[llvm-bugs] [Bug 36982] llvm.experimental.vector.reduce.{fmin, fmax} incorrect for vectors with NaN in the last place

[via llvm-bugs]

https://bugs.llvm.org/show_bug.cgi?id=36982

Sanjay Patel <spatel+llvm at rotateright.com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|NEW                         |RESOLVED
         Resolution|---                         |FIXED
 Fixed By Commit(s)|                            |3a8ea86

--- Comment #4 from Sanjay Patel <spatel+llvm at rotateright.com> ---
Yes, the semantics are specified now (we chose minnum/maxnum) and default
lowering  implemented with:
https://reviews.llvm.org/D87391

That's what we see in the x86 asm in comment 3 - the hardware instructions use
the fcmp+select semantics, so we need to check for NAN and blend those away if
present.

-- 
You are receiving this mail because:
You are on the CC list for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.llvm.org/pipermail/llvm-bugs/attachments/20200919/431554ac/attachment.html>