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
|
; RUN: opt < %s -passes=loop-vectorize,dce,instcombine -force-vector-interleave=1 -force-target-supports-scalable-vectors=true -S | FileCheck %s
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
; CHECK-LABEL: @test1(
; CHECK: store <8 x i32>
; CHECK: ret void
define void @test1(ptr nocapture %a, i32 %n) #0 {
entry:
%cmp4 = icmp sgt i32 %n, 0
br i1 %cmp4, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
store i32 42, ptr %arrayidx, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0
for.end: ; preds = %for.body, %entry
ret void
}
; CHECK-LABEL: @test2(
; CHECK: store <vscale x 8 x i32>
; CHECK: ret void
define void @test2(ptr nocapture %a, i32 %n) #0 {
entry:
%cmp4 = icmp sgt i32 %n, 0
br i1 %cmp4, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
store i32 42, ptr %arrayidx, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !2
for.end: ; preds = %for.body, %entry
ret void
}
; CHECK-LABEL: @test3(
; CHECK: store <8 x i32>
; CHECK: ret void
define void @test3(ptr nocapture %a, i32 %n) #0 {
entry:
%cmp4 = icmp sgt i32 %n, 0
br i1 %cmp4, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
store i32 42, ptr %arrayidx, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !4
for.end: ; preds = %for.body, %entry
ret void
}
; Test that when only the width property is specified, and not the scalable.enable flag,
; that the hint defaults to 'scalable.enable = false'.
; CHECK-LABEL: @test4(
; CHECK: store <8 x i32>
; CHECK: ret void
define void @test4(ptr nocapture %a, i32 %n) #0 {
entry:
%cmp4 = icmp sgt i32 %n, 0
br i1 %cmp4, label %for.body, label %for.end
for.body: ; preds = %entry, %for.body
%indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i32, ptr %a, i64 %indvars.iv
store i32 42, ptr %arrayidx, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, %n
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !6
for.end: ; preds = %for.body, %entry
ret void
}
attributes #0 = { nounwind uwtable "less-precise-fpmad"="false" "frame-pointer"="none" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "unsafe-fp-math"="false" "use-soft-float"="false" }
!0 = !{!0, !1, !5}
!1 = !{!"llvm.loop.vectorize.width", i32 8}
!2 = !{!2, !1, !3}
!3 = !{!"llvm.loop.vectorize.scalable.enable", i32 1}
!4 = !{!4, !1, !5}
!5 = !{!"llvm.loop.vectorize.scalable.enable", i32 0}
!6 = !{!6, !7}
!7 = !{!"llvm.loop.vectorize.width", i32 8}
|