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
|
; RUN: llc < %s -mtriple=x86_64-apple-darwin -mattr=+mmx,+sse2 | FileCheck %s
; There are no MMX operations here, so we use XMM or i64.
; CHECK: ti8
define void @ti8(double %a, double %b) nounwind {
entry:
%tmp1 = bitcast double %a to <8 x i8>
%tmp2 = bitcast double %b to <8 x i8>
%tmp3 = add <8 x i8> %tmp1, %tmp2
; CHECK: paddw
store <8 x i8> %tmp3, <8 x i8>* null
ret void
}
; CHECK: ti16
define void @ti16(double %a, double %b) nounwind {
entry:
%tmp1 = bitcast double %a to <4 x i16>
%tmp2 = bitcast double %b to <4 x i16>
%tmp3 = add <4 x i16> %tmp1, %tmp2
; CHECK: paddd
store <4 x i16> %tmp3, <4 x i16>* null
ret void
}
; CHECK: ti32
define void @ti32(double %a, double %b) nounwind {
entry:
%tmp1 = bitcast double %a to <2 x i32>
%tmp2 = bitcast double %b to <2 x i32>
%tmp3 = add <2 x i32> %tmp1, %tmp2
; CHECK: paddq
store <2 x i32> %tmp3, <2 x i32>* null
ret void
}
; CHECK: ti64
define void @ti64(double %a, double %b) nounwind {
entry:
%tmp1 = bitcast double %a to <1 x i64>
%tmp2 = bitcast double %b to <1 x i64>
%tmp3 = add <1 x i64> %tmp1, %tmp2
; CHECK: addq
store <1 x i64> %tmp3, <1 x i64>* null
ret void
}
; MMX intrinsics calls get us MMX instructions.
; CHECK: ti8a
define void @ti8a(double %a, double %b) nounwind {
entry:
%tmp1 = bitcast double %a to x86_mmx
; CHECK: movdq2q
%tmp2 = bitcast double %b to x86_mmx
; CHECK: movdq2q
%tmp3 = tail call x86_mmx @llvm.x86.mmx.padd.b(x86_mmx %tmp1, x86_mmx %tmp2)
store x86_mmx %tmp3, x86_mmx* null
ret void
}
; CHECK: ti16a
define void @ti16a(double %a, double %b) nounwind {
entry:
%tmp1 = bitcast double %a to x86_mmx
; CHECK: movdq2q
%tmp2 = bitcast double %b to x86_mmx
; CHECK: movdq2q
%tmp3 = tail call x86_mmx @llvm.x86.mmx.padd.w(x86_mmx %tmp1, x86_mmx %tmp2)
store x86_mmx %tmp3, x86_mmx* null
ret void
}
; CHECK: ti32a
define void @ti32a(double %a, double %b) nounwind {
entry:
%tmp1 = bitcast double %a to x86_mmx
; CHECK: movdq2q
%tmp2 = bitcast double %b to x86_mmx
; CHECK: movdq2q
%tmp3 = tail call x86_mmx @llvm.x86.mmx.padd.d(x86_mmx %tmp1, x86_mmx %tmp2)
store x86_mmx %tmp3, x86_mmx* null
ret void
}
; CHECK: ti64a
define void @ti64a(double %a, double %b) nounwind {
entry:
%tmp1 = bitcast double %a to x86_mmx
; CHECK: movdq2q
%tmp2 = bitcast double %b to x86_mmx
; CHECK: movdq2q
%tmp3 = tail call x86_mmx @llvm.x86.mmx.padd.q(x86_mmx %tmp1, x86_mmx %tmp2)
store x86_mmx %tmp3, x86_mmx* null
ret void
}
declare x86_mmx @llvm.x86.mmx.padd.b(x86_mmx, x86_mmx)
declare x86_mmx @llvm.x86.mmx.padd.w(x86_mmx, x86_mmx)
declare x86_mmx @llvm.x86.mmx.padd.d(x86_mmx, x86_mmx)
declare x86_mmx @llvm.x86.mmx.padd.q(x86_mmx, x86_mmx)
|
