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
174
175
176
177
178
179
|
; RUN: llc -mtriple=x86_64-unknown-unknown -march=x86-64 < %s | FileCheck %s
; CHECK-LABEL: fmul2_f32:
; CHECK: addss %xmm0, %xmm0
define float @fmul2_f32(float %x) {
%y = fmul float %x, 2.0
ret float %y
}
; fmul 2.0, x -> fadd x, x for vectors.
; CHECK-LABEL: fmul2_v4f32:
; CHECK: addps %xmm0, %xmm0
; CHECK-NEXT: retq
define <4 x float> @fmul2_v4f32(<4 x float> %x) {
%y = fmul <4 x float> %x, <float 2.0, float 2.0, float 2.0, float 2.0>
ret <4 x float> %y
}
; CHECK-LABEL: constant_fold_fmul_v4f32:
; CHECK: movaps
; CHECK-NEXT: ret
define <4 x float> @constant_fold_fmul_v4f32(<4 x float> %x) {
%y = fmul <4 x float> <float 4.0, float 4.0, float 4.0, float 4.0>, <float 2.0, float 2.0, float 2.0, float 2.0>
ret <4 x float> %y
}
; CHECK-LABEL: fmul0_v4f32:
; CHECK: xorps %xmm0, %xmm0
; CHECK-NEXT: retq
define <4 x float> @fmul0_v4f32(<4 x float> %x) #0 {
%y = fmul <4 x float> %x, <float 0.0, float 0.0, float 0.0, float 0.0>
ret <4 x float> %y
}
; CHECK-LABEL: fmul_c2_c4_v4f32:
; CHECK-NOT: addps
; CHECK: mulps
; CHECK-NOT: mulps
; CHECK-NEXT: ret
define <4 x float> @fmul_c2_c4_v4f32(<4 x float> %x) #0 {
%y = fmul <4 x float> %x, <float 2.0, float 2.0, float 2.0, float 2.0>
%z = fmul <4 x float> %y, <float 4.0, float 4.0, float 4.0, float 4.0>
ret <4 x float> %z
}
; CHECK-LABEL: fmul_c3_c4_v4f32:
; CHECK-NOT: addps
; CHECK: mulps
; CHECK-NOT: mulps
; CHECK-NEXT: ret
define <4 x float> @fmul_c3_c4_v4f32(<4 x float> %x) #0 {
%y = fmul <4 x float> %x, <float 3.0, float 3.0, float 3.0, float 3.0>
%z = fmul <4 x float> %y, <float 4.0, float 4.0, float 4.0, float 4.0>
ret <4 x float> %z
}
; We should be able to pre-multiply the two constant vectors.
; CHECK: float 5
; CHECK: float 12
; CHECK: float 21
; CHECK: float 32
; CHECK-LABEL: fmul_v4f32_two_consts_no_splat:
; CHECK: mulps
; CHECK-NOT: mulps
; CHECK-NEXT: ret
define <4 x float> @fmul_v4f32_two_consts_no_splat(<4 x float> %x) #0 {
%y = fmul <4 x float> %x, <float 1.0, float 2.0, float 3.0, float 4.0>
%z = fmul <4 x float> %y, <float 5.0, float 6.0, float 7.0, float 8.0>
ret <4 x float> %z
}
; Same as above, but reverse operands to make sure non-canonical form is also handled.
; CHECK: float 5
; CHECK: float 12
; CHECK: float 21
; CHECK: float 32
; CHECK-LABEL: fmul_v4f32_two_consts_no_splat_non_canonical:
; CHECK: mulps
; CHECK-NOT: mulps
; CHECK-NEXT: ret
define <4 x float> @fmul_v4f32_two_consts_no_splat_non_canonical(<4 x float> %x) #0 {
%y = fmul <4 x float> <float 1.0, float 2.0, float 3.0, float 4.0>, %x
%z = fmul <4 x float> <float 5.0, float 6.0, float 7.0, float 8.0>, %y
ret <4 x float> %z
}
; More than one use of a constant multiply should not inhibit the optimization.
; Instead of a chain of 2 dependent mults, this test will have 2 independent mults.
; CHECK: float 6
; CHECK: float 14
; CHECK: float 24
; CHECK: float 36
; CHECK-LABEL: fmul_v4f32_two_consts_no_splat_multiple_use:
; CHECK: mulps
; CHECK: ret
define <4 x float> @fmul_v4f32_two_consts_no_splat_multiple_use(<4 x float> %x) #0 {
%y = fmul <4 x float> %x, <float 1.0, float 2.0, float 3.0, float 4.0>
%z = fmul <4 x float> %y, <float 5.0, float 6.0, float 7.0, float 8.0>
%a = fadd <4 x float> %y, %z
ret <4 x float> %a
}
; PR22698 - http://llvm.org/bugs/show_bug.cgi?id=22698
; Make sure that we don't infinite loop swapping constants back and forth.
define <4 x float> @PR22698_splats(<4 x float> %a) #0 {
%mul1 = fmul fast <4 x float> <float 2.0, float 2.0, float 2.0, float 2.0>, <float 3.0, float 3.0, float 3.0, float 3.0>
%mul2 = fmul fast <4 x float> <float 4.0, float 4.0, float 4.0, float 4.0>, %mul1
%mul3 = fmul fast <4 x float> %a, %mul2
ret <4 x float> %mul3
; CHECK: float 24
; CHECK: float 24
; CHECK: float 24
; CHECK: float 24
; CHECK-LABEL: PR22698_splats:
; CHECK: mulps
; CHECK: ret
}
; Same as above, but verify that non-splat vectors are handled correctly too.
define <4 x float> @PR22698_no_splats(<4 x float> %a) #0 {
%mul1 = fmul fast <4 x float> <float 1.0, float 2.0, float 3.0, float 4.0>, <float 5.0, float 6.0, float 7.0, float 8.0>
%mul2 = fmul fast <4 x float> <float 9.0, float 10.0, float 11.0, float 12.0>, %mul1
%mul3 = fmul fast <4 x float> %a, %mul2
ret <4 x float> %mul3
; CHECK: float 45
; CHECK: float 120
; CHECK: float 231
; CHECK: float 384
; CHECK-LABEL: PR22698_no_splats:
; CHECK: mulps
; CHECK: ret
}
; CHECK-LABEL: fmul_c2_c4_f32:
; CHECK-NOT: addss
; CHECK: mulss
; CHECK-NOT: mulss
; CHECK-NEXT: ret
define float @fmul_c2_c4_f32(float %x) #0 {
%y = fmul float %x, 2.0
%z = fmul float %y, 4.0
ret float %z
}
; CHECK-LABEL: fmul_c3_c4_f32:
; CHECK-NOT: addss
; CHECK: mulss
; CHECK-NOT: mulss
; CHECK-NET: ret
define float @fmul_c3_c4_f32(float %x) #0 {
%y = fmul float %x, 3.0
%z = fmul float %y, 4.0
ret float %z
}
; CHECK-LABEL: fmul_fneg_fneg_f32:
; CHECK: mulss %xmm1, %xmm0
; CHECK-NEXT: retq
define float @fmul_fneg_fneg_f32(float %x, float %y) {
%x.neg = fsub float -0.0, %x
%y.neg = fsub float -0.0, %y
%mul = fmul float %x.neg, %y.neg
ret float %mul
}
; CHECK-LABEL: fmul_fneg_fneg_v4f32:
; CHECK: mulps {{%xmm1|\(%rdx\)}}, %xmm0
; CHECK-NEXT: retq
define <4 x float> @fmul_fneg_fneg_v4f32(<4 x float> %x, <4 x float> %y) {
%x.neg = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %x
%y.neg = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %y
%mul = fmul <4 x float> %x.neg, %y.neg
ret <4 x float> %mul
}
attributes #0 = { "less-precise-fpmad"="true" "no-infs-fp-math"="true" "no-nans-fp-math"="true" "unsafe-fp-math"="true" }
|
