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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-apple-darwin9 -mattr=+sse,+sse2,+sse4.1 | FileCheck %s --check-prefix=CHECK --check-prefix=X32
; RUN: llc < %s -mtriple=x86_64-apple-darwin9 -mattr=+sse,+sse2,+sse4.1 | FileCheck %s --check-prefix=CHECK --check-prefix=X64
define i16 @test1(float %f) nounwind {
; X32-LABEL: test1:
; X32: ## BB#0:
; X32-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X32-NEXT: xorps %xmm1, %xmm1
; X32-NEXT: subss LCPI0_0, %xmm0
; X32-NEXT: mulss LCPI0_1, %xmm0
; X32-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; X32-NEXT: minss %xmm2, %xmm0
; X32-NEXT: maxss %xmm1, %xmm0
; X32-NEXT: cvttss2si %xmm0, %eax
; X32-NEXT: ## kill: %AX<def> %AX<kill> %EAX<kill>
; X32-NEXT: retl
;
; X64-LABEL: test1:
; X64: ## BB#0:
; X64-NEXT: xorps %xmm1, %xmm1
; X64-NEXT: blendps {{.*#+}} xmm0 = xmm0[0],xmm1[1,2,3]
; X64-NEXT: subss {{.*}}(%rip), %xmm0
; X64-NEXT: mulss {{.*}}(%rip), %xmm0
; X64-NEXT: movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
; X64-NEXT: minss %xmm2, %xmm0
; X64-NEXT: maxss %xmm1, %xmm0
; X64-NEXT: cvttss2si %xmm0, %eax
; X64-NEXT: ## kill: %AX<def> %AX<kill> %EAX<kill>
; X64-NEXT: retq
%tmp = insertelement <4 x float> undef, float %f, i32 0 ; <<4 x float>> [#uses=1]
%tmp10 = insertelement <4 x float> %tmp, float 0.000000e+00, i32 1 ; <<4 x float>> [#uses=1]
%tmp11 = insertelement <4 x float> %tmp10, float 0.000000e+00, i32 2 ; <<4 x float>> [#uses=1]
%tmp12 = insertelement <4 x float> %tmp11, float 0.000000e+00, i32 3 ; <<4 x float>> [#uses=1]
%tmp28 = tail call <4 x float> @llvm.x86.sse.sub.ss( <4 x float> %tmp12, <4 x float> < float 1.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00 > ) ; <<4 x float>> [#uses=1]
%tmp37 = tail call <4 x float> @llvm.x86.sse.mul.ss( <4 x float> %tmp28, <4 x float> < float 5.000000e-01, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00 > ) ; <<4 x float>> [#uses=1]
%tmp48 = tail call <4 x float> @llvm.x86.sse.min.ss( <4 x float> %tmp37, <4 x float> < float 6.553500e+04, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00 > ) ; <<4 x float>> [#uses=1]
%tmp59 = tail call <4 x float> @llvm.x86.sse.max.ss( <4 x float> %tmp48, <4 x float> zeroinitializer ) ; <<4 x float>> [#uses=1]
%tmp.upgrd.1 = tail call i32 @llvm.x86.sse.cvttss2si( <4 x float> %tmp59 ) ; <i32> [#uses=1]
%tmp69 = trunc i32 %tmp.upgrd.1 to i16 ; <i16> [#uses=1]
ret i16 %tmp69
}
define i16 @test2(float %f) nounwind {
; X32-LABEL: test2:
; X32: ## BB#0:
; X32-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X32-NEXT: addss LCPI1_0, %xmm0
; X32-NEXT: mulss LCPI1_1, %xmm0
; X32-NEXT: minss LCPI1_2, %xmm0
; X32-NEXT: xorps %xmm1, %xmm1
; X32-NEXT: maxss %xmm1, %xmm0
; X32-NEXT: cvttss2si %xmm0, %eax
; X32-NEXT: ## kill: %AX<def> %AX<kill> %EAX<kill>
; X32-NEXT: retl
;
; X64-LABEL: test2:
; X64: ## BB#0:
; X64-NEXT: addss {{.*}}(%rip), %xmm0
; X64-NEXT: mulss {{.*}}(%rip), %xmm0
; X64-NEXT: minss {{.*}}(%rip), %xmm0
; X64-NEXT: xorps %xmm1, %xmm1
; X64-NEXT: maxss %xmm1, %xmm0
; X64-NEXT: cvttss2si %xmm0, %eax
; X64-NEXT: ## kill: %AX<def> %AX<kill> %EAX<kill>
; X64-NEXT: retq
%tmp28 = fsub float %f, 1.000000e+00 ; <float> [#uses=1]
%tmp37 = fmul float %tmp28, 5.000000e-01 ; <float> [#uses=1]
%tmp375 = insertelement <4 x float> undef, float %tmp37, i32 0 ; <<4 x float>> [#uses=1]
%tmp48 = tail call <4 x float> @llvm.x86.sse.min.ss( <4 x float> %tmp375, <4 x float> < float 6.553500e+04, float undef, float undef, float undef > ) ; <<4 x float>> [#uses=1]
%tmp59 = tail call <4 x float> @llvm.x86.sse.max.ss( <4 x float> %tmp48, <4 x float> < float 0.000000e+00, float undef, float undef, float undef > ) ; <<4 x float>> [#uses=1]
%tmp = tail call i32 @llvm.x86.sse.cvttss2si( <4 x float> %tmp59 ) ; <i32> [#uses=1]
%tmp69 = trunc i32 %tmp to i16 ; <i16> [#uses=1]
ret i16 %tmp69
}
declare <4 x float> @llvm.x86.sse.sub.ss(<4 x float>, <4 x float>)
declare <4 x float> @llvm.x86.sse.mul.ss(<4 x float>, <4 x float>)
declare <4 x float> @llvm.x86.sse.min.ss(<4 x float>, <4 x float>)
declare <4 x float> @llvm.x86.sse.max.ss(<4 x float>, <4 x float>)
declare i32 @llvm.x86.sse.cvttss2si(<4 x float>)
declare <4 x float> @llvm.x86.sse41.round.ss(<4 x float>, <4 x float>, i32)
declare <4 x float> @f()
define <4 x float> @test3(<4 x float> %A, float *%b, i32 %C) nounwind {
; X32-LABEL: test3:
; X32: ## BB#0:
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: roundss $4, (%eax), %xmm0
; X32-NEXT: retl
;
; X64-LABEL: test3:
; X64: ## BB#0:
; X64-NEXT: roundss $4, (%rdi), %xmm0
; X64-NEXT: retq
%a = load float , float *%b
%B = insertelement <4 x float> undef, float %a, i32 0
%X = call <4 x float> @llvm.x86.sse41.round.ss(<4 x float> %A, <4 x float> %B, i32 4)
ret <4 x float> %X
}
define <4 x float> @test4(<4 x float> %A, float *%b, i32 %C) nounwind {
; X32-LABEL: test4:
; X32: ## BB#0:
; X32-NEXT: subl $28, %esp
; X32-NEXT: movl {{[0-9]+}}(%esp), %eax
; X32-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X32-NEXT: movaps %xmm0, (%esp) ## 16-byte Spill
; X32-NEXT: calll _f
; X32-NEXT: movaps (%esp), %xmm1 ## 16-byte Reload
; X32-NEXT: roundss $4, %xmm1, %xmm0
; X32-NEXT: addl $28, %esp
; X32-NEXT: retl
;
; X64-LABEL: test4:
; X64: ## BB#0:
; X64-NEXT: subq $24, %rsp
; X64-NEXT: movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
; X64-NEXT: movaps %xmm0, (%rsp) ## 16-byte Spill
; X64-NEXT: callq _f
; X64-NEXT: movaps (%rsp), %xmm1 ## 16-byte Reload
; X64-NEXT: roundss $4, %xmm1, %xmm0
; X64-NEXT: addq $24, %rsp
; X64-NEXT: retq
%a = load float , float *%b
%B = insertelement <4 x float> undef, float %a, i32 0
%q = call <4 x float> @f()
%X = call <4 x float> @llvm.x86.sse41.round.ss(<4 x float> %q, <4 x float> %B, i32 4)
ret <4 x float> %X
}
; PR13576
define <2 x double> @test5() nounwind uwtable readnone noinline {
; X32-LABEL: test5:
; X32: ## BB#0: ## %entry
; X32-NEXT: movaps {{.*#+}} xmm0 = [4.569870e+02,1.233210e+02]
; X32-NEXT: movl $128, %eax
; X32-NEXT: cvtsi2sdl %eax, %xmm0
; X32-NEXT: retl
;
; X64-LABEL: test5:
; X64: ## BB#0: ## %entry
; X64-NEXT: movaps {{.*#+}} xmm0 = [4.569870e+02,1.233210e+02]
; X64-NEXT: movl $128, %eax
; X64-NEXT: cvtsi2sdl %eax, %xmm0
; X64-NEXT: retq
entry:
%0 = tail call <2 x double> @llvm.x86.sse2.cvtsi2sd(<2 x double> <double 4.569870e+02, double 1.233210e+02>, i32 128) nounwind readnone
ret <2 x double> %0
}
declare <2 x double> @llvm.x86.sse2.cvtsi2sd(<2 x double>, i32) nounwind readnone
|
