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
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
|
; REQUIRES: asserts
; RUN: opt -mattr=+neon -passes=loop-vectorize -debug-only=loop-vectorize -disable-output -S < %s 2>&1 | FileCheck %s --check-prefix=NEON-NO-VECLIB
; RUN: opt -mattr=+sve -passes=loop-vectorize -debug-only=loop-vectorize -disable-output -S < %s 2>&1 | FileCheck %s --check-prefix=SVE-NO-VECLIB
; RUN: opt -mattr=+neon -vector-library=ArmPL -passes=loop-vectorize -debug-only=loop-vectorize -disable-output -S < %s 2>&1 | FileCheck %s --check-prefix=NEON-ARMPL
; RUN: opt -mattr=+neon -vector-library=sleefgnuabi -passes=loop-vectorize -debug-only=loop-vectorize -disable-output -S < %s 2>&1 | FileCheck %s --check-prefix=NEON-SLEEF
; RUN: opt -mattr=+sve -vector-library=ArmPL -passes=loop-vectorize -debug-only=loop-vectorize -disable-output -S < %s 2>&1 | FileCheck %s --check-prefix=SVE-ARMPL
; RUN: opt -mattr=+sve -vector-library=sleefgnuabi -passes=loop-vectorize -debug-only=loop-vectorize -disable-output -S < %s 2>&1 | FileCheck %s --check-prefix=SVE-SLEEF
; RUN: opt -mattr=+sve -vector-library=ArmPL -passes=loop-vectorize -prefer-predicate-over-epilogue=predicate-dont-vectorize -debug-only=loop-vectorize -disable-output -S < %s 2>&1 | FileCheck %s --check-prefix=SVE-ARMPL-TAILFOLD
; RUN: opt -mattr=+sve -vector-library=sleefgnuabi -passes=loop-vectorize -prefer-predicate-over-epilogue=predicate-dont-vectorize -debug-only=loop-vectorize -disable-output -S < %s 2>&1 | FileCheck %s --check-prefix=SVE-SLEEF-TAILFOLD
target triple = "aarch64-unknown-linux-gnu"
define void @frem_f64(ptr noalias %in.ptr, ptr noalias %out.ptr) {
; NEON-NO-VECLIB-LABEL: 'frem_f64'
; NEON-NO-VECLIB: LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem double %in, %in
; NEON-NO-VECLIB: Cost of 24 for VF 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
;
; SVE-NO-VECLIB-LABEL: 'frem_f64'
; SVE-NO-VECLIB: LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem double %in, %in
; SVE-NO-VECLIB: Cost of 24 for VF 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-NO-VECLIB: Cost of Invalid for VF vscale x 1: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-NO-VECLIB: Cost of Invalid for VF vscale x 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
;
; NEON-ARMPL-LABEL: 'frem_f64'
; NEON-ARMPL: LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem double %in, %in
; NEON-ARMPL: Cost of 10 for VF 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
;
; NEON-SLEEF-LABEL: 'frem_f64'
; NEON-SLEEF: LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem double %in, %in
; NEON-SLEEF: Cost of 10 for VF 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
;
; SVE-ARMPL-LABEL: 'frem_f64'
; SVE-ARMPL: LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem double %in, %in
; SVE-ARMPL: Cost of 10 for VF 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-ARMPL: Cost of Invalid for VF vscale x 1: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-ARMPL: Cost of 10 for VF vscale x 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
;
; SVE-SLEEF-LABEL: 'frem_f64'
; SVE-SLEEF: LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem double %in, %in
; SVE-SLEEF: Cost of 10 for VF 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-SLEEF: Cost of Invalid for VF vscale x 1: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-SLEEF: Cost of 10 for VF vscale x 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
;
; SVE-ARMPL-TAILFOLD-LABEL: 'frem_f64'
; SVE-ARMPL-TAILFOLD: LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem double %in, %in
; SVE-ARMPL-TAILFOLD: Cost of 10 for VF 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-ARMPL-TAILFOLD: Cost of Invalid for VF vscale x 1: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-ARMPL-TAILFOLD: Cost of 10 for VF vscale x 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
;
; SVE-SLEEF-TAILFOLD-LABEL: 'frem_f64'
; SVE-SLEEF-TAILFOLD: LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem double %in, %in
; SVE-SLEEF-TAILFOLD: Cost of 10 for VF 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-SLEEF-TAILFOLD: Cost of Invalid for VF vscale x 1: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-SLEEF-TAILFOLD: Cost of 10 for VF vscale x 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
;
entry:
br label %for.body
for.body:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
%in.gep = getelementptr inbounds double, ptr %in.ptr, i64 %iv
%in = load double, ptr %in.gep, align 8
%res = frem double %in, %in
%out.gep = getelementptr inbounds double, ptr %out.ptr, i64 %iv
store double %res, ptr %out.gep, align 8
%iv.next = add nuw nsw i64 %iv, 1
%exitcond = icmp eq i64 %iv.next, 1000
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret void
}
define void @frem_f32(ptr noalias %in.ptr, ptr noalias %out.ptr) {
; NEON-NO-VECLIB-LABEL: 'frem_f32'
; NEON-NO-VECLIB: LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem float %in, %in
; NEON-NO-VECLIB: Cost of 24 for VF 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; NEON-NO-VECLIB: Cost of 52 for VF 4: WIDEN ir<%res> = frem ir<%in>, ir<%in>
;
; SVE-NO-VECLIB-LABEL: 'frem_f32'
; SVE-NO-VECLIB: LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem float %in, %in
; SVE-NO-VECLIB: Cost of 24 for VF 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-NO-VECLIB: Cost of 52 for VF 4: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-NO-VECLIB: Cost of Invalid for VF vscale x 1: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-NO-VECLIB: Cost of Invalid for VF vscale x 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-NO-VECLIB: Cost of Invalid for VF vscale x 4: WIDEN ir<%res> = frem ir<%in>, ir<%in>
;
; NEON-ARMPL-LABEL: 'frem_f32'
; NEON-ARMPL: LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem float %in, %in
; NEON-ARMPL: Cost of 24 for VF 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; NEON-ARMPL: Cost of 10 for VF 4: WIDEN ir<%res> = frem ir<%in>, ir<%in>
;
; NEON-SLEEF-LABEL: 'frem_f32'
; NEON-SLEEF: LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem float %in, %in
; NEON-SLEEF: Cost of 24 for VF 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; NEON-SLEEF: Cost of 10 for VF 4: WIDEN ir<%res> = frem ir<%in>, ir<%in>
;
; SVE-ARMPL-LABEL: 'frem_f32'
; SVE-ARMPL: LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem float %in, %in
; SVE-ARMPL: Cost of 24 for VF 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-ARMPL: Cost of 10 for VF 4: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-ARMPL: Cost of Invalid for VF vscale x 1: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-ARMPL: Cost of Invalid for VF vscale x 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-ARMPL: Cost of 10 for VF vscale x 4: WIDEN ir<%res> = frem ir<%in>, ir<%in>
;
; SVE-SLEEF-LABEL: 'frem_f32'
; SVE-SLEEF: LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem float %in, %in
; SVE-SLEEF: Cost of 24 for VF 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-SLEEF: Cost of 10 for VF 4: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-SLEEF: Cost of Invalid for VF vscale x 1: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-SLEEF: Cost of Invalid for VF vscale x 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-SLEEF: Cost of 10 for VF vscale x 4: WIDEN ir<%res> = frem ir<%in>, ir<%in>
;
; SVE-ARMPL-TAILFOLD-LABEL: 'frem_f32'
; SVE-ARMPL-TAILFOLD: LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem float %in, %in
; SVE-ARMPL-TAILFOLD: Cost of 24 for VF 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-ARMPL-TAILFOLD: Cost of 10 for VF 4: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-ARMPL-TAILFOLD: Cost of Invalid for VF vscale x 1: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-ARMPL-TAILFOLD: Cost of Invalid for VF vscale x 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-ARMPL-TAILFOLD: Cost of 10 for VF vscale x 4: WIDEN ir<%res> = frem ir<%in>, ir<%in>
;
; SVE-SLEEF-TAILFOLD-LABEL: 'frem_f32'
; SVE-SLEEF-TAILFOLD: LV: Found an estimated cost of 10 for VF 1 For instruction: %res = frem float %in, %in
; SVE-SLEEF-TAILFOLD: Cost of 24 for VF 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-SLEEF-TAILFOLD: Cost of 10 for VF 4: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-SLEEF-TAILFOLD: Cost of Invalid for VF vscale x 1: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-SLEEF-TAILFOLD: Cost of Invalid for VF vscale x 2: WIDEN ir<%res> = frem ir<%in>, ir<%in>
; SVE-SLEEF-TAILFOLD: Cost of 10 for VF vscale x 4: WIDEN ir<%res> = frem ir<%in>, ir<%in>
;
entry:
br label %for.body
for.body:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
%in.gep = getelementptr inbounds float, ptr %in.ptr, i64 %iv
%in = load float, ptr %in.gep, align 8
%res = frem float %in, %in
%out.gep = getelementptr inbounds float, ptr %out.ptr, i64 %iv
store float %res, ptr %out.gep, align 4
%iv.next = add nuw nsw i64 %iv, 1
%exitcond = icmp eq i64 %iv.next, 1000
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret void
}
|
