avx1-logical-load-folding.ll
4.32 KB
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
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -O3 -disable-peephole -mtriple=i686-apple-macosx10.9.0 -mcpu=corei7-avx -mattr=+avx | FileCheck %s --check-prefix=X86
; RUN: llc < %s -O3 -disable-peephole -mtriple=x86_64-apple-macosx10.9.0 -mcpu=corei7-avx -mattr=+avx | FileCheck %s --check-prefix=X64
; Function Attrs: nounwind ssp uwtable
define void @test1(float* %A, float* %C) #0 {
; X86-LABEL: test1:
; X86: ## %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X86-NEXT: vandps LCPI0_0, %xmm0, %xmm0
; X86-NEXT: vmovss %xmm0, (%eax)
; X86-NEXT: retl
;
; X64-LABEL: test1:
; X64: ## %bb.0:
; X64-NEXT: vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X64-NEXT: vandps {{.*}}(%rip), %xmm0, %xmm0
; X64-NEXT: vmovss %xmm0, (%rsi)
; X64-NEXT: retq
%tmp1 = bitcast float* %A to <8 x float>*
%tmp2 = load <8 x float>, <8 x float>* %tmp1, align 32
%tmp3 = bitcast <8 x float> %tmp2 to <8 x i32>
%tmp4 = and <8 x i32> %tmp3, <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
%tmp5 = bitcast <8 x i32> %tmp4 to <8 x float>
%tmp6 = extractelement <8 x float> %tmp5, i32 0
store float %tmp6, float* %C
ret void
}
; Function Attrs: nounwind ssp uwtable
define void @test2(float* %A, float* %C) #0 {
; X86-LABEL: test2:
; X86: ## %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: vmovaps (%ecx), %xmm0
; X86-NEXT: vorps LCPI1_0, %xmm0, %xmm0
; X86-NEXT: vmovss %xmm0, (%eax)
; X86-NEXT: retl
;
; X64-LABEL: test2:
; X64: ## %bb.0:
; X64-NEXT: vmovaps (%rdi), %xmm0
; X64-NEXT: vorps {{.*}}(%rip), %xmm0, %xmm0
; X64-NEXT: vmovss %xmm0, (%rsi)
; X64-NEXT: retq
%tmp1 = bitcast float* %A to <8 x float>*
%tmp2 = load <8 x float>, <8 x float>* %tmp1, align 32
%tmp3 = bitcast <8 x float> %tmp2 to <8 x i32>
%tmp4 = or <8 x i32> %tmp3, <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
%tmp5 = bitcast <8 x i32> %tmp4 to <8 x float>
%tmp6 = extractelement <8 x float> %tmp5, i32 0
store float %tmp6, float* %C
ret void
}
; Function Attrs: nounwind ssp uwtable
define void @test3(float* %A, float* %C) #0 {
; X86-LABEL: test3:
; X86: ## %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: vmovaps (%ecx), %xmm0
; X86-NEXT: vxorps LCPI2_0, %xmm0, %xmm0
; X86-NEXT: vmovss %xmm0, (%eax)
; X86-NEXT: retl
;
; X64-LABEL: test3:
; X64: ## %bb.0:
; X64-NEXT: vmovaps (%rdi), %xmm0
; X64-NEXT: vxorps {{.*}}(%rip), %xmm0, %xmm0
; X64-NEXT: vmovss %xmm0, (%rsi)
; X64-NEXT: retq
%tmp1 = bitcast float* %A to <8 x float>*
%tmp2 = load <8 x float>, <8 x float>* %tmp1, align 32
%tmp3 = bitcast <8 x float> %tmp2 to <8 x i32>
%tmp4 = xor <8 x i32> %tmp3, <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
%tmp5 = bitcast <8 x i32> %tmp4 to <8 x float>
%tmp6 = extractelement <8 x float> %tmp5, i32 0
store float %tmp6, float* %C
ret void
}
define void @test4(float* %A, float* %C) #0 {
; X86-LABEL: test4:
; X86: ## %bb.0:
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: vmovaps (%ecx), %xmm0
; X86-NEXT: vandnps LCPI3_0, %xmm0, %xmm0
; X86-NEXT: vmovss %xmm0, (%eax)
; X86-NEXT: retl
;
; X64-LABEL: test4:
; X64: ## %bb.0:
; X64-NEXT: vmovaps (%rdi), %xmm0
; X64-NEXT: vandnps {{.*}}(%rip), %xmm0, %xmm0
; X64-NEXT: vmovss %xmm0, (%rsi)
; X64-NEXT: retq
%tmp1 = bitcast float* %A to <8 x float>*
%tmp2 = load <8 x float>, <8 x float>* %tmp1, align 32
%tmp3 = bitcast <8 x float> %tmp2 to <8 x i32>
%tmp4 = xor <8 x i32> %tmp3, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
%tmp5 = and <8 x i32> %tmp4, <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
%tmp6 = bitcast <8 x i32> %tmp5 to <8 x float>
%tmp7 = extractelement <8 x float> %tmp6, i32 0
store float %tmp7, float * %C
ret void
}