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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -slp-vectorizer -S -mtriple=x86_64-apple-macosx10.10.0 -mattr=+sse4.2 | FileCheck %s
define i32 @test(i32* nocapture readonly %p) {
; CHECK-LABEL: @test(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[ARRAYIDX_1:%.*]] = getelementptr inbounds i32, i32* [[P:%.*]], i64 1
; CHECK-NEXT: [[ARRAYIDX_2:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 2
; CHECK-NEXT: [[ARRAYIDX_3:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 3
; CHECK-NEXT: [[ARRAYIDX_4:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 4
; CHECK-NEXT: [[ARRAYIDX_5:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 5
; CHECK-NEXT: [[ARRAYIDX_6:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 6
; CHECK-NEXT: [[ARRAYIDX_7:%.*]] = getelementptr inbounds i32, i32* [[P]], i64 7
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[SUM:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[BIN_EXTRA:%.*]], [[FOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = bitcast i32* [[P]] to <8 x i32>*
; CHECK-NEXT: [[TMP1:%.*]] = load <8 x i32>, <8 x i32>* [[TMP0]], align 4
; CHECK-NEXT: [[TMP2:%.*]] = mul <8 x i32> <i32 42, i32 42, i32 42, i32 42, i32 42, i32 42, i32 42, i32 42>, [[TMP1]]
; CHECK-NEXT: [[ADD:%.*]] = add i32 undef, [[SUM]]
; CHECK-NEXT: [[ADD_1:%.*]] = add i32 undef, [[ADD]]
; CHECK-NEXT: [[ADD_2:%.*]] = add i32 undef, [[ADD_1]]
; CHECK-NEXT: [[ADD_3:%.*]] = add i32 undef, [[ADD_2]]
; CHECK-NEXT: [[ADD_4:%.*]] = add i32 undef, [[ADD_3]]
; CHECK-NEXT: [[ADD_5:%.*]] = add i32 undef, [[ADD_4]]
; CHECK-NEXT: [[ADD_6:%.*]] = add i32 undef, [[ADD_5]]
; CHECK-NEXT: [[RDX_SHUF:%.*]] = shufflevector <8 x i32> [[TMP2]], <8 x i32> undef, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX:%.*]] = add <8 x i32> [[TMP2]], [[RDX_SHUF]]
; CHECK-NEXT: [[RDX_SHUF1:%.*]] = shufflevector <8 x i32> [[BIN_RDX]], <8 x i32> undef, <8 x i32> <i32 2, i32 3, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX2:%.*]] = add <8 x i32> [[BIN_RDX]], [[RDX_SHUF1]]
; CHECK-NEXT: [[RDX_SHUF3:%.*]] = shufflevector <8 x i32> [[BIN_RDX2]], <8 x i32> undef, <8 x i32> <i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
; CHECK-NEXT: [[BIN_RDX4:%.*]] = add <8 x i32> [[BIN_RDX2]], [[RDX_SHUF3]]
; CHECK-NEXT: [[TMP3:%.*]] = extractelement <8 x i32> [[BIN_RDX4]], i32 0
; CHECK-NEXT: [[BIN_EXTRA]] = add i32 [[TMP3]], [[SUM]]
; CHECK-NEXT: [[ADD_7:%.*]] = add i32 undef, [[ADD_6]]
; CHECK-NEXT: br i1 true, label [[FOR_END:%.*]], label [[FOR_BODY]]
; CHECK: for.end:
; CHECK-NEXT: ret i32 [[BIN_EXTRA]]
;
entry:
%arrayidx.1 = getelementptr inbounds i32, i32* %p, i64 1
%arrayidx.2 = getelementptr inbounds i32, i32* %p, i64 2
%arrayidx.3 = getelementptr inbounds i32, i32* %p, i64 3
%arrayidx.4 = getelementptr inbounds i32, i32* %p, i64 4
%arrayidx.5 = getelementptr inbounds i32, i32* %p, i64 5
%arrayidx.6 = getelementptr inbounds i32, i32* %p, i64 6
%arrayidx.7 = getelementptr inbounds i32, i32* %p, i64 7
br label %for.body
for.body:
%sum = phi i32 [ 0, %entry ], [ %add.7, %for.body ]
%tmp = load i32, i32* %p, align 4
%mul = mul i32 %tmp, 42
%add = add i32 %mul, %sum
%tmp5 = load i32, i32* %arrayidx.1, align 4
%mul.1 = mul i32 %tmp5, 42
%add.1 = add i32 %mul.1, %add
%tmp6 = load i32, i32* %arrayidx.2, align 4
%mul.2 = mul i32 %tmp6, 42
%add.2 = add i32 %mul.2, %add.1
%tmp7 = load i32, i32* %arrayidx.3, align 4
%mul.3 = mul i32 %tmp7, 42
%add.3 = add i32 %mul.3, %add.2
%tmp8 = load i32, i32* %arrayidx.4, align 4
%mul.4 = mul i32 %tmp8, 42
%add.4 = add i32 %mul.4, %add.3
%tmp9 = load i32, i32* %arrayidx.5, align 4
%mul.5 = mul i32 %tmp9, 42
%add.5 = add i32 %mul.5, %add.4
%tmp10 = load i32, i32* %arrayidx.6, align 4
%mul.6 = mul i32 %tmp10, 42
%add.6 = add i32 %mul.6, %add.5
%tmp11 = load i32, i32* %arrayidx.7, align 4
%mul.7 = mul i32 %tmp11, 42
%add.7 = add i32 %mul.7, %add.6
br i1 true, label %for.end, label %for.body
for.end:
ret i32 %add.7
}
|
