llvm-project/llvm/test/CodeGen/AArch64/arm64-neon-vector-shuffle-e...

34 lines
1.4 KiB
LLVM

; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -verify-machineinstrs -mtriple=aarch64-unknown-linux -o - | FileCheck %s
define void @test(i32* %p1, i32* %p2) {
; CHECK-LABEL: test:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #3
; CHECK-NEXT: mov w9, #1
; CHECK-NEXT: str w8, [x0]
; CHECK-NEXT: str w9, [x1]
; CHECK-NEXT: ret
%tmp = shufflevector <1 x i32> <i32 1>, <1 x i32> undef, <3 x i32> <i32 0, i32 undef, i32 undef>
%tmp2 = shufflevector <3 x i32> <i32 2, i32 3, i32 4>, <3 x i32> %tmp, <3 x i32> <i32 0, i32 1, i32 3>
%tmp3 = shufflevector <3 x i32> %tmp2, <3 x i32> undef, <6 x i32> <i32 0, i32 1, i32 2, i32 undef, i32 undef, i32 undef>
%tmp4 = shufflevector <6 x i32> undef, <6 x i32> %tmp3, <9 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8>
%tmp6 = extractelement <9 x i32> %tmp4, i32 7
%tmp8 = extractelement <9 x i32> %tmp4, i32 8
store i32 %tmp6, i32* %p1, align 4
store i32 %tmp8, i32* %p2, align 4
ret void
}
; Test case from PR41951
define <4 x i32> @widen_shuffles_reduced(<3 x i32> %x, <3 x i32> %y) {
; CHECK-LABEL: widen_shuffles_reduced:
; CHECK: // %bb.0:
; CHECK-NEXT: zip1 v2.4s, v0.4s, v1.4s
; CHECK-NEXT: zip1 v0.4s, v1.4s, v0.4s
; CHECK-NEXT: ext v0.16b, v0.16b, v2.16b, #8
; CHECK-NEXT: ret
%s3 = shufflevector <3 x i32> %y, <3 x i32> %x, <4 x i32> <i32 1, i32 4, i32 3, i32 0>
ret <4 x i32> %s3
}