Merge branch 'develop' into ck_tile/fmha_receipt_aiter

codegen/test/grouped_conv_fwd_multiple_d_v1.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
+
 #include "ck/host/device_grouped_conv_fwd_multiple_d/conv_fwd_op.hpp"
 #include "ck/host/device_grouped_conv_fwd_multiple_d/conv_fwd_problem.hpp"
 #include "ck/host/headers.hpp"

codegen/test/grouped_conv_fwd_multiple_d_v2.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
+
 #include "ck/host/device_grouped_conv_fwd_multiple_d/conv_fwd_op.hpp"
 #include "ck/host/device_grouped_conv_fwd_multiple_d/conv_fwd_problem.hpp"
 #include "ck/host/headers.hpp"

codegen/test/grouped_conv_fwd_multiple_d_v3.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
+
 #include "ck/host/device_grouped_conv_fwd_multiple_d/conv_fwd_op.hpp"
 #include "ck/host/device_grouped_conv_fwd_multiple_d/conv_fwd_problem.hpp"
 #include "ck/host/headers.hpp"

codegen/test/grouped_conv_fwd_multiple_d_v4.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
+
 #include "ck/host/device_grouped_conv_fwd_multiple_d/conv_fwd_op.hpp"
 #include "ck/host/device_grouped_conv_fwd_multiple_d/conv_fwd_problem.hpp"
 #include "ck/host/headers.hpp"

codegen/test/include/common.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
+
 #pragma once
 #include <algorithm>
 #include <cmath>

codegen/test/rtc/include/rtc/compile_kernel.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
+
 #ifndef GUARD_HOST_TEST_RTC_INCLUDE_RTC_COMPILE_KERNEL
 #define GUARD_HOST_TEST_RTC_INCLUDE_RTC_COMPILE_KERNEL
 

codegen/test/rtc/include/rtc/hip.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
+
 #ifndef GUARD_HOST_TEST_RTC_INCLUDE_RTC_HIP
 #define GUARD_HOST_TEST_RTC_INCLUDE_RTC_HIP
 
 #include <hip/hip_runtime_api.h>
 #include <memory>
+#include <stdexcept>
 #include <string>
 #include <stdexcept>
 

codegen/test/rtc/include/rtc/kernel.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
+
 #ifndef GUARD_HOST_TEST_RTC_INCLUDE_RTC_KERNEL
 #define GUARD_HOST_TEST_RTC_INCLUDE_RTC_KERNEL
 

codegen/test/rtc/include/rtc/manage_ptr.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
+
 #ifndef GUARD_HOST_TEST_RTC_INCLUDE_RTC_MANAGE_POINTER
 #define GUARD_HOST_TEST_RTC_INCLUDE_RTC_MANAGE_POINTER
 

codegen/test/rtc/include/rtc/tmp_dir.hpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
+
 #ifndef GUARD_HOST_TEST_RTC_INCLUDE_RTC_TMP_DIR
 #define GUARD_HOST_TEST_RTC_INCLUDE_RTC_TMP_DIR
 

codegen/test/rtc/src/compile_kernel.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
+
 #include <rtc/hip.hpp>
 #include <rtc/compile_kernel.hpp>
 #include <rtc/tmp_dir.hpp>

codegen/test/rtc/src/hip.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
+
 #include <rtc/hip.hpp>
 #include <rtc/manage_ptr.hpp>
 #include <stdexcept>

codegen/test/rtc/src/kernel.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
+
 #include <rtc/kernel.hpp>
 #include <rtc/manage_ptr.hpp>
 #include <rtc/hip.hpp>
+#include <stdexcept>
 #include <cassert>
 
 // extern declare the function since hip/hip_ext.h header is broken

codegen/test/rtc/src/tmp_dir.cpp

+// SPDX-License-Identifier: MIT
+// Copyright (c) 2024-2025, Advanced Micro Devices, Inc. All rights reserved.
+
 #include <rtc/tmp_dir.hpp>
 #include <algorithm>
 #include <random>

docs/sphinx/requirements.in

-rocm-docs-core==1.14.1
+rocm-docs-core==1.15.0
 sphinxcontrib-bibtex==2.6.3

docs/sphinx/requirements.txt

@@ -199,7 +199,7 @@ requests==2.32.3
     # via
     #   pygithub
     #   sphinx
-rocm-docs-core==1.14.1
+rocm-docs-core==1.15.0
     # via -r requirements.in
 rpds-py==0.22.3
     # via

example/01_gemm/CMakeLists.txt

@@ -61,7 +61,7 @@ add_example_dependencies(example_gemm_xdl example_gemm_xdl_fp64)
 
 add_example_executable(example_gemm_xdl_streamk gemm_xdl_streamk.cpp)
 
-list(APPEND gpu_list gfx90a gfx940 gfx941 gfx942)
+list(APPEND gpu_list gfx90a gfx940 gfx941 gfx942 gfx950)
 set(target 0)
 foreach(gpu IN LISTS GPU_TARGETS)
     if(gpu IN_LIST gpu_list AND target EQUAL 0)

example/01_gemm/gemm_xdl_fp16.cpp

@@ -31,9 +31,7 @@ using DeviceGemmInstance0 = ck::tensor_operation::device::DeviceGemmXdl
 // ######|          |          |          |            |        |        |        |   Operation|   Operation|   Operation|              |      |      |      |      |   |     |     | Wave| Wave| Lengths_K0_M_K1|   ArrangeOrder|               |               |      PerVector|   PerVector_K1|          | Lengths_K0_N_K1|   ArrangeOrder|               |              |      PerVector|   PerVector_K1|          |                |       PerVector|
 // ######|          |          |          |            |        |        |        |            |            |            |              |      |      |      |      |   |     |     |     |     |                |               |               |               |               |               |          |                |               |               |              |               |               |          |                |                |
          < ADataType, BDataType, CDataType, AccDataType, ALayout, BLayout, CLayout,  AElementOp,  BElementOp,  CElementOp,   GemmDefault,   256,   256,   128,     4,  8,   32,   32,    4,    2,     S<4, 64, 1>,     S<1, 0, 2>,     S<1, 0, 2>,              2,              8,              8,      true,     S<4, 32, 1>,     S<0, 2, 1>,     S<0, 2, 1>,             1,              4,              8,      true,               7,               1>;
-// // clang-format on
 
-// clang-format off
 using DeviceGemmInstance1 = ck::tensor_operation::device::DeviceGemm_Xdl_CShuffle
 // ######| ALayout| BLayout| CLayout|     AData|     BData|     CData|     AccData|         CShuffle|           A|           B|           C|           GEMM| NumGemmK| Block|  MPer|  NPer|  KPer| AK1| BK1| MPer| NPer| MXdl| NXdl|  ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockTransfer| ABlockLds|  BBlockTransfer| BBlockTransfer| BBlockTransfer| BlockTransfer| BBlockTransfer| BBlockTransfer| BBlockLds|    CShuffle|    CShuffle| CBlockTransferClusterLengths|  CBlockTransfer|
 // ######|        |        |        |      Type|      Type|      Type|        Type|         DataType| Elementwise| Elementwise| Elementwise| Spacialization| Prefetch|  Size| Block| Block| Block|    |    |  XDL|  XDL|  Per|  Per|   ThreadCluster|  ThreadCluster| SrcAccessOrder|   SrcVectorDim|      SrcScalar|      DstScalar| AddExtraM|   ThreadCluster|  ThreadCluster| SrcAccessOrder|  SrcVectorDim|      SrcScalar|      DstScalar| AddExtraN| MXdlPerWave| NXdlPerWave|         _MBlock_MWaveMPerXdl| ScalarPerVector|

example/04_gemm_add_add_fastgelu/CMakeLists.txt

@@ -16,7 +16,7 @@ if(USE_BITINT_EXTENSION_INT4)
     add_example_dependencies(example_gemm_add_add_fastgelu_xdl example_gemm_add_add_fastgelu_xdl_int4)
 endif(USE_BITINT_EXTENSION_INT4)
 
-list(APPEND gpu_list gfx90a gfx940 gfx941 gfx942)
+list(APPEND gpu_list gfx90a gfx940 gfx941 gfx942 gfx950)
 set(target 0)
 foreach(gpu IN LISTS GPU_TARGETS)
     if(gpu IN_LIST gpu_list AND target EQUAL 0)

example/18_batched_gemm_reduce/CMakeLists.txt

-list(APPEND gpu_list gfx908 gfx90a gfx940 gfx941 gfx942)
+list(APPEND gpu_list gfx908 gfx90a gfx940 gfx941 gfx942 gfx950)
 set(target 0)
 foreach(gpu IN LISTS GPU_TARGETS)
  if(gpu IN_LIST gpu_list AND target EQUAL 0)