This commit contains a few changes that had to go in together.
1. Simplify xor/and/or (bitcast(A), bitcast(B)) -> bitcast(op (A,B))
(and also scalar_to_vector).
2. Xor/and/or are indifferent to the swizzle operation (shuffle of one src).
Simplify xor/and/or (shuff(A), shuff(B)) -> shuff(op (A, B))
3. Optimize swizzles of shuffles: shuff(shuff(x, y), undef) -> shuff(x, y).
4. Fix an X86ISelLowering optimization which was very bitcast-sensitive.
Code which was previously compiled to this:
movd (%rsi), %xmm0
movdqa .LCPI0_0(%rip), %xmm2
pshufb %xmm2, %xmm0
movd (%rdi), %xmm1
pshufb %xmm2, %xmm1
pxor %xmm0, %xmm1
pshufb .LCPI0_1(%rip), %xmm1
movd %xmm1, (%rdi)
ret
Now compiles to this:
movl (%rsi), %eax
xorl %eax, (%rdi)
ret
llvm-svn: 153848
2012-04-01 21:31:22 +02:00
|
|
|
; 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
|
|
|
|
|
}
|
2012-04-02 09:11:12 +02:00
|
|
|
|
|
|
|
|
; 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
|
|
|
|
|
}
|
2012-04-03 09:39:36 +02:00
|
|
|
|
|
|
|
|
; 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
|
|
|
|
|
}
|
2012-04-07 23:19:08 +02:00
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
; 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
|
|
|
|
|
}
|
