aboutsummaryrefslogtreecommitdiffstats
path: root/test/CodeGen/X86/avx.ll
blob: f71ec5c10e69aa6151c44e59fd0f4c3b6a808eb4 (plain)
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
; RUN: llc < %s -mtriple=i686-apple-darwin -mcpu=corei7-avx | FileCheck %s -check-prefix=X32 --check-prefix=CHECK
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx | FileCheck %s -check-prefix=X64 --check-prefix=CHECK

define <4 x i32> @blendvb_fallback_v4i32(<4 x i1> %mask, <4 x i32> %x, <4 x i32> %y) {
; CHECK-LABEL: @blendvb_fallback_v4i32
; CHECK: vblendvps
; CHECK: ret
  %ret = select <4 x i1> %mask, <4 x i32> %x, <4 x i32> %y
  ret <4 x i32> %ret
}

define <8 x i32> @blendvb_fallback_v8i32(<8 x i1> %mask, <8 x i32> %x, <8 x i32> %y) {
; CHECK-LABEL: @blendvb_fallback_v8i32
; CHECK: vblendvps
; CHECK: ret
  %ret = select <8 x i1> %mask, <8 x i32> %x, <8 x i32> %y
  ret <8 x i32> %ret
}

define <8 x float> @blendvb_fallback_v8f32(<8 x i1> %mask, <8 x float> %x, <8 x float> %y) {
; CHECK-LABEL: @blendvb_fallback_v8f32
; CHECK: vblendvps
; CHECK: ret
  %ret = select <8 x i1> %mask, <8 x float> %x, <8 x float> %y
  ret <8 x float> %ret
}

declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i32) nounwind readnone

define <4 x float> @insertps_from_vector_load(<4 x float> %a, <4 x float>* nocapture readonly %pb) {
; CHECK-LABEL: insertps_from_vector_load:
; On X32, account for the argument's move to registers
; X32: movl    4(%esp), %eax
; CHECK-NOT: mov
; CHECK: insertps    $48
; CHECK-NEXT: ret
  %1 = load <4 x float>, <4 x float>* %pb, align 16
  %2 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %1, i32 48)
  ret <4 x float> %2
}

;; Use a non-zero CountS for insertps
define <4 x float> @insertps_from_vector_load_offset(<4 x float> %a, <4 x float>* nocapture readonly %pb) {
; CHECK-LABEL: insertps_from_vector_load_offset:
; On X32, account for the argument's move to registers
; X32: movl    4(%esp), %eax
; CHECK-NOT: mov
;; Try to match a bit more of the instr, since we need the load's offset.
; CHECK: insertps    $96, 4(%{{...}}), %
; CHECK-NEXT: ret
  %1 = load <4 x float>, <4 x float>* %pb, align 16
  %2 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %1, i32 96)
  ret <4 x float> %2
}

define <4 x float> @insertps_from_vector_load_offset_2(<4 x float> %a, <4 x float>* nocapture readonly %pb, i64 %index) {
; CHECK-LABEL: insertps_from_vector_load_offset_2:
; On X32, account for the argument's move to registers
; X32: movl    4(%esp), %eax
; X32: movl    8(%esp), %ecx
; CHECK-NOT: mov
;; Try to match a bit more of the instr, since we need the load's offset.
; CHECK: vinsertps    $192, 12(%{{...}},%{{...}}), %
; CHECK-NEXT: ret
  %1 = getelementptr inbounds <4 x float>, <4 x float>* %pb, i64 %index
  %2 = load <4 x float>, <4 x float>* %1, align 16
  %3 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %2, i32 192)
  ret <4 x float> %3
}

define <4 x float> @insertps_from_broadcast_loadf32(<4 x float> %a, float* nocapture readonly %fb, i64 %index) {
; CHECK-LABEL: insertps_from_broadcast_loadf32:
; On X32, account for the arguments' move to registers
; X32: movl    8(%esp), %eax
; X32: movl    4(%esp), %ecx
; CHECK-NOT: mov
; CHECK: insertps    $48
; CHECK-NEXT: ret
  %1 = getelementptr inbounds float, float* %fb, i64 %index
  %2 = load float, float* %1, align 4
  %3 = insertelement <4 x float> undef, float %2, i32 0
  %4 = insertelement <4 x float> %3, float %2, i32 1
  %5 = insertelement <4 x float> %4, float %2, i32 2
  %6 = insertelement <4 x float> %5, float %2, i32 3
  %7 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %6, i32 48)
  ret <4 x float> %7
}

define <4 x float> @insertps_from_broadcast_loadv4f32(<4 x float> %a, <4 x float>* nocapture readonly %b) {
; CHECK-LABEL: insertps_from_broadcast_loadv4f32:
; On X32, account for the arguments' move to registers
; X32: movl    4(%esp), %{{...}}
; CHECK-NOT: mov
; CHECK: insertps    $48
; CHECK-NEXT: ret
  %1 = load <4 x float>, <4 x float>* %b, align 4
  %2 = extractelement <4 x float> %1, i32 0
  %3 = insertelement <4 x float> undef, float %2, i32 0
  %4 = insertelement <4 x float> %3, float %2, i32 1
  %5 = insertelement <4 x float> %4, float %2, i32 2
  %6 = insertelement <4 x float> %5, float %2, i32 3
  %7 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %6, i32 48)
  ret <4 x float> %7
}

;; FIXME: We're emitting an extraneous pshufd/vbroadcast.
define <4 x float> @insertps_from_broadcast_multiple_use(<4 x float> %a, <4 x float> %b, <4 x float> %c, <4 x float> %d, float* nocapture readonly %fb, i64 %index) {
; CHECK-LABEL: insertps_from_broadcast_multiple_use:
; On X32, account for the arguments' move to registers
; X32: movl    8(%esp), %eax
; X32: movl    4(%esp), %ecx
; CHECK: vbroadcastss
; CHECK-NOT: mov
; CHECK: insertps    $48
; CHECK: insertps    $48
; CHECK: insertps    $48
; CHECK: insertps    $48
; CHECK: vaddps
; CHECK: vaddps
; CHECK: vaddps
; CHECK-NEXT: ret
  %1 = getelementptr inbounds float, float* %fb, i64 %index
  %2 = load float, float* %1, align 4
  %3 = insertelement <4 x float> undef, float %2, i32 0
  %4 = insertelement <4 x float> %3, float %2, i32 1
  %5 = insertelement <4 x float> %4, float %2, i32 2
  %6 = insertelement <4 x float> %5, float %2, i32 3
  %7 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %6, i32 48)
  %8 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %b, <4 x float> %6, i32 48)
  %9 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %c, <4 x float> %6, i32 48)
  %10 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %d, <4 x float> %6, i32 48)
  %11 = fadd <4 x float> %7, %8
  %12 = fadd <4 x float> %9, %10
  %13 = fadd <4 x float> %11, %12
  ret <4 x float> %13
}