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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=aarch64-none-linux-gnu -verify-machineinstrs | FileCheck %s
define double @test1(double %a, double %b) {
; CHECK-LABEL: test1:
; CHECK: // %bb.0:
; CHECK-NEXT: fadd d1, d1, d1
; CHECK-NEXT: fsub d0, d0, d1
; CHECK-NEXT: ret
%mul = fmul double %b, -2.000000e+00
%add1 = fadd double %a, %mul
ret double %add1
}
; DAGCombine will canonicalize 'a - 2.0*b' to 'a + -2.0*b'
define double @test2(double %a, double %b) {
; CHECK-LABEL: test2:
; CHECK: // %bb.0:
; CHECK-NEXT: fadd d1, d1, d1
; CHECK-NEXT: fsub d0, d0, d1
; CHECK-NEXT: ret
%mul = fmul double %b, 2.000000e+00
%add1 = fsub double %a, %mul
ret double %add1
}
define double @test3(double %a, double %b, double %c) {
; CHECK-LABEL: test3:
; CHECK: // %bb.0:
; CHECK-NEXT: fmul d0, d0, d1
; CHECK-NEXT: fadd d1, d2, d2
; CHECK-NEXT: fsub d0, d0, d1
; CHECK-NEXT: ret
%mul = fmul double %a, %b
%mul1 = fmul double %c, 2.000000e+00
%sub = fsub double %mul, %mul1
ret double %sub
}
define double @test4(double %a, double %b, double %c) {
; CHECK-LABEL: test4:
; CHECK: // %bb.0:
; CHECK-NEXT: fmul d0, d0, d1
; CHECK-NEXT: fadd d1, d2, d2
; CHECK-NEXT: fsub d0, d0, d1
; CHECK-NEXT: ret
%mul = fmul double %a, %b
%mul1 = fmul double %c, -2.000000e+00
%add2 = fadd double %mul, %mul1
ret double %add2
}
define <4 x float> @fmulnegtwo_vec(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: fmulnegtwo_vec:
; CHECK: // %bb.0:
; CHECK-NEXT: fadd v1.4s, v1.4s, v1.4s
; CHECK-NEXT: fsub v0.4s, v0.4s, v1.4s
; CHECK-NEXT: ret
%mul = fmul <4 x float> %b, <float -2.0, float -2.0, float -2.0, float -2.0>
%add = fadd <4 x float> %a, %mul
ret <4 x float> %add
}
define <4 x float> @fmulnegtwo_vec_commute(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: fmulnegtwo_vec_commute:
; CHECK: // %bb.0:
; CHECK-NEXT: fadd v1.4s, v1.4s, v1.4s
; CHECK-NEXT: fsub v0.4s, v0.4s, v1.4s
; CHECK-NEXT: ret
%mul = fmul <4 x float> %b, <float -2.0, float -2.0, float -2.0, float -2.0>
%add = fadd <4 x float> %mul, %a
ret <4 x float> %add
}
define <4 x float> @fmulnegtwo_vec_undefs(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: fmulnegtwo_vec_undefs:
; CHECK: // %bb.0:
; CHECK-NEXT: fadd v1.4s, v1.4s, v1.4s
; CHECK-NEXT: fsub v0.4s, v0.4s, v1.4s
; CHECK-NEXT: ret
%mul = fmul <4 x float> %b, <float undef, float -2.0, float undef, float -2.0>
%add = fadd <4 x float> %a, %mul
ret <4 x float> %add
}
define <4 x float> @fmulnegtwo_vec_commute_undefs(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: fmulnegtwo_vec_commute_undefs:
; CHECK: // %bb.0:
; CHECK-NEXT: fadd v1.4s, v1.4s, v1.4s
; CHECK-NEXT: fsub v0.4s, v0.4s, v1.4s
; CHECK-NEXT: ret
%mul = fmul <4 x float> %b, <float -2.0, float undef, float -2.0, float -2.0>
%add = fadd <4 x float> %mul, %a
ret <4 x float> %add
}
define <4 x float> @test6(<4 x float> %a, <4 x float> %b) {
; CHECK-LABEL: test6:
; CHECK: // %bb.0:
; CHECK-NEXT: fadd v1.4s, v1.4s, v1.4s
; CHECK-NEXT: fsub v0.4s, v0.4s, v1.4s
; CHECK-NEXT: ret
%mul = fmul <4 x float> %b, <float 2.0, float 2.0, float 2.0, float 2.0>
%add = fsub <4 x float> %a, %mul
ret <4 x float> %add
}
; Don't fold (fadd A, (fmul B, -2.0)) -> (fsub A, (fadd B, B)) if the fmul has
; multiple uses.
define double @test7(double %a, double %b) nounwind {
; CHECK-LABEL: test7:
; CHECK: // %bb.0:
; CHECK-NEXT: str d8, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT: fmov d2, #-2.00000000
; CHECK-NEXT: fmul d1, d1, d2
; CHECK-NEXT: fadd d8, d0, d1
; CHECK-NEXT: mov v0.16b, v1.16b
; CHECK-NEXT: str x30, [sp, #8] // 8-byte Folded Spill
; CHECK-NEXT: bl use
; CHECK-NEXT: ldr x30, [sp, #8] // 8-byte Folded Reload
; CHECK-NEXT: mov v0.16b, v8.16b
; CHECK-NEXT: ldr d8, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: ret
%mul = fmul double %b, -2.000000e+00
%add1 = fadd double %a, %mul
call void @use(double %mul)
ret double %add1
}
define float @fadd_const_multiuse_fmf(float %x) {
; CHECK-LABEL: fadd_const_multiuse_fmf:
; CHECK: // %bb.0:
; CHECK-DAG: mov [[W59:w[0-9]+]], #1114374144
; CHECK-DAG: mov [[W42:w[0-9]+]], #1109917696
; CHECK-DAG: fmov [[FP59:s[0-9]+]], [[W59]]
; CHECK-DAG: fmov [[FP42:s[0-9]+]], [[W42]]
; CHECK-NEXT: fadd [[TMP1:s[0-9]+]], s0, [[FP42]]
; CHECK-NEXT: fadd [[TMP2:s[0-9]+]], s0, [[FP59]]
; CHECK-NEXT: fadd s0, [[TMP1]], [[TMP2]]
; CHECK-NEXT: ret
%a1 = fadd float %x, 42.0
%a2 = fadd nsz reassoc float %a1, 17.0
%a3 = fadd float %a1, %a2
ret float %a3
}
; DAGCombiner transforms this into: (x + 59.0) + (x + 17.0).
; The machine combiner transforms this into a chain of 3 dependent adds:
; ((x + 59.0) + 17.0) + x
define float @fadd_const_multiuse_attr(float %x) #0 {
; CHECK-LABEL: fadd_const_multiuse_attr:
; CHECK: // %bb.0:
; CHECK-DAG: mov [[W59:w[0-9]+]], #1114374144
; CHECK-DAG: mov [[W17:w[0-9]+]], #1109917696
; CHECK-NEXT: fmov [[FP59:s[0-9]+]], [[W59]]
; CHECK-NEXT: fmov [[FP17:s[0-9]+]], [[W17]]
; CHECK-NEXT: fadd [[TMP1:s[0-9]+]], s0, [[FP59]]
; CHECK-NEXT: fadd [[TMP2:s[0-9]+]], [[FP17]], [[TMP1]]
; CHECK-NEXT: fadd s0, s0, [[TMP2]]
; CHECK-NEXT: ret
%a1 = fadd float %x, 42.0
%a2 = fadd float %a1, 17.0
%a3 = fadd float %a1, %a2
ret float %a3
}
attributes #0 = { "unsafe-fp-math"="true" }
declare void @use(double)
|
