Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add _CCCL_BUILTIN_PREFETCH #3433

Merged
merged 6 commits into from
Jan 21, 2025
Merged

Add _CCCL_BUILTIN_PREFETCH #3433

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
5cacce4
add _CCCL_BUILTIN_PREFETCH
fbusato Jan 17, 2025
3a8b8a4
Merge branch 'main' into builtin-prefetch
fbusato Jan 21, 2025
4bd87f2
Update libcudacxx/test/libcudacxx/libcxx/macros/prefetch.compile.pass…
fbusato Jan 21, 2025
f99edc5
Update libcudacxx/include/cuda/std/__cccl/builtin.h
fbusato Jan 21, 2025
76c5b3b
Update libcudacxx/include/cuda/std/__cccl/builtin.h
fbusato Jan 21, 2025
c970ef3
improve testing
fbusato Jan 21, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 9 additions & 7 deletions docs/cccl_development/macro.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -264,13 +264,15 @@ Usage example:

**Portable Builtin Macros**:

+-----------------------------+--------------------------------------------+
| ``_CCCL_UNREACHABLE()`` | Portable ``__builtin_unreachable()`` |
+-----------------------------+--------------------------------------------+
| ``_CCCL_BUILTIN_ASSUME(X)`` | Portable ``__builtin_assume(X)`` |
+-----------------------------+--------------------------------------------+
| ``_CCCL_BUILTIN_EXPECT(X)`` | Portable ``__builtin_expected(X)`` |
+-----------------------------+--------------------------------------------+
+---------------------------------------+--------------------------------------------+
| ``_CCCL_UNREACHABLE()`` | Portable ``__builtin_unreachable()`` |
+---------------------------------------+--------------------------------------------+
| ``_CCCL_BUILTIN_ASSUME(X)`` | Portable ``__builtin_assume(X)`` |
+---------------------------------------+--------------------------------------------+
| ``_CCCL_BUILTIN_EXPECT(X)`` | Portable ``__builtin_expected(X)`` |
+---------------------------------------+--------------------------------------------+
| ``_CCCL_BUILTIN_PREFETCH(X[, Y, Z])`` | Portable ``__builtin_prefetch(X, Y, Z)`` |
+---------------------------------------+--------------------------------------------+

**Portable Keyword Macros**

Expand Down
6 changes: 6 additions & 0 deletions libcudacxx/include/cuda/std/__cccl/builtin.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -111,6 +111,12 @@
NV_IF_ELSE_TARGET(NV_IS_DEVICE, (__builtin_assume(__VA_ARGS__);), (__assume(__VA_ARGS__);))
#endif // _CCCL_CHECK_BUILTIN(builtin_assume)

#if _CCCL_CHECK_BUILTIN(builtin_assume) || _CCCL_COMPILER(CLANG) || _CCCL_COMPILER(GCC) || _CCCL_COMPILER(NVHPC)
# define _CCCL_BUILTIN_PREFETCH(...) NV_IF_TARGET(NV_IS_HOST, __builtin_prefetch(__VA_ARGS__);)
#else
# define _CCCL_BUILTIN_PREFETCH(...)
#endif // _CCCL_CHECK_BUILTIN(builtin_assume)

// NVCC prior to 11.2 cannot handle __builtin_assume
#if _CCCL_CUDACC_BELOW(11, 2)
# undef _CCCL_BUILTIN_ASSUME
Expand Down
20 changes: 20 additions & 0 deletions libcudacxx/test/libcudacxx/libcxx/macros/prefetch.compile.pass.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
//===----------------------------------------------------------------------===//
//
// Part of the LLVM Project, 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) 2023 NVIDIA CORPORATION & AFFILIATES.
//
//===----------------------------------------------------------------------===//

#include <cuda/std/detail/__config>

#include <test_macros.h>

int main(int, char**)
{
int memory[8];
_CCCL_BUILTIN_PREFETCH(memory, 0, 1);
unused(memory);
return 0;
}
Loading