llvm/test/CodeGen/X86/SwizzleShuff.ll
Nadav Rotem d16c8d0d33 1. Remove the part of r153848 which optimizes shuffle-of-shuffle into a new
shuffle node because it could introduce new shuffle nodes that were not
   supported efficiently by the target.

2. Add a more restrictive shuffle-of-shuffle optimization for cases where the
   second shuffle reverses the transformation of the first shuffle.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@154266 91177308-0d34-0410-b5e6-96231b3b80d8
2012-04-07 21:19:08 +00:00

69 lines
2.0 KiB
LLVM

; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck %s
; Check that we perform a scalar XOR on i32.
; CHECK: pull_bitcast
; CHECK: xorl
; CHECK: ret
define void @pull_bitcast (<4 x i8>* %pA, <4 x i8>* %pB) {
%A = load <4 x i8>* %pA
%B = load <4 x i8>* %pB
%C = xor <4 x i8> %A, %B
store <4 x i8> %C, <4 x i8>* %pA
ret void
}
; CHECK: multi_use_swizzle
; CHECK: mov
; CHECK-NEXT: shuf
; CHECK-NEXT: shuf
; CHECK-NEXT: shuf
; CHECK-NEXT: xor
; CHECK-NEXT: ret
define <4 x i32> @multi_use_swizzle (<4 x i32>* %pA, <4 x i32>* %pB) {
%A = load <4 x i32>* %pA
%B = load <4 x i32>* %pB
%S = shufflevector <4 x i32> %A, <4 x i32> %B, <4 x i32> <i32 1, i32 1, i32 5, i32 6>
%S1 = shufflevector <4 x i32> %S, <4 x i32> undef, <4 x i32> <i32 1, i32 3, i32 2, i32 2>
%S2 = shufflevector <4 x i32> %S, <4 x i32> undef, <4 x i32> <i32 2, i32 1, i32 0, i32 2>
%R = xor <4 x i32> %S1, %S2
ret <4 x i32> %R
}
; CHECK: pull_bitcast2
; CHECK: xorl
; CHECK: ret
define <4 x i8> @pull_bitcast2 (<4 x i8>* %pA, <4 x i8>* %pB, <4 x i8>* %pC) {
%A = load <4 x i8>* %pA
store <4 x i8> %A, <4 x i8>* %pC
%B = load <4 x i8>* %pB
%C = xor <4 x i8> %A, %B
store <4 x i8> %C, <4 x i8>* %pA
ret <4 x i8> %C
}
; CHECK: reverse_1
; CHECK-NOT: shuf
; CHECK: ret
define <4 x i32> @reverse_1 (<4 x i32>* %pA, <4 x i32>* %pB) {
%A = load <4 x i32>* %pA
%B = load <4 x i32>* %pB
%S = shufflevector <4 x i32> %A, <4 x i32> %B, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
%S1 = shufflevector <4 x i32> %S, <4 x i32> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
ret <4 x i32> %S1
}
; CHECK: no_reverse_shuff
; CHECK: shuf
; CHECK: ret
define <4 x i32> @no_reverse_shuff (<4 x i32>* %pA, <4 x i32>* %pB) {
%A = load <4 x i32>* %pA
%B = load <4 x i32>* %pB
%S = shufflevector <4 x i32> %A, <4 x i32> %B, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
%S1 = shufflevector <4 x i32> %S, <4 x i32> undef, <4 x i32> <i32 3, i32 2, i32 3, i32 2>
ret <4 x i32> %S1
}