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
|
; RUN: llc < %s -mtriple=x86_64-apple-darwin -march=x86 -mcpu=corei7-avx | FileCheck %s
; We don't check any vinsertf128 variant with immediate 0 because that's just a blend.
define <4 x double> @test_x86_avx_vinsertf128_pd_256_1(<4 x double> %a0, <2 x double> %a1) {
; CHECK-LABEL: test_x86_avx_vinsertf128_pd_256_1:
; CHECK: vinsertf128 $1, %xmm1, %ymm0, %ymm0
%res = call <4 x double> @llvm.x86.avx.vinsertf128.pd.256(<4 x double> %a0, <2 x double> %a1, i8 1)
ret <4 x double> %res
}
declare <4 x double> @llvm.x86.avx.vinsertf128.pd.256(<4 x double>, <2 x double>, i8) nounwind readnone
define <8 x float> @test_x86_avx_vinsertf128_ps_256_1(<8 x float> %a0, <4 x float> %a1) {
; CHECK-LABEL: test_x86_avx_vinsertf128_ps_256_1:
; CHECK: vinsertf128 $1, %xmm1, %ymm0, %ymm0
%res = call <8 x float> @llvm.x86.avx.vinsertf128.ps.256(<8 x float> %a0, <4 x float> %a1, i8 1)
ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx.vinsertf128.ps.256(<8 x float>, <4 x float>, i8) nounwind readnone
define <8 x i32> @test_x86_avx_vinsertf128_si_256_1(<8 x i32> %a0, <4 x i32> %a1) {
; CHECK-LABEL: test_x86_avx_vinsertf128_si_256_1:
; CHECK: vinsertf128 $1, %xmm1, %ymm0, %ymm0
%res = call <8 x i32> @llvm.x86.avx.vinsertf128.si.256(<8 x i32> %a0, <4 x i32> %a1, i8 1)
ret <8 x i32> %res
}
; Verify that high bits of the immediate are masked off. This should be the equivalent
; of a vinsertf128 $0 which should be optimized into a blend, so just check that it's
; not a vinsertf128 $1.
define <8 x i32> @test_x86_avx_vinsertf128_si_256_2(<8 x i32> %a0, <4 x i32> %a1) {
; CHECK-LABEL: test_x86_avx_vinsertf128_si_256_2:
; CHECK-NOT: vinsertf128 $1, %xmm1, %ymm0, %ymm0
%res = call <8 x i32> @llvm.x86.avx.vinsertf128.si.256(<8 x i32> %a0, <4 x i32> %a1, i8 2)
ret <8 x i32> %res
}
declare <8 x i32> @llvm.x86.avx.vinsertf128.si.256(<8 x i32>, <4 x i32>, i8) nounwind readnone
; We don't check any vextractf128 variant with immediate 0 because that's just a move.
define <2 x double> @test_x86_avx_vextractf128_pd_256_1(<4 x double> %a0) {
; CHECK-LABEL: test_x86_avx_vextractf128_pd_256_1:
; CHECK: vextractf128 $1, %ymm0, %xmm0
%res = call <2 x double> @llvm.x86.avx.vextractf128.pd.256(<4 x double> %a0, i8 1)
ret <2 x double> %res
}
declare <2 x double> @llvm.x86.avx.vextractf128.pd.256(<4 x double>, i8) nounwind readnone
define <4 x float> @test_x86_avx_vextractf128_ps_256_1(<8 x float> %a0) {
; CHECK-LABEL: test_x86_avx_vextractf128_ps_256_1:
; CHECK: vextractf128 $1, %ymm0, %xmm0
%res = call <4 x float> @llvm.x86.avx.vextractf128.ps.256(<8 x float> %a0, i8 1)
ret <4 x float> %res
}
declare <4 x float> @llvm.x86.avx.vextractf128.ps.256(<8 x float>, i8) nounwind readnone
define <4 x i32> @test_x86_avx_vextractf128_si_256_1(<8 x i32> %a0) {
; CHECK-LABEL: test_x86_avx_vextractf128_si_256_1:
; CHECK: vextractf128 $1, %ymm0, %xmm0
%res = call <4 x i32> @llvm.x86.avx.vextractf128.si.256(<8 x i32> %a0, i8 1)
ret <4 x i32> %res
}
declare <4 x i32> @llvm.x86.avx.vextractf128.si.256(<8 x i32>, i8) nounwind readnone
; Verify that high bits of the immediate are masked off. This should be the equivalent
; of a vextractf128 $0 which should be optimized away, so just check that it's
; not a vextractf128 of any kind.
define <2 x double> @test_x86_avx_extractf128_pd_256_2(<4 x double> %a0) {
; CHECK-LABEL: test_x86_avx_extractf128_pd_256_2:
; CHECK-NOT: vextractf128
%res = call <2 x double> @llvm.x86.avx.vextractf128.pd.256(<4 x double> %a0, i8 2)
ret <2 x double> %res
}
define <4 x double> @test_x86_avx_blend_pd_256(<4 x double> %a0, <4 x double> %a1) {
; CHECK-LABEL: test_x86_avx_blend_pd_256:
; CHECK: vblendpd
%res = call <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double> %a0, <4 x double> %a1, i32 7) ; <<4 x double>> [#uses=1]
ret <4 x double> %res
}
declare <4 x double> @llvm.x86.avx.blend.pd.256(<4 x double>, <4 x double>, i32) nounwind readnone
define <8 x float> @test_x86_avx_blend_ps_256(<8 x float> %a0, <8 x float> %a1) {
; CHECK-LABEL: test_x86_avx_blend_ps_256:
; CHECK: vblendps
%res = call <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float> %a0, <8 x float> %a1, i32 7) ; <<8 x float>> [#uses=1]
ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx.blend.ps.256(<8 x float>, <8 x float>, i32) nounwind readnone
define <8 x float> @test_x86_avx_dp_ps_256(<8 x float> %a0, <8 x float> %a1) {
; CHECK-LABEL: test_x86_avx_dp_ps_256:
; CHECK: vdpps
%res = call <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float> %a0, <8 x float> %a1, i32 7) ; <<8 x float>> [#uses=1]
ret <8 x float> %res
}
declare <8 x float> @llvm.x86.avx.dp.ps.256(<8 x float>, <8 x float>, i32) nounwind readnone
define <2 x i64> @test_x86_sse2_psll_dq(<2 x i64> %a0) {
; CHECK-LABEL: test_x86_sse2_psll_dq:
; CHECK: vpslldq {{.*#+}} xmm0 = zero,xmm0[0,1,2,3,4,5,6,7,8,9,10,11,12,13,14]
%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: vpsrldq {{.*#+}} xmm0 = xmm0[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15],zero
%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_sse41_blendpd(<2 x double> %a0, <2 x double> %a1) {
; CHECK-LABEL: test_x86_sse41_blendpd:
; CHECK: vblendpd
%res = call <2 x double> @llvm.x86.sse41.blendpd(<2 x double> %a0, <2 x double> %a1, i8 2) ; <<2 x double>> [#uses=1]
ret <2 x double> %res
}
declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i8) nounwind readnone
define <4 x float> @test_x86_sse41_blendps(<4 x float> %a0, <4 x float> %a1) {
; CHECK-LABEL: test_x86_sse41_blendps:
; CHECK: vblendps
%res = call <4 x float> @llvm.x86.sse41.blendps(<4 x float> %a0, <4 x float> %a1, i8 7) ; <<4 x float>> [#uses=1]
ret <4 x float> %res
}
declare <4 x float> @llvm.x86.sse41.blendps(<4 x float>, <4 x float>, i8) nounwind readnone
define <8 x i16> @test_x86_sse41_pblendw(<8 x i16> %a0, <8 x i16> %a1) {
; CHECK-LABEL: test_x86_sse41_pblendw:
; CHECK: vpblendw
%res = call <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16> %a0, <8 x i16> %a1, i8 7) ; <<8 x i16>> [#uses=1]
ret <8 x i16> %res
}
declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i8) nounwind readnone
|
