10f6c3e270
We can fold combineConcatVectorOfConcatVectors/combineConcatVectorOfExtracts until after vector legalization
32 lines
1.3 KiB
LLVM
32 lines
1.3 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc < %s -mtriple=i686-- -mattr=avx2 | FileCheck %s --check-prefixes=X86
|
|
; RUN: llc < %s -mtriple=x86_64-- -mattr=avx2 | FileCheck %s --check-prefixes=X64
|
|
|
|
; Make sure this sequence doesn't hang in DAG combine.
|
|
|
|
define <8 x i32> @foo(<8 x i64> %x, <4 x i64> %y) {
|
|
; X86-LABEL: foo:
|
|
; X86: # %bb.0:
|
|
; X86-NEXT: vandps %ymm2, %ymm0, %ymm0
|
|
; X86-NEXT: vandps {{\.?LCPI[0-9]+_[0-9]+}}, %ymm1, %ymm1
|
|
; X86-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
|
|
; X86-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
|
|
; X86-NEXT: retl
|
|
;
|
|
; X64-LABEL: foo:
|
|
; X64: # %bb.0:
|
|
; X64-NEXT: vandps %ymm2, %ymm0, %ymm0
|
|
; X64-NEXT: vextractf128 $1, %ymm0, %xmm2
|
|
; X64-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,2],xmm2[0,2]
|
|
; X64-NEXT: vextractf128 $1, %ymm1, %xmm2
|
|
; X64-NEXT: vshufps {{.*#+}} xmm1 = xmm1[0,2],xmm2[0,2]
|
|
; X64-NEXT: vandps {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm1, %xmm1
|
|
; X64-NEXT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
|
|
; X64-NEXT: retq
|
|
%a = shufflevector <4 x i64> %y, <4 x i64> <i64 12345, i64 67890, i64 13579, i64 24680>, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
|
|
%b = and <8 x i64> %x, %a
|
|
%c = trunc <8 x i64> %b to <8 x i32>
|
|
ret <8 x i32> %c
|
|
}
|
|
|