[clang] [CUDA] Change '__activemask' to use '__nvvm_activemask()' (PR #79892)
https://github.com/jhuber6 closed https://github.com/llvm/llvm-project/pull/79892 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
[clang] [CUDA] Change '__activemask' to use '__nvvm_activemask()' (PR #79892)
jhuber6 wrote: Scratch that, I missed `Ui` in the builtin definition. I'll do a quick fix. https://github.com/llvm/llvm-project/pull/79892 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
[clang] [CUDA] Change '__activemask' to use '__nvvm_activemask()' (PR #79892)
jhuber6 wrote:
I've actually encountered some really strange behavior when trying to update
`libc` to use the new intrinsic. The following returns a common 64-bit value to
be compatible with AMDGPU's 64 lane wide mode. When I run this against the test
suite, it fails on tests that specifically check against divergence.
This works
```c++
[[clang::convergent, gnu::noinline]] uint64_t get_lane_mask() {
uint32_t mask;
mask = __nvvm_activemask();
return mask;
}
```
But this does not
```c++
[[clang::convergent, gnu::noinline]] uint64_t get_lane_mask() {
return __nvvm_activemask();
}
```
If I check the PTX, the main difference seems to be the `cvt` instruction,
here's the output respectively.
```asm
.weak .func (.param .b64 func_retval0)
_ZN22__llvm_libc_19_0_0_git3gpu13get_lane_maskEv()
{
.reg .b32 %r<2>;
.reg .b64 %rd<2>;
// %bb.0: // %entry
activemask.b32 %r1;
cvt.u64.u32 %rd1, %r1;
st.param.b64 [func_retval0+0], %rd1;
ret;
}
```
```asm
.weak .func (.param .b64 func_retval0)
_ZN22__llvm_libc_19_0_0_git3gpu13get_lane_maskEv()
{
.reg .b32 %r<2>;
.reg .b64 %rd<2>;
// %bb.0: // %entry
activemask.b32 %r1;
cvt.s64.s32 %rd1, %r1;
st.param.b64 [func_retval0+0], %rd1;
ret;
}
```
So, the difference is that the version that works uses `cvt.u64.u32` while the
version that's broken uses `cvt.s64.s32`. This means that likely this is
returning a "signed" value, and the conversion is treating it like a negative
number when all threads are active. @Artem-B is there a correct way to assert
that this is unsigned so it does the correct thing?
https://github.com/llvm/llvm-project/pull/79892
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
[clang] [CUDA] Change '__activemask' to use '__nvvm_activemask()' (PR #79892)
https://github.com/Artem-B approved this pull request. https://github.com/llvm/llvm-project/pull/79892 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
[clang] [CUDA] Change '__activemask' to use '__nvvm_activemask()' (PR #79892)
https://github.com/jlebar approved this pull request. https://github.com/llvm/llvm-project/pull/79892 ___ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
[clang] [CUDA] Change '__activemask' to use '__nvvm_activemask()' (PR #79892)
llvmbot wrote:
@llvm/pr-subscribers-clang
Author: Joseph Huber (jhuber6)
Changes
Summary:
We recently added builitin support for this function.
---
Full diff: https://github.com/llvm/llvm-project/pull/79892.diff
1 Files Affected:
- (modified) clang/lib/Headers/__clang_cuda_intrinsics.h (+1-3)
``diff
diff --git a/clang/lib/Headers/__clang_cuda_intrinsics.h
b/clang/lib/Headers/__clang_cuda_intrinsics.h
index 3c3948863c1d453..a04e8b6de44d053 100644
--- a/clang/lib/Headers/__clang_cuda_intrinsics.h
+++ b/clang/lib/Headers/__clang_cuda_intrinsics.h
@@ -215,9 +215,7 @@ inline __device__ unsigned int __activemask() {
#if CUDA_VERSION < 9020
return __nvvm_vote_ballot(1);
#else
- unsigned int mask;
- asm volatile("activemask.b32 %0;" : "=r"(mask));
- return mask;
+ return __nvvm_activemask();
#endif
}
``
https://github.com/llvm/llvm-project/pull/79892
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
[clang] [CUDA] Change '__activemask' to use '__nvvm_activemask()' (PR #79892)
https://github.com/jhuber6 created
https://github.com/llvm/llvm-project/pull/79892
Summary:
We recently added builitin support for this function.
>From 5f316d30a179dd21cfadd50d232de622d394ccea Mon Sep 17 00:00:00 2001
From: Joseph Huber
Date: Mon, 29 Jan 2024 14:28:35 -0600
Subject: [PATCH] [CUDA] Change '__activemask' to use '__nvvm_activemask()'
Summary:
We recently added builitin support for this function.
---
clang/lib/Headers/__clang_cuda_intrinsics.h | 4 +---
1 file changed, 1 insertion(+), 3 deletions(-)
diff --git a/clang/lib/Headers/__clang_cuda_intrinsics.h
b/clang/lib/Headers/__clang_cuda_intrinsics.h
index 3c3948863c1d45..a04e8b6de44d05 100644
--- a/clang/lib/Headers/__clang_cuda_intrinsics.h
+++ b/clang/lib/Headers/__clang_cuda_intrinsics.h
@@ -215,9 +215,7 @@ inline __device__ unsigned int __activemask() {
#if CUDA_VERSION < 9020
return __nvvm_vote_ballot(1);
#else
- unsigned int mask;
- asm volatile("activemask.b32 %0;" : "=r"(mask));
- return mask;
+ return __nvvm_activemask();
#endif
}
___
cfe-commits mailing list
cfe-commits@lists.llvm.org
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
