Add json dump support to output details from CK/CKTile Examples. (#2551)

* Adding RapidJson Library

* Adding Json Dumps in all CK_Tile Examples

Not verified yet

* Adding json to cktile Batched Transpose

* adding json dumps to layernorm2d_fwd

* Adding  json dump to flatmm_basic

* Adding RapidJson Library

* Adding Json Dumps in all CK_Tile Examples

Not verified yet

* Adding json to cktile Batched Transpose

* adding json dumps to layernorm2d_fwd

* Adding  json dump to flatmm_basic

* Adding json in 03_gemm

* Add json dump to 16_batched_gemm

* Add json dump to gemm_multi_d_fp16

* Add json dump to grouped_gemm

* fix fmha_bwd/fwd

* Fix clang-format errors

exclude include/rapidjson in jenkins as its a third-party library

* Saparating function and defination.

* Update Documentation of 03_gemm

* Refactoring as per code review

* Disable fp8 instances on unsupported targets (#2592)

* Restrict building of gemm_universal_preshuffle_f8 instances to specific targets in CMakeLists.txt

* Add condition to skip gemm_xdl_universal_preshuffle_f8 instances for unsupported targets in CMakeLists.txt

* Add conditions to skip unsupported targets for gemm_universal_preshuffle_f8 and gemm_xdl_universal_preshuffle_f8 instances in CMakeLists.txt

* Refine conditions to exclude gemm_universal_preshuffle_f8 instances for unsupported targets in CMakeLists.txt

---------

Co-authored-by: AviralGoelAMD <aviralgoel@amd.com>

* fix clang format

* remove duplicate lines of code from library/src/tensor_operation_instance/gpu/CMakeLists.txt

* Fixing Readme and unifying jsondumps

* adding moe_smoothquant

* adding fused_moe

* Fixing Readme for batched_gemm

* Fixing Readme for grouped_gemm

* adding flatmm

* adding gemm_multi_d_fp16

* adding elementwise

* adding File name when json is dumped

* Fixing Reduce after merge

* adding batched_transpose

* Adding Warptile in Gemm

* Fixing Clang Format

---------

Co-authored-by: Aviral Goel <aviral.goel@amd.com>
Co-authored-by: AviralGoelAMD <aviralgoel@amd.com>
Co-authored-by: illsilin_amdeng <Illia.Silin@amd.com>

example/ck_tile/09_topk_softmax/README.md

@@ -24,5 +24,7 @@ args:
        -st_o    row stride of output/indices, -1 means same as topk (default:-1)
        -seed    seed to be used, -1 means random every time (default:-1)
       -kname    when set to 1 it will print kernel name (default:0)
+       -json    0: No Json, 1: Dump Results in Json format (default:0)
+   -jsonfile    json file name to dump results (default:topk_softmax.json)
 
 ```

example/ck_tile/09_topk_softmax/topk_softmax.cpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #include <vector>
 #include <iostream>
@@ -13,6 +13,7 @@
 #include "ck_tile/core.hpp"
 #include "ck_tile/ops/reduce.hpp"
 #include "topk_softmax_api.hpp"
+#include "json_dump.hpp"
 
 #if 0
 template <typename T>
@@ -130,7 +131,9 @@ auto create_args(int argc, char* argv[])
         .insert("seed", "-1", "seed to be used, -1 means random every time")
         .insert("kname", "0", "when set to 1 it will print kernel name")
         .insert("warmup", "5", "number of iterations before benchmark the kernel")
-        .insert("repeat", "20", "number of iterations to benchmark the kernel");
+        .insert("repeat", "20", "number of iterations to benchmark the kernel")
+        .insert("json", "0", "0: No Json, 1: Dump Results in Json format")
+        .insert("jsonfile", "topk_softmax.json", "json file name to dump results");
 
     bool result = arg_parser.parse(argc, argv);
     return std::make_tuple(result, arg_parser);
@@ -273,6 +276,23 @@ bool test_topk_softmax(ck_tile::ArgParser args)
     }
 
     printf("valid:%s\n", rtn ? "y" : "n");
+
+    if(args.get_int("json") == 1)
+    {
+        dump_topk_softmax_json(args.get_str("jsonfile"),
+                               input_prec,
+                               weight_prec,
+                               tokens,
+                               experts,
+                               topk,
+                               stride_input,
+                               stride_output,
+                               ms,
+                               0,
+                               0,
+                               rtn);
+    }
+
     fflush(stdout);
     return rtn;
 }

example/ck_tile/09_topk_softmax/topk_softmax_api.cpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2024, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "topk_softmax_api.hpp"