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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt --passes=slp-vectorizer -mtriple=x86_64-unknown-linux-gnu -o - -S < %s | FileCheck %s
@b = common dso_local global ptr null, align 8
@e = common dso_local global float 0.000000e+00, align 4
@c = common dso_local global float 0.000000e+00, align 4
@g = common dso_local global float 0.000000e+00, align 4
@d = common dso_local global float 0.000000e+00, align 4
@f = common dso_local global float 0.000000e+00, align 4
@a = common dso_local global i32 0, align 4
@h = common dso_local global float 0.000000e+00, align 4
define dso_local void @j() local_unnamed_addr {
; CHECK-LABEL: @j(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = load ptr, ptr @b, align 8
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[TMP0]], i64 4
; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i32, ptr [[TMP0]], i64 12
; CHECK-NEXT: [[TMP1:%.*]] = load i32, ptr @a, align 4
; CHECK-NEXT: [[CONV19:%.*]] = sitofp i32 [[TMP1]] to float
; CHECK-NEXT: [[TMP3:%.*]] = load <2 x i32>, ptr [[ARRAYIDX]], align 4
; CHECK-NEXT: [[TMP5:%.*]] = load <2 x i32>, ptr [[ARRAYIDX1]], align 4
; CHECK-NEXT: [[TMP6:%.*]] = add nsw <2 x i32> [[TMP5]], [[TMP3]]
; CHECK-NEXT: [[TMP7:%.*]] = sitofp <2 x i32> [[TMP6]] to <2 x float>
; CHECK-NEXT: [[TMP8:%.*]] = fmul <2 x float> [[TMP7]], <float 1.000000e+01, float 1.000000e+01>
; CHECK-NEXT: [[TMP9:%.*]] = fsub <2 x float> <float 1.000000e+00, float 0.000000e+00>, [[TMP8]]
; CHECK-NEXT: [[TMP10:%.*]] = shufflevector <2 x float> [[TMP9]], <2 x float> poison, <4 x i32> <i32 1, i32 0, i32 1, i32 0>
; CHECK-NEXT: [[TMP11:%.*]] = extractelement <4 x float> [[TMP10]], i32 1
; CHECK-NEXT: store float [[TMP11]], ptr @g, align 4
; CHECK-NEXT: [[TMP12:%.*]] = fadd <4 x float> [[TMP10]], <float -1.000000e+00, float -1.000000e+00, float 1.000000e+00, float 1.000000e+00>
; CHECK-NEXT: [[TMP13:%.*]] = extractelement <4 x float> [[TMP12]], i32 2
; CHECK-NEXT: store float [[TMP13]], ptr @c, align 4
; CHECK-NEXT: [[TMP14:%.*]] = extractelement <4 x float> [[TMP12]], i32 0
; CHECK-NEXT: store float [[TMP14]], ptr @d, align 4
; CHECK-NEXT: [[TMP15:%.*]] = extractelement <4 x float> [[TMP12]], i32 3
; CHECK-NEXT: store float [[TMP15]], ptr @e, align 4
; CHECK-NEXT: [[TMP16:%.*]] = extractelement <4 x float> [[TMP12]], i32 1
; CHECK-NEXT: store float [[TMP16]], ptr @f, align 4
; CHECK-NEXT: [[TMP17:%.*]] = insertelement <4 x float> <float poison, float -1.000000e+00, float poison, float -1.000000e+00>, float [[CONV19]], i32 0
; CHECK-NEXT: [[TMP18:%.*]] = shufflevector <2 x float> [[TMP9]], <2 x float> poison, <4 x i32> <i32 0, i32 1, i32 poison, i32 poison>
; CHECK-NEXT: [[TMP19:%.*]] = shufflevector <4 x float> [[TMP17]], <4 x float> [[TMP18]], <4 x i32> <i32 0, i32 1, i32 5, i32 3>
; CHECK-NEXT: [[TMP20:%.*]] = fsub <4 x float> [[TMP12]], [[TMP19]]
; CHECK-NEXT: [[TMP21:%.*]] = fadd <4 x float> [[TMP12]], [[TMP19]]
; CHECK-NEXT: [[TMP22:%.*]] = shufflevector <4 x float> [[TMP20]], <4 x float> [[TMP21]], <4 x i32> <i32 0, i32 5, i32 2, i32 7>
; CHECK-NEXT: [[TMP23:%.*]] = fptosi <4 x float> [[TMP22]] to <4 x i32>
; CHECK-NEXT: store <4 x i32> [[TMP23]], ptr [[ARRAYIDX1]], align 4
; CHECK-NEXT: ret void
;
entry:
%0 = load ptr, ptr @b, align 8
%arrayidx = getelementptr inbounds i32, ptr %0, i64 4
%1 = load i32, ptr %arrayidx, align 4
%arrayidx1 = getelementptr inbounds i32, ptr %0, i64 12
%2 = load i32, ptr %arrayidx1, align 4
%add = add nsw i32 %2, %1
%conv = sitofp i32 %add to float
%mul = fmul float %conv, 1.000000e+01
%arrayidx2 = getelementptr inbounds i32, ptr %0, i64 5
%3 = load i32, ptr %arrayidx2, align 4
%arrayidx3 = getelementptr inbounds i32, ptr %0, i64 13
%4 = load i32, ptr %arrayidx3, align 4
%add4 = add nsw i32 %4, %3
%conv5 = sitofp i32 %add4 to float
%mul6 = fmul float %conv5, 1.000000e+01
%sub = fsub float 0.000000e+00, %mul6
%sub7 = fsub float 1.000000e+00, %mul
store float %sub7, ptr @g, align 4
%add9 = fadd float %sub, 1.000000e+00
store float %add9, ptr @c, align 4
%sub10 = fadd float %sub, -1.000000e+00
store float %sub10, ptr @d, align 4
%add11 = fadd float %sub7, 1.000000e+00
store float %add11, ptr @e, align 4
%sub12 = fadd float %sub7, -1.000000e+00
store float %sub12, ptr @f, align 4
%sub13 = fsub float %add9, %sub
%conv14 = fptosi float %sub13 to i32
%arrayidx15 = getelementptr inbounds i32, ptr %0, i64 14
store i32 %conv14, ptr %arrayidx15, align 4
%sub16 = fadd float %add11, -1.000000e+00
%conv17 = fptosi float %sub16 to i32
%arrayidx18 = getelementptr inbounds i32, ptr %0, i64 15
store i32 %conv17, ptr %arrayidx18, align 4
%5 = load i32, ptr @a, align 4
%conv19 = sitofp i32 %5 to float
%sub20 = fsub float %sub10, %conv19
%conv21 = fptosi float %sub20 to i32
store i32 %conv21, ptr %arrayidx1, align 4
%sub23 = fadd float %sub12, -1.000000e+00
%conv24 = fptosi float %sub23 to i32
store i32 %conv24, ptr %arrayidx3, align 4
ret void
}
|
