[llvm-bugs] [Bug 47506] New: [X86][AVX512] Convert _mm_reduce_* intrinsics to emit llvm.reduction intrinsics in IR

[via llvm-bugs]

https://bugs.llvm.org/show_bug.cgi?id=47506

            Bug ID: 47506
           Summary: [X86][AVX512] Convert _mm_reduce_* intrinsics to emit
                    llvm.reduction intrinsics in IR
           Product: clang
           Version: unspecified
          Hardware: PC
                OS: Windows NT
            Status: NEW
          Severity: enhancement
          Priority: P
         Component: Headers
          Assignee: unassignedclangbugs at nondot.org
          Reporter: llvm-dev at redking.me.uk
                CC: craig.topper at gmail.com, llvm-bugs at lists.llvm.org,
                    richard-llvm at metafoo.co.uk
        Depends on: 47505

The _mm_reduce_*/_mm_mask_reduce_* style AVX512 intrinsics currently expand to
a  reduction code sequence in the header.

Now that we are close to handling llvm.reduction intrinsics in IR, we should be
able to emit these IR intrinsics directly instead of relying on a later pass to
recognise the pattern.


Referenced Bugs:

https://bugs.llvm.org/show_bug.cgi?id=47505
[Bug 47505] Make reduction intrinsics non-experimental
-- 
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/20200912/c99aef65/attachment.html>