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
|
; REQUIRES: asserts
; RUN: opt < %s -passes=loop-vectorize -debug -disable-output -force-ordered-reductions=true -hints-allow-reordering=false \
; RUN: -force-vector-width=4 -force-vector-interleave=1 -S 2>&1 | FileCheck %s --check-prefix=CHECK-VF4
; RUN: opt < %s -passes=loop-vectorize -debug -disable-output -force-ordered-reductions=true -hints-allow-reordering=false \
; RUN: -force-vector-width=8 -force-vector-interleave=1 -S 2>&1 | FileCheck %s --check-prefix=CHECK-VF8
target triple="aarch64-unknown-linux-gnu"
; CHECK-VF4: Found an estimated cost of 14 for VF 4 For instruction: %add = fadd float %0, %sum.07
; CHECK-VF8: Found an estimated cost of 28 for VF 8 For instruction: %add = fadd float %0, %sum.07
define float @fadd_strict32(ptr noalias nocapture readonly %a, i64 %n) {
entry:
br label %for.body
for.body:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
%sum.07 = phi float [ 0.000000e+00, %entry ], [ %add, %for.body ]
%arrayidx = getelementptr inbounds float, ptr %a, i64 %iv
%0 = load float, ptr %arrayidx, align 4
%add = fadd float %0, %sum.07
%iv.next = add nuw nsw i64 %iv, 1
%exitcond.not = icmp eq i64 %iv.next, %n
br i1 %exitcond.not, label %for.end, label %for.body
for.end:
ret float %add
}
; CHECK-VF4: Found an estimated cost of 12 for VF 4 For instruction: %add = fadd double %0, %sum.07
; CHECK-VF8: Found an estimated cost of 24 for VF 8 For instruction: %add = fadd double %0, %sum.07
define double @fadd_strict64(ptr noalias nocapture readonly %a, i64 %n) {
entry:
br label %for.body
for.body:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
%sum.07 = phi double [ 0.000000e+00, %entry ], [ %add, %for.body ]
%arrayidx = getelementptr inbounds double, ptr %a, i64 %iv
%0 = load double, ptr %arrayidx, align 4
%add = fadd double %0, %sum.07
%iv.next = add nuw nsw i64 %iv, 1
%exitcond.not = icmp eq i64 %iv.next, %n
br i1 %exitcond.not, label %for.end, label %for.body
for.end:
ret double %add
}
; CHECK-VF4: Found an estimated cost of 16 for VF 4 For instruction: %muladd = tail call float @llvm.fmuladd.f32(float %0, float %1, float %sum.07)
; CHECK-VF8: Found an estimated cost of 32 for VF 8 For instruction: %muladd = tail call float @llvm.fmuladd.f32(float %0, float %1, float %sum.07)
define float @fmuladd_strict32(ptr %a, ptr %b, i64 %n) {
entry:
br label %for.body
for.body:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
%sum.07 = phi float [ 0.000000e+00, %entry ], [ %muladd, %for.body ]
%arrayidx = getelementptr inbounds float, ptr %a, i64 %iv
%0 = load float, ptr %arrayidx, align 4
%arrayidx2 = getelementptr inbounds float, ptr %b, i64 %iv
%1 = load float, ptr %arrayidx2, align 4
%muladd = tail call float @llvm.fmuladd.f32(float %0, float %1, float %sum.07)
%iv.next = add nuw nsw i64 %iv, 1
%exitcond.not = icmp eq i64 %iv.next, %n
br i1 %exitcond.not, label %for.end, label %for.body
for.end:
ret float %muladd
}
declare float @llvm.fmuladd.f32(float, float, float)
; CHECK-VF4: Found an estimated cost of 16 for VF 4 For instruction: %muladd = tail call double @llvm.fmuladd.f64(double %0, double %1, double %sum.07)
; CHECK-VF8: Found an estimated cost of 32 for VF 8 For instruction: %muladd = tail call double @llvm.fmuladd.f64(double %0, double %1, double %sum.07)
define double @fmuladd_strict64(ptr %a, ptr %b, i64 %n) {
entry:
br label %for.body
for.body:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
%sum.07 = phi double [ 0.000000e+00, %entry ], [ %muladd, %for.body ]
%arrayidx = getelementptr inbounds double, ptr %a, i64 %iv
%0 = load double, ptr %arrayidx, align 4
%arrayidx2 = getelementptr inbounds double, ptr %b, i64 %iv
%1 = load double, ptr %arrayidx2, align 4
%muladd = tail call double @llvm.fmuladd.f64(double %0, double %1, double %sum.07)
%iv.next = add nuw nsw i64 %iv, 1
%exitcond.not = icmp eq i64 %iv.next, %n
br i1 %exitcond.not, label %for.end, label %for.body
for.end:
ret double %muladd
}
declare double @llvm.fmuladd.f64(double, double, double)
|
