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
| ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -basicaa -slp-vectorizer -dce -S -mtriple=i386-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s
target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128-n8:16:32-S128"
target triple = "i386-apple-macosx10.9.0"
; We disable the vectorization of <3 x float> for now
; float foo(float *A) {
;
; float R = A[0];
; float G = A[1];
; float B = A[2];
; for (int i=0; i < 121; i+=3) {
; R+=A[i+0]*7;
; G+=A[i+1]*8;
; B+=A[i+2]*9;
; }
;
; return R+G+B;
; }
define float @foo(float* nocapture readonly %A) {
; CHECK-LABEL: @foo(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = load float, float* [[A:%.*]], align 4
; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds float, float* [[A]], i64 1
; CHECK-NEXT: [[TMP1:%.*]] = load float, float* [[ARRAYIDX1]], align 4
; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds float, float* [[A]], i64 2
; CHECK-NEXT: [[TMP2:%.*]] = load float, float* [[ARRAYIDX2]], align 4
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: [[TMP3:%.*]] = phi float [ [[TMP0]], [[ENTRY:%.*]] ], [ [[DOTPRE:%.*]], [[FOR_BODY_FOR_BODY_CRIT_EDGE:%.*]] ]
; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, [[ENTRY]] ], [ [[INDVARS_IV_NEXT:%.*]], [[FOR_BODY_FOR_BODY_CRIT_EDGE]] ]
; CHECK-NEXT: [[B_032:%.*]] = phi float [ [[TMP2]], [[ENTRY]] ], [ [[ADD14:%.*]], [[FOR_BODY_FOR_BODY_CRIT_EDGE]] ]
; CHECK-NEXT: [[G_031:%.*]] = phi float [ [[TMP1]], [[ENTRY]] ], [ [[ADD9:%.*]], [[FOR_BODY_FOR_BODY_CRIT_EDGE]] ]
; CHECK-NEXT: [[R_030:%.*]] = phi float [ [[TMP0]], [[ENTRY]] ], [ [[ADD4:%.*]], [[FOR_BODY_FOR_BODY_CRIT_EDGE]] ]
; CHECK-NEXT: [[MUL:%.*]] = fmul float [[TMP3]], 7.000000e+00
; CHECK-NEXT: [[ADD4]] = fadd float [[R_030]], [[MUL]]
; CHECK-NEXT: [[TMP4:%.*]] = add nsw i64 [[INDVARS_IV]], 1
; CHECK-NEXT: [[ARRAYIDX7:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[TMP4]]
; CHECK-NEXT: [[TMP5:%.*]] = load float, float* [[ARRAYIDX7]], align 4
; CHECK-NEXT: [[MUL8:%.*]] = fmul float [[TMP5]], 8.000000e+00
; CHECK-NEXT: [[ADD9]] = fadd float [[G_031]], [[MUL8]]
; CHECK-NEXT: [[TMP6:%.*]] = add nsw i64 [[INDVARS_IV]], 2
; CHECK-NEXT: [[ARRAYIDX12:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[TMP6]]
; CHECK-NEXT: [[TMP7:%.*]] = load float, float* [[ARRAYIDX12]], align 4
; CHECK-NEXT: [[MUL13:%.*]] = fmul float [[TMP7]], 9.000000e+00
; CHECK-NEXT: [[ADD14]] = fadd float [[B_032]], [[MUL13]]
; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add i64 [[INDVARS_IV]], 3
; CHECK-NEXT: [[TMP8:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[TMP8]], 121
; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY_FOR_BODY_CRIT_EDGE]], label [[FOR_END:%.*]]
; CHECK: for.body.for.body_crit_edge:
; CHECK-NEXT: [[ARRAYIDX3_PHI_TRANS_INSERT:%.*]] = getelementptr inbounds float, float* [[A]], i64 [[INDVARS_IV_NEXT]]
; CHECK-NEXT: [[DOTPRE]] = load float, float* [[ARRAYIDX3_PHI_TRANS_INSERT]], align 4
; CHECK-NEXT: br label [[FOR_BODY]]
; CHECK: for.end:
; CHECK-NEXT: [[ADD16:%.*]] = fadd float [[ADD4]], [[ADD9]]
; CHECK-NEXT: [[ADD17:%.*]] = fadd float [[ADD16]], [[ADD14]]
; CHECK-NEXT: ret float [[ADD17]]
;
entry:
%0 = load float, float* %A, align 4
%arrayidx1 = getelementptr inbounds float, float* %A, i64 1
%1 = load float, float* %arrayidx1, align 4
%arrayidx2 = getelementptr inbounds float, float* %A, i64 2
%2 = load float, float* %arrayidx2, align 4
br label %for.body
for.body: ; preds = %for.body.for.body_crit_edge, %entry
%3 = phi float [ %0, %entry ], [ %.pre, %for.body.for.body_crit_edge ]
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body.for.body_crit_edge ]
%B.032 = phi float [ %2, %entry ], [ %add14, %for.body.for.body_crit_edge ]
%G.031 = phi float [ %1, %entry ], [ %add9, %for.body.for.body_crit_edge ]
%R.030 = phi float [ %0, %entry ], [ %add4, %for.body.for.body_crit_edge ]
%mul = fmul float %3, 7.000000e+00
%add4 = fadd float %R.030, %mul
%4 = add nsw i64 %indvars.iv, 1
%arrayidx7 = getelementptr inbounds float, float* %A, i64 %4
%5 = load float, float* %arrayidx7, align 4
%mul8 = fmul float %5, 8.000000e+00
%add9 = fadd float %G.031, %mul8
%6 = add nsw i64 %indvars.iv, 2
%arrayidx12 = getelementptr inbounds float, float* %A, i64 %6
%7 = load float, float* %arrayidx12, align 4
%mul13 = fmul float %7, 9.000000e+00
%add14 = fadd float %B.032, %mul13
%indvars.iv.next = add i64 %indvars.iv, 3
%8 = trunc i64 %indvars.iv.next to i32
%cmp = icmp slt i32 %8, 121
br i1 %cmp, label %for.body.for.body_crit_edge, label %for.end
for.body.for.body_crit_edge: ; preds = %for.body
%arrayidx3.phi.trans.insert = getelementptr inbounds float, float* %A, i64 %indvars.iv.next
%.pre = load float, float* %arrayidx3.phi.trans.insert, align 4
br label %for.body
for.end: ; preds = %for.body
%add16 = fadd float %add4, %add9
%add17 = fadd float %add16, %add14
ret float %add17
}
|