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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: llc < %s -mtriple=i686-apple-darwin -mattr=+sse2 | FileCheck %s
define <2 x i64> @test_x86_sse2_psll_dq_bs(<2 x i64> %a0) {
; CHECK-LABEL: test_x86_sse2_psll_dq_bs:
; CHECK: ## BB#0:
; CHECK-NEXT: pslldq {{.*#+}} xmm0 = zero,zero,zero,zero,zero,zero,zero,xmm0[0,1,2,3,4,5,6,7,8]
; CHECK-NEXT: retl
%res = call <2 x i64> @llvm.x86.sse2.psll.dq.bs(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
ret <2 x i64> %res
}
declare <2 x i64> @llvm.x86.sse2.psll.dq.bs(<2 x i64>, i32) nounwind readnone
define <2 x i64> @test_x86_sse2_psrl_dq_bs(<2 x i64> %a0) {
; CHECK-LABEL: test_x86_sse2_psrl_dq_bs:
; CHECK: ## BB#0:
; CHECK-NEXT: psrldq {{.*#+}} xmm0 = xmm0[7,8,9,10,11,12,13,14,15],zero,zero,zero,zero,zero,zero,zero
; CHECK-NEXT: retl
%res = call <2 x i64> @llvm.x86.sse2.psrl.dq.bs(<2 x i64> %a0, i32 7) ; <<2 x i64>> [#uses=1]
ret <2 x i64> %res
}
declare <2 x i64> @llvm.x86.sse2.psrl.dq.bs(<2 x i64>, i32) nounwind readnone
define <2 x i64> @test_x86_sse2_psll_dq(<2 x i64> %a0) {
; CHECK-LABEL: test_x86_sse2_psll_dq:
; CHECK: ## BB#0:
; CHECK-NEXT: pslldq {{.*#+}} xmm0 = zero,xmm0[0,1,2,3,4,5,6,7,8,9,10,11,12,13,14]
; CHECK-NEXT: retl
%res = call <2 x i64> @llvm.x86.sse2.psll.dq(<2 x i64> %a0, i32 8) ; <<2 x i64>> [#uses=1]
ret <2 x i64> %res
}
declare <2 x i64> @llvm.x86.sse2.psll.dq(<2 x i64>, i32) nounwind readnone
define <2 x i64> @test_x86_sse2_psrl_dq(<2 x i64> %a0) {
; CHECK-LABEL: test_x86_sse2_psrl_dq:
; CHECK: ## BB#0:
; CHECK-NEXT: psrldq {{.*#+}} xmm0 = xmm0[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15],zero
; CHECK-NEXT: retl
%res = call <2 x i64> @llvm.x86.sse2.psrl.dq(<2 x i64> %a0, i32 8) ; <<2 x i64>> [#uses=1]
ret <2 x i64> %res
}
declare <2 x i64> @llvm.x86.sse2.psrl.dq(<2 x i64>, i32) nounwind readnone
define <2 x double> @test_x86_sse2_cvtdq2pd(<4 x i32> %a0) {
; SSE-LABEL: test_x86_sse2_cvtdq2pd:
; SSE: ## BB#0:
; SSE-NEXT: cvtdq2pd %xmm0, %xmm0
; SSE-NEXT: retl
;
; KNL-LABEL: test_x86_sse2_cvtdq2pd:
; KNL: ## BB#0:
; KNL-NEXT: vcvtdq2pd %xmm0, %xmm0
; KNL-NEXT: retl
; CHECK-LABEL: test_x86_sse2_cvtdq2pd:
; CHECK: ## BB#0:
; CHECK-NEXT: cvtdq2pd %xmm0, %xmm0
; CHECK-NEXT: retl
%res = call <2 x double> @llvm.x86.sse2.cvtdq2pd(<4 x i32> %a0) ; <<2 x double>> [#uses=1]
ret <2 x double> %res
}
declare <2 x double> @llvm.x86.sse2.cvtdq2pd(<4 x i32>) nounwind readnone
define <2 x double> @test_x86_sse2_cvtps2pd(<4 x float> %a0) {
; SSE-LABEL: test_x86_sse2_cvtps2pd:
; SSE: ## BB#0:
; SSE-NEXT: cvtps2pd %xmm0, %xmm0
; SSE-NEXT: retl
;
; KNL-LABEL: test_x86_sse2_cvtps2pd:
; KNL: ## BB#0:
; KNL-NEXT: vcvtps2pd %xmm0, %xmm0
; KNL-NEXT: retl
; CHECK-LABEL: test_x86_sse2_cvtps2pd:
; CHECK: ## BB#0:
; CHECK-NEXT: cvtps2pd %xmm0, %xmm0
; CHECK-NEXT: retl
%res = call <2 x double> @llvm.x86.sse2.cvtps2pd(<4 x float> %a0) ; <<2 x double>> [#uses=1]
ret <2 x double> %res
}
declare <2 x double> @llvm.x86.sse2.cvtps2pd(<4 x float>) nounwind readnone
define void @test_x86_sse2_storel_dq(i8* %a0, <4 x i32> %a1) {
; CHECK-LABEL: test_x86_sse2_storel_dq:
; CHECK: ## BB#0:
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: movlps %xmm0, (%eax)
; CHECK-NEXT: retl
call void @llvm.x86.sse2.storel.dq(i8* %a0, <4 x i32> %a1)
ret void
}
declare void @llvm.x86.sse2.storel.dq(i8*, <4 x i32>) nounwind
define void @test_x86_sse2_storeu_dq(i8* %a0, <16 x i8> %a1) {
; add operation forces the execution domain.
; CHECK-LABEL: test_x86_sse2_storeu_dq:
; CHECK: ## BB#0:
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: paddb LCPI7_0, %xmm0
; CHECK-NEXT: movdqu %xmm0, (%eax)
; CHECK-NEXT: retl
%a2 = add <16 x i8> %a1, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
call void @llvm.x86.sse2.storeu.dq(i8* %a0, <16 x i8> %a2)
ret void
}
declare void @llvm.x86.sse2.storeu.dq(i8*, <16 x i8>) nounwind
define void @test_x86_sse2_storeu_pd(i8* %a0, <2 x double> %a1) {
; fadd operation forces the execution domain.
; CHECK-LABEL: test_x86_sse2_storeu_pd:
; CHECK: ## BB#0:
; CHECK-NEXT: movl {{[0-9]+}}(%esp), %eax
; CHECK-NEXT: movsd {{.*#+}} xmm1 = mem[0],zero
; CHECK-NEXT: pslldq {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,1,2,3,4,5,6,7]
; CHECK-NEXT: addpd %xmm0, %xmm1
; CHECK-NEXT: movupd %xmm1, (%eax)
; CHECK-NEXT: retl
%a2 = fadd <2 x double> %a1, <double 0x0, double 0x4200000000000000>
call void @llvm.x86.sse2.storeu.pd(i8* %a0, <2 x double> %a2)
ret void
}
declare void @llvm.x86.sse2.storeu.pd(i8*, <2 x double>) nounwind
|
