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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+avx2,+fma | FileCheck %s --check-prefix=X32
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+avx2,+fma | FileCheck %s --check-prefix=X64
; This test checks combinations of FNEG and FMA intrinsics
define <8 x float> @test1(<8 x float> %a, <8 x float> %b, <8 x float> %c) {
; X32-LABEL: test1:
; X32: # %bb.0: # %entry
; X32-NEXT: vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - ymm2
; X32-NEXT: retl
;
; X64-LABEL: test1:
; X64: # %bb.0: # %entry
; X64-NEXT: vfmsub213ps {{.*#+}} ymm0 = (ymm1 * ymm0) - ymm2
; X64-NEXT: retq
entry:
%sub.i = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
%0 = tail call <8 x float> @llvm.x86.fma.vfmadd.ps.256(<8 x float> %a, <8 x float> %b, <8 x float> %sub.i) #2
ret <8 x float> %0
}
declare <8 x float> @llvm.x86.fma.vfmadd.ps.256(<8 x float>, <8 x float>, <8 x float>)
define <4 x float> @test2(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; X32-LABEL: test2:
; X32: # %bb.0: # %entry
; X32-NEXT: vfnmsub213ps {{.*#+}} xmm0 = -(xmm1 * xmm0) - xmm2
; X32-NEXT: retl
;
; X64-LABEL: test2:
; X64: # %bb.0: # %entry
; X64-NEXT: vfnmsub213ps {{.*#+}} xmm0 = -(xmm1 * xmm0) - xmm2
; X64-NEXT: retq
entry:
%0 = tail call <4 x float> @llvm.x86.fma.vfmadd.ps(<4 x float> %a, <4 x float> %b, <4 x float> %c) #2
%sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0
ret <4 x float> %sub.i
}
declare <4 x float> @llvm.x86.fma.vfmadd.ps(<4 x float> %a, <4 x float> %b, <4 x float> %c)
define <4 x float> @test3(<4 x float> %a, <4 x float> %b, <4 x float> %c) {
; X32-LABEL: test3:
; X32: # %bb.0: # %entry
; X32-NEXT: vfnmadd213ss {{.*#+}} xmm0 = -(xmm1 * xmm0) + xmm2
; X32-NEXT: vbroadcastss {{.*#+}} xmm1 = [-0,-0,-0,-0]
; X32-NEXT: vxorps %xmm1, %xmm0, %xmm0
; X32-NEXT: retl
;
; X64-LABEL: test3:
; X64: # %bb.0: # %entry
; X64-NEXT: vfnmadd213ss {{.*#+}} xmm0 = -(xmm1 * xmm0) + xmm2
; X64-NEXT: vbroadcastss {{.*#+}} xmm1 = [-0,-0,-0,-0]
; X64-NEXT: vxorps %xmm1, %xmm0, %xmm0
; X64-NEXT: retq
entry:
%0 = tail call <4 x float> @llvm.x86.fma.vfnmadd.ss(<4 x float> %a, <4 x float> %b, <4 x float> %c) #2
%sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0
ret <4 x float> %sub.i
}
declare <4 x float> @llvm.x86.fma.vfnmadd.ss(<4 x float> %a, <4 x float> %b, <4 x float> %c)
define <8 x float> @test4(<8 x float> %a, <8 x float> %b, <8 x float> %c) {
; X32-LABEL: test4:
; X32: # %bb.0: # %entry
; X32-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm2
; X32-NEXT: retl
;
; X64-LABEL: test4:
; X64: # %bb.0: # %entry
; X64-NEXT: vfnmadd213ps {{.*#+}} ymm0 = -(ymm1 * ymm0) + ymm2
; X64-NEXT: retq
entry:
%0 = tail call <8 x float> @llvm.x86.fma.vfmsub.ps.256(<8 x float> %a, <8 x float> %b, <8 x float> %c) #2
%sub.i = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0
ret <8 x float> %sub.i
}
define <8 x float> @test5(<8 x float> %a, <8 x float> %b, <8 x float> %c) {
; X32-LABEL: test5:
; X32: # %bb.0: # %entry
; X32-NEXT: vfmadd213ps {{.*#+}} ymm0 = (ymm1 * ymm0) + ymm2
; X32-NEXT: retl
;
; X64-LABEL: test5:
; X64: # %bb.0: # %entry
; X64-NEXT: vfmadd213ps {{.*#+}} ymm0 = (ymm1 * ymm0) + ymm2
; X64-NEXT: retq
entry:
%sub.c = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
%0 = tail call <8 x float> @llvm.x86.fma.vfmsub.ps.256(<8 x float> %a, <8 x float> %b, <8 x float> %sub.c) #2
ret <8 x float> %0
}
declare <8 x float> @llvm.x86.fma.vfmsub.ps.256(<8 x float>, <8 x float>, <8 x float>)
define <2 x double> @test6(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; X32-LABEL: test6:
; X32: # %bb.0: # %entry
; X32-NEXT: vfnmsub213pd {{.*#+}} xmm0 = -(xmm1 * xmm0) - xmm2
; X32-NEXT: retl
;
; X64-LABEL: test6:
; X64: # %bb.0: # %entry
; X64-NEXT: vfnmsub213pd {{.*#+}} xmm0 = -(xmm1 * xmm0) - xmm2
; X64-NEXT: retq
entry:
%0 = tail call <2 x double> @llvm.x86.fma.vfmadd.pd(<2 x double> %a, <2 x double> %b, <2 x double> %c) #2
%sub.i = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %0
ret <2 x double> %sub.i
}
declare <2 x double> @llvm.x86.fma.vfmadd.pd(<2 x double> %a, <2 x double> %b, <2 x double> %c)
define <8 x float> @test7(float %a, <8 x float> %b, <8 x float> %c) {
; X32-LABEL: test7:
; X32: # %bb.0: # %entry
; X32-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; X32-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; X32-NEXT: vsubps %ymm2, %ymm3, %ymm2
; X32-NEXT: vbroadcastss %xmm2, %ymm2
; X32-NEXT: vfmadd213ps {{.*#+}} ymm0 = (ymm2 * ymm0) + ymm1
; X32-NEXT: retl
;
; X64-LABEL: test7:
; X64: # %bb.0: # %entry
; X64-NEXT: # kill: def $xmm0 killed $xmm0 def $ymm0
; X64-NEXT: vmovss {{.*#+}} xmm3 = mem[0],zero,zero,zero
; X64-NEXT: vsubps %ymm0, %ymm3, %ymm0
; X64-NEXT: vbroadcastss %xmm0, %ymm0
; X64-NEXT: vfmadd213ps {{.*#+}} ymm0 = (ymm1 * ymm0) + ymm2
; X64-NEXT: retq
entry:
%0 = insertelement <8 x float> undef, float %a, i32 0
%1 = fsub <8 x float> <float -0.000000e+00, float undef, float undef, float undef, float undef, float undef, float undef, float undef>, %0
%2 = shufflevector <8 x float> %1, <8 x float> undef, <8 x i32> zeroinitializer
%3 = tail call <8 x float> @llvm.fma.v8f32(<8 x float> %2, <8 x float> %b, <8 x float> %c)
ret <8 x float> %3
}
define <8 x float> @test8(float %a, <8 x float> %b, <8 x float> %c) {
; X32-LABEL: test8:
; X32: # %bb.0: # %entry
; X32-NEXT: vmovss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; X32-NEXT: vbroadcastss {{.*#+}} xmm3 = [-0,-0,-0,-0]
; X32-NEXT: vxorps %xmm3, %xmm2, %xmm2
; X32-NEXT: vbroadcastss %xmm2, %ymm2
; X32-NEXT: vfmadd213ps {{.*#+}} ymm0 = (ymm2 * ymm0) + ymm1
; X32-NEXT: retl
;
; X64-LABEL: test8:
; X64: # %bb.0: # %entry
; X64-NEXT: vbroadcastss {{.*#+}} xmm3 = [-0,-0,-0,-0]
; X64-NEXT: vxorps %xmm3, %xmm0, %xmm0
; X64-NEXT: vbroadcastss %xmm0, %ymm0
; X64-NEXT: vfmadd213ps {{.*#+}} ymm0 = (ymm1 * ymm0) + ymm2
; X64-NEXT: retq
entry:
%0 = fsub float -0.0, %a
%1 = insertelement <8 x float> undef, float %0, i32 0
%2 = shufflevector <8 x float> %1, <8 x float> undef, <8 x i32> zeroinitializer
%3 = tail call <8 x float> @llvm.fma.v8f32(<8 x float> %2, <8 x float> %b, <8 x float> %c)
ret <8 x float> %3
}
declare <8 x float> @llvm.fma.v8f32(<8 x float> %a, <8 x float> %b, <8 x float> %c)
|
