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
|
; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7 -S | FileCheck %s
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
; Function Attrs: nounwind uwtable
define void @test1(float* noalias nocapture %a, float* noalias nocapture readonly %b) #0 {
entry:
br label %for.body
; CHECK-LABEL: @test1
; CHECK: vector.body:
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: for.body:
; CHECK: ret void
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%arrayidx = getelementptr inbounds float* %b, i64 %indvars.iv
%0 = load float* %arrayidx, align 4
%cmp1 = fcmp ogt float %0, 1.000000e+02
tail call void @llvm.assume(i1 %cmp1)
%add = fadd float %0, 1.000000e+00
%arrayidx5 = getelementptr inbounds float* %a, i64 %indvars.iv
store float %add, float* %arrayidx5, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv, 1599
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
; Function Attrs: nounwind
declare void @llvm.assume(i1) #1
attributes #0 = { nounwind uwtable }
attributes #1 = { nounwind }
%struct.data = type { float*, float* }
; Function Attrs: nounwind uwtable
define void @test2(%struct.data* nocapture readonly %d) #0 {
entry:
%b = getelementptr inbounds %struct.data* %d, i64 0, i32 1
%0 = load float** %b, align 8
%ptrint = ptrtoint float* %0 to i64
%maskedptr = and i64 %ptrint, 31
%maskcond = icmp eq i64 %maskedptr, 0
%a = getelementptr inbounds %struct.data* %d, i64 0, i32 0
%1 = load float** %a, align 8
%ptrint2 = ptrtoint float* %1 to i64
%maskedptr3 = and i64 %ptrint2, 31
%maskcond4 = icmp eq i64 %maskedptr3, 0
br label %for.body
; CHECK-LABEL: @test2
; CHECK: vector.body:
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: @llvm.assume
; CHECK: for.body:
; CHECK: ret void
for.body: ; preds = %for.body, %entry
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
tail call void @llvm.assume(i1 %maskcond)
%arrayidx = getelementptr inbounds float* %0, i64 %indvars.iv
%2 = load float* %arrayidx, align 4
%add = fadd float %2, 1.000000e+00
tail call void @llvm.assume(i1 %maskcond4)
%arrayidx5 = getelementptr inbounds float* %1, i64 %indvars.iv
store float %add, float* %arrayidx5, align 4
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv, 1599
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body
ret void
}
|
