forked from OSchip/llvm-project
b5fb26951a
(a[0] + a[1] + a[2] + a[3]) - (b[0] + b[1] + b[2] +b[3]) --> (a[0] - b[0]) + (a[1] - b[1]) + (a[2] - b[2]) + (a[3] - b[3]) This should be the last step in solving PR43953: https://bugs.llvm.org/show_bug.cgi?id=43953 We started emitting reduction intrinsics with: D80867/ rGe50059f6b6b3 So it's a relatively easy pattern match now to re-order those ops. Also, I have not seen any complaints for the switch to intrinsics yet, so I'll propose to remove the "experimental" tag from the intrinsics soon. Differential Revision: https://reviews.llvm.org/D81491 |
||
|---|---|---|
| .. | ||
| X86 | ||
| 2010-03-22-empty-baseclass.ll | ||
| PR6627.ll | ||
| basic.ll | ||
| bitfield-bittests.ll | ||
| gdce.ll | ||
| globalaa-retained.ll | ||
| inlining-alignment-assumptions.ll | ||
| lifetime-sanitizer.ll | ||
| min-max-abs-cse.ll | ||
| minmax.ll | ||
| reassociate-after-unroll.ll | ||
| rotate.ll | ||
| scev-custom-dl.ll | ||
| scev.ll | ||
| simplifycfg-options.ll | ||
| two-shifts-by-sext.ll | ||
| unsigned-multiply-overflow-check.ll | ||
| vector-trunc.ll | ||