[CK][Examples] Extending support for rdna3/4 in following examples: (#2884)

* [CK][Examples] Extending support for rdna3/4 in following examples:
-example_gemm_xdl_splitk_reduce_multi_d_fp16
-example_gemm_xdl_splitk_reduce_multi_d_bf16
-example_gemm_xdl_splitk_reduce_bf16A_i8B
-example_gemm_xdl_splitk_reduce_bfp16
-example_splitk_gemm_bias_e_permute_xdl_fp32
-example_gemm_add_multiply_xdl_fp16
-example_complex_contraction_bilinear_xdl_fp32
-example_grouped_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16
-example_batched_gemm_bias_e_permute_xdl_fp16
-example_gemm_xdl_fp16
-example_gemm_xdl_fp16_av2
-example_gemm_xdl_wavelet_fp16
-example_gemm_add_add_fastgelu_xdl_bf16
-example_gemm_add_add_fastgelu_xdl_fp16
-example_gemm_add_add_fastgelu_xdl_fp32
-example_grouped_gemm_xdl_fp32
-example_grouped_gemm_xdl_fp16
-example_grouped_gemm_xdl_bf16
-example_cgemm_xdl_bf16
-example_cgemm_xdl_fp16

Signed-off-by: Michal Kulikowski <Michal.Kulikowski@amd.com>

* [CK][Examples] Extending support for rdna3/4 in following examples:
-example_gemm_xdl_splitk_reduce_multi_d_fp16
-example_gemm_xdl_splitk_reduce_multi_d_bf16
-example_gemm_xdl_splitk_reduce_bf16A_i8B
-example_gemm_xdl_splitk_reduce_bfp16
-example_splitk_gemm_bias_e_permute_xdl_fp32
-example_gemm_add_multiply_xdl_fp16
-example_complex_contraction_bilinear_xdl_fp32
-example_grouped_gemm_lower_triangle_scale_softmax_gemm_permute_xdl_fp16
-example_batched_gemm_bias_e_permute_xdl_fp16
-example_gemm_xdl_fp16
-example_gemm_xdl_fp16_av2
-example_gemm_xdl_wavelet_fp16
-example_gemm_add_add_fastgelu_xdl_bf16
-example_gemm_add_add_fastgelu_xdl_fp16
-example_gemm_add_add_fastgelu_xdl_fp32
-example_grouped_gemm_xdl_fp32
-example_grouped_gemm_xdl_fp16
-example_grouped_gemm_xdl_bf16
-example_cgemm_xdl_bf16
-example_cgemm_xdl_fp16

Signed-off-by: Michal Kulikowski <Michal.Kulikowski@amd.com>

---------

Signed-off-by: Michal Kulikowski <Michal.Kulikowski@amd.com>

[ROCm/composable_kernel commit: 2b684f0a7d]

example/35_splitK_gemm/gemm_xdl_splitk_reduce_bf16.cpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "common.hpp"
 
@@ -35,13 +35,13 @@ using DeviceGemmV2Instance =
         256,
         128,  128,  64,
         8,    4,
-        32,   32,
-        2,    2,
+        16,   16,
+        4,    4,
         S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,
         2,    8,    8,   0,
         S<16, 16, 1>,    S<0, 2, 1>,    S<0, 2, 1>,
         1,    8,    4,   0,
-        1,    1,    S<1, 32, 1, 8>,  8,
+        1,    1,    S<1, 32, 1, 8>,  4,
         ck::BlockGemmPipelineScheduler::Intrawave,ck::BlockGemmPipelineVersion::v3>;
 // clang-format on
 

example/35_splitK_gemm/gemm_xdl_splitk_reduce_bf16A_i8B.cpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "common.hpp"
 
@@ -35,13 +35,13 @@ using DeviceGemmV2Instance =
         256,   
         128,  128,  64,
         8,    4,
-        32,   32,
-        2,    2,
+        16,   16,
+        4,    4,
         S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,
         2,    8,    8,   0,
         S<16, 16, 1>,    S<0, 2, 1>,    S<0, 2, 1>,
         1,    8,    4,   0,
-        1,    1,    S<1, 32, 1, 8>,  8,
+        1,    1,    S<1, 32, 1, 8>,  4,
         ck::BlockGemmPipelineScheduler::Intrawave,ck::BlockGemmPipelineVersion::v3, ReduceDataType>;
 // clang-format on
 

example/35_splitK_gemm/gemm_xdl_splitk_reduce_multi_d_bf16.cpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "common.hpp"
 
@@ -35,13 +35,13 @@ using DeviceGemmV2Instance =
         256,
         128,  128,  64,
         8,    4,
-        32,   32,
-        2,    2,
+        16,   16,
+        4,    4,
         S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,
         2,    8,    8,   0,
         S<16, 16, 1>,    S<0, 2, 1>,    S<0, 2, 1>,
         1,    8,    4,   0,
-        1,    1,    S<1, 32, 1, 8>,  8,
+        1,    1,    S<1, 32, 1, 8>,  4,
         ck::BlockGemmPipelineScheduler::Intrawave,ck::BlockGemmPipelineVersion::v3, ReduceDataType>;
 // clang-format on
 

example/35_splitK_gemm/gemm_xdl_splitk_reduce_multi_d_fp16.cpp

@@ -1,5 +1,5 @@
 // SPDX-License-Identifier: MIT
-// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
+// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
 
 #include "common.hpp"
 
@@ -35,13 +35,13 @@ using DeviceGemmV2Instance =
         256,
         128,  128,  64,
         8,    4,
-        32,   32,
-        2,    2,
+        16,   16,
+        4,    4,
         S<8, 32, 1>,     S<1, 0, 2>,    S<1, 0, 2>,
         2,    8,    8,   0,
         S<16, 16, 1>,    S<0, 2, 1>,    S<0, 2, 1>,
         1,    8,    4,   0,
-        1,    1,    S<1, 32, 1, 8>,  8,
+        1,    1,    S<1, 32, 1, 8>,  4,
         ck::BlockGemmPipelineScheduler::Intrawave,ck::BlockGemmPipelineVersion::v2, ReduceDataType>;
 // clang-format on