13d04fa560
Always match ABD patterns pre-legalization, and use TargetLowering::expandABD to expand again during legalization. abdu(lhs, rhs) -> sub(xor(sub(lhs, rhs), usub_overflow(lhs, rhs)), usub_overflow(lhs, rhs)) Alive2: https://alive2.llvm.org/ce/z/dVdMyv REAPPLIED: Fix regression issue with "abs(ext(x) - ext(y)) -> zext(abd(x, y))" fold failing after type legalization
20 lines
721 B
LLVM
20 lines
721 B
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 2
|
|
; RUN: llc -verify-machineinstrs -mtriple=powerpc64le -mcpu=pwr9 < %s | FileCheck %s
|
|
|
|
; Widen to <16 x i8>
|
|
define <12 x i8> @zext_abdu(<12 x i8> %a, <12 x i8> %b) {
|
|
; CHECK-LABEL: zext_abdu:
|
|
; CHECK: # %bb.0: # %entry
|
|
; CHECK-NEXT: vabsdub 2, 2, 3
|
|
; CHECK-NEXT: blr
|
|
entry:
|
|
%aa = zext <12 x i8> %a to <12 x i32>
|
|
%bb = zext <12 x i8> %b to <12 x i32>
|
|
%s = sub nsw <12 x i32> %aa, %bb
|
|
%c = icmp slt <12 x i32> %s, zeroinitializer
|
|
%ss = sub nsw <12 x i32> zeroinitializer, %s
|
|
%sel = select <12 x i1> %c, <12 x i32> %ss, <12 x i32> %s
|
|
%ret = trunc <12 x i32> %sel to <12 x i8>
|
|
ret <12 x i8> %ret
|
|
}
|