You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
See #96479: the uniform path for fadd/fsub was disabled because it can return the wrong value in the first active lane of the result in the presence of NaNs and signed zeros.
We should find a way to fix and re-enable it, e.g. by overwriting the first active lane of %y * +0.0 with -0.0. And maybe this can be optimized more if certain values are known not to be zero or nan.
The text was updated successfully, but these errors were encountered:
See #96479: the uniform path for fadd/fsub was disabled because it can return the wrong value in the first active lane of the result in the presence of NaNs and signed zeros.
We should find a way to fix and re-enable it, e.g. by overwriting the first active lane of %y * +0.0 with -0.0. And maybe this can be optimized more if certain values are known not to be zero or nan.
…lt (llvm#97604)
Fix various problems to do with the first active lane of the result of
optimized fp atomics, as explained in the comment.
Fixesllvm#97554
aaryanshukla
pushed a commit
to aaryanshukla/llvm-project
that referenced
this issue
Jul 16, 2024
…lt (llvm#97604)
Fix various problems to do with the first active lane of the result of
optimized fp atomics, as explained in the comment.
Fixesllvm#97554
See #96479: the uniform path for fadd/fsub was disabled because it can return the wrong value in the first active lane of the result in the presence of NaNs and signed zeros.
We should find a way to fix and re-enable it, e.g. by overwriting the first active lane of
%y * +0.0
with -0.0. And maybe this can be optimized more if certain values are known not to be zero or nan.The text was updated successfully, but these errors were encountered: