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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s
define <8 x half> @cvt_and_clamp2(<8 x float>) nounwind {
; CHECK-LABEL: cvt_and_clamp2:
; CHECK: # %bb.0:
; CHECK-NEXT: subq $120, %rsp
; CHECK-NEXT: movaps %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: movaps %xmm1, %xmm0
; CHECK-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,3],xmm1[3,3]
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-NEXT: movhlps {{.*#+}} xmm0 = xmm0[1,1]
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,1,1,1]
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-NEXT: shufps {{.*#+}} xmm0 = xmm0[3,3,3,3]
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-NEXT: movhlps {{.*#+}} xmm0 = xmm0[1,1]
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; CHECK-NEXT: movaps {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Reload
; CHECK-NEXT: shufps {{.*#+}} xmm0 = xmm0[1,1,1,1]
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: callq __extendhfsf2@PLT
; CHECK-NEXT: xorps %xmm1, %xmm1
; CHECK-NEXT: callq fmaxf@PLT
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; CHECK-NEXT: movss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: callq __extendhfsf2@PLT
; CHECK-NEXT: xorps %xmm1, %xmm1
; CHECK-NEXT: callq fmaxf@PLT
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; CHECK-NEXT: movss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: callq __extendhfsf2@PLT
; CHECK-NEXT: xorps %xmm1, %xmm1
; CHECK-NEXT: callq fmaxf@PLT
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; CHECK-NEXT: movss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: callq __extendhfsf2@PLT
; CHECK-NEXT: xorps %xmm1, %xmm1
; CHECK-NEXT: callq fmaxf@PLT
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; CHECK-NEXT: movss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: callq __extendhfsf2@PLT
; CHECK-NEXT: xorps %xmm1, %xmm1
; CHECK-NEXT: callq fmaxf@PLT
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; CHECK-NEXT: movss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: callq __extendhfsf2@PLT
; CHECK-NEXT: xorps %xmm1, %xmm1
; CHECK-NEXT: callq fmaxf@PLT
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; CHECK-NEXT: movss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: callq __extendhfsf2@PLT
; CHECK-NEXT: xorps %xmm1, %xmm1
; CHECK-NEXT: callq fmaxf@PLT
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movss %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 4-byte Spill
; CHECK-NEXT: movss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: callq __extendhfsf2@PLT
; CHECK-NEXT: xorps %xmm1, %xmm1
; CHECK-NEXT: callq fmaxf@PLT
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: callq __extendhfsf2@PLT
; CHECK-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT: callq fminf@PLT
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: movd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Folded Reload
; CHECK-NEXT: # xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: callq __extendhfsf2@PLT
; CHECK-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT: callq fminf@PLT
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: punpcklwd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT: # xmm0 = xmm0[0],mem[0],xmm0[1],mem[1],xmm0[2],mem[2],xmm0[3],mem[3]
; CHECK-NEXT: movdqa %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: movss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: callq __extendhfsf2@PLT
; CHECK-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT: callq fminf@PLT
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: movd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Folded Reload
; CHECK-NEXT: # xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: callq __extendhfsf2@PLT
; CHECK-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT: callq fminf@PLT
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
; CHECK-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; CHECK-NEXT: punpckldq {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT: # xmm1 = xmm1[0],mem[0],xmm1[1],mem[1]
; CHECK-NEXT: movdqa %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: movss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: callq __extendhfsf2@PLT
; CHECK-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT: callq fminf@PLT
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: movd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Folded Reload
; CHECK-NEXT: # xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: callq __extendhfsf2@PLT
; CHECK-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT: callq fminf@PLT
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: punpcklwd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 16-byte Folded Reload
; CHECK-NEXT: # xmm0 = xmm0[0],mem[0],xmm0[1],mem[1],xmm0[2],mem[2],xmm0[3],mem[3]
; CHECK-NEXT: movdqa %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: movss {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Reload
; CHECK-NEXT: # xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: callq __extendhfsf2@PLT
; CHECK-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT: callq fminf@PLT
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movaps %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 16-byte Spill
; CHECK-NEXT: movd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 4-byte Folded Reload
; CHECK-NEXT: # xmm0 = mem[0],zero,zero,zero
; CHECK-NEXT: callq __extendhfsf2@PLT
; CHECK-NEXT: movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
; CHECK-NEXT: callq fminf@PLT
; CHECK-NEXT: callq __truncsfhf2@PLT
; CHECK-NEXT: movdqa {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Reload
; CHECK-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
; CHECK-NEXT: punpckldq {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT: # xmm1 = xmm1[0],mem[0],xmm1[1],mem[1]
; CHECK-NEXT: punpcklqdq {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 16-byte Folded Reload
; CHECK-NEXT: # xmm1 = xmm1[0],mem[0]
; CHECK-NEXT: movdqa %xmm1, %xmm0
; CHECK-NEXT: addq $120, %rsp
; CHECK-NEXT: retq
%2 = fptrunc <8 x float> %0 to <8 x half>
%3 = call <8 x half> @llvm.maxnum.v8f16(<8 x half> zeroinitializer, <8 x half> %2)
%4 = call <8 x half> @llvm.minnum.v8f16(<8 x half> %3, <8 x half> <half 1.0, half 1.0, half 1.0, half 1.0, half 1.0, half 1.0, half 1.0, half 1.0>)
ret <8 x half> %4
}
declare <8 x half> @llvm.maxnum.v8f16(<8 x half>, <8 x half>)
declare <8 x half> @llvm.minnum.v8f16(<8 x half>, <8 x half>)
|
