1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx -x86-experimental-vector-widening-legalization | FileCheck %s
; Check that we perform a scalar XOR on i32.
define void @pull_bitcast(<4 x i8>* %pA, <4 x i8>* %pB) {
; CHECK-LABEL: pull_bitcast:
; CHECK: # %bb.0:
; CHECK-NEXT: movl (%rsi), %eax
; CHECK-NEXT: xorl %eax, (%rdi)
; CHECK-NEXT: retq
%A = load <4 x i8>, <4 x i8>* %pA
%B = load <4 x i8>, <4 x i8>* %pB
%C = xor <4 x i8> %A, %B
store <4 x i8> %C, <4 x i8>* %pA
ret void
}
define <4 x i32> @multi_use_swizzle(<4 x i32>* %pA, <4 x i32>* %pB) {
; CHECK-LABEL: multi_use_swizzle:
; CHECK: # %bb.0:
; CHECK-NEXT: vmovaps (%rdi), %xmm0
; CHECK-NEXT: vshufps {{.*#+}} xmm0 = xmm0[1,1],mem[1,2]
; CHECK-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[1,3,2,2]
; CHECK-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,1,0,2]
; CHECK-NEXT: vxorps %xmm0, %xmm1, %xmm0
; CHECK-NEXT: retq
%A = load <4 x i32>, <4 x i32>* %pA
%B = load <4 x i32>, <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
}
define <4 x i8> @pull_bitcast2(<4 x i8>* %pA, <4 x i8>* %pB, <4 x i8>* %pC) {
; CHECK-LABEL: pull_bitcast2:
; CHECK: # %bb.0:
; CHECK-NEXT: movl (%rdi), %eax
; CHECK-NEXT: movl %eax, (%rdx)
; CHECK-NEXT: xorl (%rsi), %eax
; CHECK-NEXT: vmovd %eax, %xmm0
; CHECK-NEXT: movl %eax, (%rdi)
; CHECK-NEXT: retq
%A = load <4 x i8>, <4 x i8>* %pA
store <4 x i8> %A, <4 x i8>* %pC
%B = load <4 x i8>, <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
}
define <4 x i32> @reverse_1(<4 x i32>* %pA, <4 x i32>* %pB) {
; CHECK-LABEL: reverse_1:
; CHECK: # %bb.0:
; CHECK-NEXT: vmovaps (%rdi), %xmm0
; CHECK-NEXT: retq
%A = load <4 x i32>, <4 x i32>* %pA
%B = load <4 x i32>, <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
}
define <4 x i32> @no_reverse_shuff(<4 x i32>* %pA, <4 x i32>* %pB) {
; CHECK-LABEL: no_reverse_shuff:
; CHECK: # %bb.0:
; CHECK-NEXT: vpermilps {{.*#+}} xmm0 = mem[2,3,2,3]
; CHECK-NEXT: retq
%A = load <4 x i32>, <4 x i32>* %pA
%B = load <4 x i32>, <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
}
|
