1m2n3k1_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 <iostream>
 #include <numeric>