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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-apple-darwin -mattr=+avx2 | FileCheck %s
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+avx2 | FileCheck %s
define <8 x float> @test_unpacklo_hadd_v8f32(<8 x float> %0, <8 x float> %1, <8 x float> %2, <8 x float> %3) {
; CHECK-LABEL: test_unpacklo_hadd_v8f32:
; CHECK: ## %bb.0:
; CHECK-NEXT: vhaddps %ymm2, %ymm0, %ymm0
; CHECK-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
; CHECK-NEXT: ret{{[l|q]}}
%5 = tail call <8 x float> @llvm.x86.avx.hadd.ps.256(<8 x float> %0, <8 x float> %1) #4
%6 = tail call <8 x float> @llvm.x86.avx.hadd.ps.256(<8 x float> %2, <8 x float> %3) #4
%7 = shufflevector <8 x float> %5, <8 x float> %6, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 4, i32 12, i32 5, i32 13>
ret <8 x float> %7
}
define <8 x float> @test_unpackhi_hadd_v8f32(<8 x float> %0, <8 x float> %1, <8 x float> %2, <8 x float> %3) {
; CHECK-LABEL: test_unpackhi_hadd_v8f32:
; CHECK: ## %bb.0:
; CHECK-NEXT: vhaddps %ymm3, %ymm1, %ymm0
; CHECK-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
; CHECK-NEXT: ret{{[l|q]}}
%5 = tail call <8 x float> @llvm.x86.avx.hadd.ps.256(<8 x float> %0, <8 x float> %1) #4
%6 = tail call <8 x float> @llvm.x86.avx.hadd.ps.256(<8 x float> %2, <8 x float> %3) #4
%7 = shufflevector <8 x float> %5, <8 x float> %6, <8 x i32> <i32 2, i32 10, i32 3, i32 11, i32 6, i32 14, i32 7, i32 15>
ret <8 x float> %7
}
define <8 x float> @test_unpacklo_hsub_v8f32(<8 x float> %0, <8 x float> %1, <8 x float> %2, <8 x float> %3) {
; CHECK-LABEL: test_unpacklo_hsub_v8f32:
; CHECK: ## %bb.0:
; CHECK-NEXT: vhsubps %ymm2, %ymm0, %ymm0
; CHECK-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
; CHECK-NEXT: ret{{[l|q]}}
%5 = tail call <8 x float> @llvm.x86.avx.hsub.ps.256(<8 x float> %0, <8 x float> %1) #4
%6 = tail call <8 x float> @llvm.x86.avx.hsub.ps.256(<8 x float> %2, <8 x float> %3) #4
%7 = shufflevector <8 x float> %5, <8 x float> %6, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 4, i32 12, i32 5, i32 13>
ret <8 x float> %7
}
define <8 x float> @test_unpackhi_hsub_v8f32(<8 x float> %0, <8 x float> %1, <8 x float> %2, <8 x float> %3) {
; CHECK-LABEL: test_unpackhi_hsub_v8f32:
; CHECK: ## %bb.0:
; CHECK-NEXT: vhsubps %ymm3, %ymm1, %ymm0
; CHECK-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
; CHECK-NEXT: ret{{[l|q]}}
%5 = tail call <8 x float> @llvm.x86.avx.hsub.ps.256(<8 x float> %0, <8 x float> %1) #4
%6 = tail call <8 x float> @llvm.x86.avx.hsub.ps.256(<8 x float> %2, <8 x float> %3) #4
%7 = shufflevector <8 x float> %5, <8 x float> %6, <8 x i32> <i32 2, i32 10, i32 3, i32 11, i32 6, i32 14, i32 7, i32 15>
ret <8 x float> %7
}
define <8 x i32> @test_unpacklo_hadd_v8i32(<8 x i32> %0, <8 x i32> %1, <8 x i32> %2, <8 x i32> %3) {
; CHECK-LABEL: test_unpacklo_hadd_v8i32:
; CHECK: ## %bb.0:
; CHECK-NEXT: vphaddd %ymm2, %ymm0, %ymm0
; CHECK-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
; CHECK-NEXT: ret{{[l|q]}}
%5 = tail call <8 x i32> @llvm.x86.avx2.phadd.d(<8 x i32> %0, <8 x i32> %1) #5
%6 = tail call <8 x i32> @llvm.x86.avx2.phadd.d(<8 x i32> %2, <8 x i32> %3) #5
%7 = shufflevector <8 x i32> %5, <8 x i32> %6, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 4, i32 12, i32 5, i32 13>
ret <8 x i32> %7
}
define <8 x i32> @test_unpackhi_hadd_v8i32(<8 x i32> %0, <8 x i32> %1, <8 x i32> %2, <8 x i32> %3) {
; CHECK-LABEL: test_unpackhi_hadd_v8i32:
; CHECK: ## %bb.0:
; CHECK-NEXT: vphaddd %ymm3, %ymm1, %ymm0
; CHECK-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
; CHECK-NEXT: ret{{[l|q]}}
%5 = tail call <8 x i32> @llvm.x86.avx2.phadd.d(<8 x i32> %0, <8 x i32> %1) #5
%6 = tail call <8 x i32> @llvm.x86.avx2.phadd.d(<8 x i32> %2, <8 x i32> %3) #5
%7 = shufflevector <8 x i32> %5, <8 x i32> %6, <8 x i32> <i32 2, i32 10, i32 3, i32 11, i32 6, i32 14, i32 7, i32 15>
ret <8 x i32> %7
}
define <8 x i32> @test_unpacklo_hsub_v8i32(<8 x i32> %0, <8 x i32> %1, <8 x i32> %2, <8 x i32> %3) {
; CHECK-LABEL: test_unpacklo_hsub_v8i32:
; CHECK: ## %bb.0:
; CHECK-NEXT: vphsubd %ymm2, %ymm0, %ymm0
; CHECK-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
; CHECK-NEXT: ret{{[l|q]}}
%5 = tail call <8 x i32> @llvm.x86.avx2.phsub.d(<8 x i32> %0, <8 x i32> %1) #5
%6 = tail call <8 x i32> @llvm.x86.avx2.phsub.d(<8 x i32> %2, <8 x i32> %3) #5
%7 = shufflevector <8 x i32> %5, <8 x i32> %6, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 4, i32 12, i32 5, i32 13>
ret <8 x i32> %7
}
define <8 x i32> @test_unpackhi_hsub_v8i32(<8 x i32> %0, <8 x i32> %1, <8 x i32> %2, <8 x i32> %3) {
; CHECK-LABEL: test_unpackhi_hsub_v8i32:
; CHECK: ## %bb.0:
; CHECK-NEXT: vphsubd %ymm3, %ymm1, %ymm0
; CHECK-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
; CHECK-NEXT: ret{{[l|q]}}
%5 = tail call <8 x i32> @llvm.x86.avx2.phsub.d(<8 x i32> %0, <8 x i32> %1) #5
%6 = tail call <8 x i32> @llvm.x86.avx2.phsub.d(<8 x i32> %2, <8 x i32> %3) #5
%7 = shufflevector <8 x i32> %5, <8 x i32> %6, <8 x i32> <i32 2, i32 10, i32 3, i32 11, i32 6, i32 14, i32 7, i32 15>
ret <8 x i32> %7
}
define <4 x double> @PR49971(<4 x double> %0) {
; CHECK-LABEL: PR49971:
; CHECK: ## %bb.0:
; CHECK-NEXT: vhaddpd %xmm0, %xmm0, %xmm0
; CHECK-NEXT: vbroadcastsd %xmm0, %ymm0
; CHECK-NEXT: ret{{[l|q]}}
%2 = tail call <4 x double> @llvm.x86.avx.hadd.pd.256(<4 x double> %0, <4 x double> %0)
%3 = shufflevector <4 x double> %2, <4 x double> undef, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
ret <4 x double> %3
}
declare <8 x float> @llvm.x86.avx.hadd.ps.256(<8 x float>, <8 x float>)
declare <8 x float> @llvm.x86.avx.hsub.ps.256(<8 x float>, <8 x float>)
declare <4 x double> @llvm.x86.avx.hadd.pd.256(<4 x double>, <4 x double>)
declare <4 x double> @llvm.x86.avx.hsub.pd.256(<4 x double>, <4 x double>)
declare <16 x i16> @llvm.x86.avx2.phadd.w(<16 x i16>, <16 x i16>)
declare <8 x i32> @llvm.x86.avx2.phadd.d(<8 x i32>, <8 x i32>)
declare <16 x i16> @llvm.x86.avx2.phsub.w(<16 x i16>, <16 x i16>)
declare <8 x i32> @llvm.x86.avx2.phsub.d(<8 x i32>, <8 x i32>)
declare <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16>, <16 x i16>)
declare <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32>, <8 x i32>)
declare <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16>, <16 x i16>)
declare <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32>, <8 x i32>)
|
