summaryrefslogtreecommitdiff
path: root/test/CodeGen/X86/avx-basic.ll
blob: 6857bb8bd1128ff3d3c9ff1f7d52e52ff2e3b35c (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
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mcpu=corei7-avx -mattr=+avx | FileCheck %s

@x = common global <8 x float> zeroinitializer, align 32
@y = common global <4 x double> zeroinitializer, align 32
@z = common global <4 x float> zeroinitializer, align 16

define void @zero128() nounwind ssp {
entry:
  ; CHECK: vxorps
  ; CHECK: vmovaps
  store <4 x float> zeroinitializer, <4 x float>* @z, align 16
  ret void
}

define void @zero256() nounwind ssp {
entry:
  ; CHECK: vxorps
  ; CHECK: vmovaps
  ; CHECK: vmovaps
  store <8 x float> zeroinitializer, <8 x float>* @x, align 32
  store <4 x double> zeroinitializer, <4 x double>* @y, align 32
  ret void
}

; CHECK: vpcmpeqd
; CHECK: vinsertf128 $1
define void @ones([0 x float]* nocapture %RET, [0 x float]* nocapture %aFOO) nounwind {
allocas:
  %ptr2vec615 = bitcast [0 x float]* %RET to <8 x float>*
  store <8 x float> <float 0xFFFFFFFFE0000000, float 0xFFFFFFFFE0000000, float
0xFFFFFFFFE0000000, float 0xFFFFFFFFE0000000, float 0xFFFFFFFFE0000000, float
0xFFFFFFFFE0000000, float 0xFFFFFFFFE0000000, float 0xFFFFFFFFE0000000>, <8 x
float>* %ptr2vec615, align 32
  ret void
}

; CHECK: vpcmpeqd
; CHECK: vinsertf128 $1
define void @ones2([0 x i32]* nocapture %RET, [0 x i32]* nocapture %aFOO) nounwind {
allocas:
  %ptr2vec615 = bitcast [0 x i32]* %RET to <8 x i32>*
  store <8 x i32> <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>, <8 x i32>* %ptr2vec615, align 32
  ret void
}

;;; Just make sure this doesn't crash
; CHECK: _ISelCrash
define <4 x i64> @ISelCrash(<4 x i64> %a) nounwind uwtable readnone ssp {
entry:
  %shuffle = shufflevector <4 x i64> %a, <4 x i64> undef, <4 x i32> <i32 2, i32 3, i32 4, i32 4>
  ret <4 x i64> %shuffle
}

;;; Don't crash on movd
; CHECK: _VMOVZQI2PQI
; CHECK: vmovd (%
define <8 x i32> @VMOVZQI2PQI([0 x float]* nocapture %aFOO) nounwind {
allocas:
  %ptrcast.i33.i = bitcast [0 x float]* %aFOO to i32*
  %val.i34.i = load i32, i32* %ptrcast.i33.i, align 4
  %ptroffset.i22.i992 = getelementptr [0 x float], [0 x float]* %aFOO, i64 0, i64 1
  %ptrcast.i23.i = bitcast float* %ptroffset.i22.i992 to i32*
  %val.i24.i = load i32, i32* %ptrcast.i23.i, align 4
  %updatedret.i30.i = insertelement <8 x i32> undef, i32 %val.i34.i, i32 1
  ret <8 x i32> %updatedret.i30.i
}

;;;; Don't crash on fneg
; rdar://10566486
; CHECK: fneg
; CHECK: vxorps
define <16 x float> @fneg(<16 x float> %a) nounwind {
  %1 = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %a
  ret <16 x float> %1
}

;;; Don't crash on build vector
; CHECK: @build_vec_16x16
; CHECK: vmovd
define <16 x i16> @build_vec_16x16(i16 %a) nounwind readonly {
  %res = insertelement <16 x i16> <i16 undef, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0>, i16 %a, i32 0
  ret <16 x i16> %res
}

;;; Check that VMOVPQIto64rr generates the assembly string "vmovq".  Previously
;;; an incorrect mnemonic of "movd" was printed for this instruction.
; CHECK: VMOVPQIto64rr
; CHECK: vmovq
define i64 @VMOVPQIto64rr(<2 x i64> %a) {
entry:
  %vecext.i = extractelement <2 x i64> %a, i32 0
  ret i64 %vecext.i
}

; PR22685
; CHECK: mov00
; CHECK: vmovss
define <8 x float> @mov00_8f32(float* %ptr) {
  %val = load float, float* %ptr
  %vec = insertelement <8 x float> zeroinitializer, float %val, i32 0
  ret <8 x float> %vec
}