vitor1001 wrote:
Create PR #144851 to re-apply it.
https://github.com/llvm/llvm-project/pull/143664
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
Artem-B wrote:
It's a C++-11 feature. Tests still include c++98. We do not intend to keep
everything working with c++98 (we already use c++11 in other headers), but we
should not break it either. In this case, you can just enable the new stuff for
c++11 or newer standards.
https://github.com/
vitor1001 wrote:
> It appears to be breaking CUDA tests:
> https://lab.llvm.org/buildbot/#/builders/69/builds/22559
Strange. Do you have any ideas why `decltype` is not working?
https://github.com/llvm/llvm-project/pull/143664
___
cfe-commits mailin
Artem-B wrote:
It appears to be breaking CUDA tests:
https://lab.llvm.org/buildbot/#/builders/69/builds/22559
I'll revert it for now and we'll try again later.
```
[29/988] Building CXX object
External/CUDA/CMakeFiles/math_h-cuda-11.8-c++98-libstdc++-10.dir/math_h.cu.o
FAILED:
External/CUDA/
github-actions[bot] wrote:
@vitor1001 Congratulations on having your first Pull Request (PR) merged into
the LLVM Project!
Your changes will be combined with recent changes from other authors, then
tested by our [build bots](https://lab.llvm.org/buildbot/). If there is a
problem with a buil
https://github.com/Artem-B closed
https://github.com/llvm/llvm-project/pull/143664
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/vitor1001 updated
https://github.com/llvm/llvm-project/pull/143664
>From 539e69459aaf59785e9e835aec4fb0c45bbe6afc Mon Sep 17 00:00:00 2001
From: Vitor Sessak
Date: Wed, 11 Jun 2025 08:21:48 +
Subject: [PATCH] Add missing intrinsics to cuda headers.
LLVM prevents the sm_3
https://github.com/rnk approved this pull request.
@erichkeane, thanks for looking into it, no worries if nobody gets back. I
think we should go ahead and land this in the mean time.
https://github.com/llvm/llvm-project/pull/143664
___
cfe-commits mai
vitor1001 wrote:
> LGTM with one last nit.
Thanks, all temporary variables (`tmp`, `ptr` and `value`) are now prefixed
with __.
https://github.com/llvm/llvm-project/pull/143664
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llv
https://github.com/vitor1001 updated
https://github.com/llvm/llvm-project/pull/143664
>From dd356e979cc50d587ad73661bd7d7679776bc45b Mon Sep 17 00:00:00 2001
From: Vitor Sessak
Date: Wed, 11 Jun 2025 08:21:48 +
Subject: [PATCH] Add missing intrinsics to cuda headers.
LLVM prevents the sm_3
https://github.com/Artem-B approved this pull request.
LGTM with one last nit.
https://github.com/llvm/llvm-project/pull/143664
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
@@ -479,7 +479,291 @@ inline __device__ unsigned __funnelshift_rc(unsigned
low32, unsigned high32,
return ret;
}
-#endif // !defined(__CUDA_ARCH__) || __CUDA_ARCH__ >= 320
+#pragma push_macro("__INTRINSIC_LOAD")
+#define __INTRINSIC_LOAD(__FnName, __AsmOp, __DeclType, __Tmp
vitor1001 wrote:
Thanks, good suggestions, all done.
https://github.com/llvm/llvm-project/pull/143664
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/vitor1001 updated
https://github.com/llvm/llvm-project/pull/143664
>From 079672a23dd5ef832f4fa9b974b3b23b2b48a207 Mon Sep 17 00:00:00 2001
From: Vitor Sessak
Date: Wed, 11 Jun 2025 08:21:48 +
Subject: [PATCH] Add missing intrinsics to cuda headers.
LLVM prevents the sm_3
@@ -479,6 +479,275 @@ inline __device__ unsigned __funnelshift_rc(unsigned
low32, unsigned high32,
return ret;
}
+#define INTRINSIC_LOAD(func_name, asm_op, decl_type, internal_type, asm_type) \
Artem-B wrote:
We have to be careful with the names used in th
https://github.com/Artem-B requested changes to this pull request.
Nice. I like this approach better. There are few more things to polish up, but
it looks good overall.
https://github.com/llvm/llvm-project/pull/143664
___
cfe-commits mailing list
cfe-
@@ -479,6 +479,275 @@ inline __device__ unsigned __funnelshift_rc(unsigned
low32, unsigned high32,
return ret;
}
+#define INTRINSIC_LOAD(func_name, asm_op, decl_type, internal_type, asm_type) \
Artem-B wrote:
Can we merge `INTRINSIC*` and `MINTRINSIC*` mac
https://github.com/Artem-B edited
https://github.com/llvm/llvm-project/pull/143664
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
github-actions[bot] wrote:
:warning: C/C++ code formatter, clang-format found issues in your code.
:warning:
You can test this locally with the following command:
``bash
git-clang-format --diff HEAD~1 HEAD --extensions h --
clang/lib/Headers/__clang_cuda_intrinsics.h
``
https://github.com/vitor1001 updated
https://github.com/llvm/llvm-project/pull/143664
>From f84189201a974dca4cdf29541bfa6877de0056e7 Mon Sep 17 00:00:00 2001
From: Vitor Sessak
Date: Wed, 11 Jun 2025 08:21:48 +
Subject: [PATCH] Add missing intrinsics to cuda headers.
LLVM prevents the sm_3
https://github.com/vitor1001 updated
https://github.com/llvm/llvm-project/pull/143664
>From 78ac958d175568362dc6984486457585d0bb7d6d Mon Sep 17 00:00:00 2001
From: Vitor Sessak
Date: Wed, 11 Jun 2025 08:21:48 +
Subject: [PATCH] Add missing intrinsics to cuda headers.
LLVM prevents the sm_3
erichkeane wrote:
> Erich, is there a good point-of-contact at nvidia who can review CUDA
> intrinsic header changes in the future?
For the most part, we don't have ANYTHING to do with CUDA in clang as far as I
know. I also don't know much about CUDA, but I'll ping an internal slack
channel
rnk wrote:
Erich, is there a good point-of-contact at nvidia who can review CUDA intrinsic
header changes in the future?
https://github.com/llvm/llvm-project/pull/143664
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cg
https://github.com/Artem-B approved this pull request.
https://github.com/llvm/llvm-project/pull/143664
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
https://github.com/vitor1001 ready_for_review
https://github.com/llvm/llvm-project/pull/143664
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
llvmbot wrote:
@llvm/pr-subscribers-backend-x86
@llvm/pr-subscribers-clang
Author: None (vitor1001)
Changes
LLVM prevents the sm_32_intrinsics.hpp header from being included with a
#define __SM_32_INTRINSICS_HPP__. It also provides drop-in replacements of the
functions defined in the CUD
github-actions[bot] wrote:
Thank you for submitting a Pull Request (PR) to the LLVM Project!
This PR will be automatically labeled and the relevant teams will be notified.
If you wish to, you can add reviewers by using the "Reviewers" section on this
page.
If this is not working for you, it
https://github.com/vitor1001 created
https://github.com/llvm/llvm-project/pull/143664
LLVM prevents the sm_32_intrinsics.hpp header from being included with a
#define __SM_32_INTRINSICS_HPP__. It also provides drop-in replacements of the
functions defined in the CUDA header.
One issue is that
28 matches
Mail list logo
