[PATCH] D48347: [X86] Update fast-isel tests for changes from D48346.

[Craig Topper via Phabricator via llvm-commits]

craig.topper created this revision.
craig.topper added a reviewer: RKSimon.

The new IR fixes a mismatch in the final extractelement for the i32 intrinsics. Previously we extracted a 64-bit element even though we only wanted 32 bits.

SimplifyDemandedElts isn't able to make FP elements undef now and the shuffle mask I used prevents the use of horizontal add we had before. Not sure we should have been using horizontal add anyway. It's implemented on Intel with two port 5 shuffles and an add. So we have on less shuffle now, but an additional instruction to decode.


Repository:
  rL LLVM

https://reviews.llvm.org/D48347

Files:
  test/CodeGen/X86/avx512-intrinsics-fast-isel.ll

-------------- next part --------------
A non-text attachment was scrubbed...
Name: D48347.152023.patch
Type: text/x-patch
Size: 42398 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20180620/02789248/attachment-0001.bin>