Similar to what we already do for add/sub + saturation variants. Scalar support will be added in a future patch covering the other variants at the same time. Alive2: https://alive2.llvm.org/ce/z/rBDrNE Fixes #69080
39 lines
1.4 KiB
LLVM
39 lines
1.4 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
|
|
; RUN: llc < %s -mtriple=x86_64-- | FileCheck %s --check-prefixes=SSE
|
|
; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx2 | FileCheck %s --check-prefixes=AVX
|
|
; RUN: llc < %s -mtriple=x86_64-- -mattr=+avx512f | FileCheck %s --check-prefixes=AVX
|
|
|
|
define { <4 x i1>, <4 x i1> } @uaddo(<4 x i1> %a) {
|
|
; SSE-LABEL: uaddo:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: movaps %xmm0, %xmm1
|
|
; SSE-NEXT: xorps %xmm0, %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: uaddo:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vmovaps %xmm0, %xmm1
|
|
; AVX-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
%f = call { <4 x i1>, <4 x i1> } @llvm.uadd.with.overflow.v4i1(<4 x i1> %a, <4 x i1> %a)
|
|
ret { <4 x i1>, <4 x i1> } %f
|
|
}
|
|
declare { <4 x i1>, <4 x i1> } @llvm.uadd.with.overflow.v4i1(<4 x i1>, <4 x i1>)
|
|
|
|
define { <4 x i1>, <4 x i1> } @saddo(<4 x i1> %a) {
|
|
; SSE-LABEL: saddo:
|
|
; SSE: # %bb.0:
|
|
; SSE-NEXT: movaps %xmm0, %xmm1
|
|
; SSE-NEXT: xorps %xmm0, %xmm0
|
|
; SSE-NEXT: retq
|
|
;
|
|
; AVX-LABEL: saddo:
|
|
; AVX: # %bb.0:
|
|
; AVX-NEXT: vmovaps %xmm0, %xmm1
|
|
; AVX-NEXT: vxorps %xmm0, %xmm0, %xmm0
|
|
; AVX-NEXT: retq
|
|
%f = call { <4 x i1>, <4 x i1> } @llvm.sadd.with.overflow.v4i1(<4 x i1> %a, <4 x i1> %a)
|
|
ret { <4 x i1>, <4 x i1> } %f
|
|
}
|
|
declare { <4 x i1>, <4 x i1> } @llvm.sadd.with.overflow.v4i1(<4 x i1>, <4 x i1>)
|