PTX: Add clusterlaunchcontrol (#3589)

Co-authored-by: Allard Hendriksen <[email protected]>

docs/libcudacxx/ptx/instructions.rst

@@ -7,6 +7,7 @@ PTX Instructions
    :maxdepth: 1
 
    instructions/barrier_cluster
+   instructions/clusterlaunchcontrol
    instructions/cp_async_bulk
    instructions/cp_async_bulk_commit_group
    instructions/cp_async_bulk_wait_group

docs/libcudacxx/ptx/instructions/clusterlaunchcontrol.rst

@@ -0,0 +1,11 @@
+.. _libcudacxx-ptx-instructions-clusterlaunchcontrol:
+
+clusterlaunchcontrol
+====================
+
+-  PTX ISA:
+   `clusterlaunchcontrol.try_cancel <https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#parallel-synchronization-and-communication-instructions-clusterlaunchcontrol-try-cancel>`__
+-  PTX ISA:
+   `clusterlaunchcontrol.query_cancel <https://docs.nvidia.com/cuda/parallel-thread-execution/index.html#parallel-synchronization-and-communication-instructions-clusterlaunchcontrol-query-cancel>`__
+
+.. include:: generated/clusterlaunchcontrol.rst

libcudacxx/include/cuda/__ptx/instructions/clusterlaunchcontrol.h

@@ -0,0 +1,37 @@
+// -*- C++ -*-
+//===----------------------------------------------------------------------===//
+//
+// Part of libcu++, the C++ Standard Library for your entire system,
+// under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+// SPDX-FileCopyrightText: Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef _CUDA_PTX_CLUSTERLAUNCHCONTROL_H_
+#define _CUDA_PTX_CLUSTERLAUNCHCONTROL_H_
+
+#include <cuda/std/detail/__config>
+
+#if defined(_CCCL_IMPLICIT_SYSTEM_HEADER_GCC)
+#  pragma GCC system_header
+#elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_CLANG)
+#  pragma clang system_header
+#elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_MSVC)
+#  pragma system_header
+#endif // no system header
+
+#include <cuda/__ptx/ptx_dot_variants.h>
+#include <cuda/__ptx/ptx_helper_functions.h>
+#include <cuda/std/cstdint>
+
+#include <nv/target> // __CUDA_MINIMUM_ARCH__ and friends
+
+_LIBCUDACXX_BEGIN_NAMESPACE_CUDA_PTX
+
+#include <cuda/__ptx/instructions/generated/clusterlaunchcontrol.h>
+
+_LIBCUDACXX_END_NAMESPACE_CUDA_PTX
+
+#endif // _CUDA_PTX_CLUSTERLAUNCHCONTROL_H_

libcudacxx/include/cuda/ptx

@@ -70,6 +70,7 @@
  */
 
 #include <cuda/__ptx/instructions/barrier_cluster.h>
+#include <cuda/__ptx/instructions/clusterlaunchcontrol.h>
 #include <cuda/__ptx/instructions/cp_async_bulk.h>
 #include <cuda/__ptx/instructions/cp_async_bulk_commit_group.h>
 #include <cuda/__ptx/instructions/cp_async_bulk_tensor.h>

libcudacxx/test/libcudacxx/cuda/ptx/ptx.clusterlaunchcontrol.compile.pass.cpp

@@ -0,0 +1,22 @@
+//===----------------------------------------------------------------------===//
+//
+// Part of libcu++, the C++ Standard Library for your entire system,
+// under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+// SPDX-FileCopyrightText: Copyright (c) 2024 NVIDIA CORPORATION & AFFILIATES.
+//
+//===----------------------------------------------------------------------===//
+// UNSUPPORTED: libcpp-has-no-threads
+
+// <cuda/ptx>
+
+#include <cuda/ptx>
+#include <cuda/std/utility>
+
+#include "generated/clusterlaunchcontrol.h"
+
+int main(int, char**)
+{
+  return 0;
+}