[llvm] [NVPTX] Add support for atomic add for bf16 type (PR #89586)
David Majnemer via llvm-commits
llvm-commits at lists.llvm.org
Tue May 7 16:26:59 PDT 2024
majnemer wrote:
I think it is OK for us not to do anything special for `noftz`.
It is a bit tricky to fix it post-hoc because of cases like:
```
x = 0
x += 0x1.02p-126
x += -0x1p-126
```
Here, none of the inputs were subnormal but `x` ends up as `0x1p-133` which is subnormal.
Also, LLVM semantics allow us to return subnormal results instead of flushing.
LGTM.
https://github.com/llvm/llvm-project/pull/89586
More information about the llvm-commits
mailing list