[llvm-bugs] [Bug 39709] [X86] Suboptimal code in vXi8 vector multiply reduction

[via llvm-bugs]

https://bugs.llvm.org/show_bug.cgi?id=39709

Simon Pilgrim <llvm-dev at redking.me.uk> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|CONFIRMED                   |RESOLVED
 Fixed By Commit(s)|                            |47321c311bdbe0145b9bf45d822
                   |                            |185c37b19fa50
         Resolution|---                         |FIXED

--- Comment #3 from Simon Pilgrim <llvm-dev at redking.me.uk> ---
Fixed in rG47321c311bdbe0145b9bf45d822185c37b19fa50 - we were able to get quite
close with SimplifyDemandedBits/SimplifyDemandedVectorElts + shuffle combining
but just a custom promotion to a vXi16 reduction worked best in the end.

-- 
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/20201214/19f41cb8/attachment.html>