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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-linux-gnu < %s | FileCheck %s
; Check that expensive divides are expanded into a more performant sequence
;
; SDIV
;
define <vscale x 16 x i8> @sdiv_i8(<vscale x 16 x i8> %a) #0 {
; CHECK-LABEL: sdiv_i8:
; CHECK: // %bb.0:
; CHECK-NEXT: mov z1.b, #86 // =0x56
; CHECK-NEXT: ptrue p0.b
; CHECK-NEXT: smulh z0.b, p0/m, z0.b, z1.b
; CHECK-NEXT: lsr z1.b, z0.b, #7
; CHECK-NEXT: add z0.b, z0.b, z1.b
; CHECK-NEXT: ret
%div = sdiv <vscale x 16 x i8> %a, shufflevector (<vscale x 16 x i8> insertelement (<vscale x 16 x i8> undef, i8 3, i32 0), <vscale x 16 x i8> undef, <vscale x 16 x i32> zeroinitializer)
ret <vscale x 16 x i8> %div
}
define <vscale x 8 x i16> @sdiv_i16(<vscale x 8 x i16> %a) #0 {
; CHECK-LABEL: sdiv_i16:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #21846
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: mov z1.h, w8
; CHECK-NEXT: smulh z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: lsr z1.h, z0.h, #15
; CHECK-NEXT: add z0.h, z0.h, z1.h
; CHECK-NEXT: ret
%div = sdiv <vscale x 8 x i16> %a, shufflevector (<vscale x 8 x i16> insertelement (<vscale x 8 x i16> undef, i16 3, i32 0), <vscale x 8 x i16> undef, <vscale x 8 x i32> zeroinitializer)
ret <vscale x 8 x i16> %div
}
define <vscale x 4 x i32> @sdiv_i32(<vscale x 4 x i32> %a) #0 {
; CHECK-LABEL: sdiv_i32:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #21846
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: movk w8, #21845, lsl #16
; CHECK-NEXT: mov z1.s, w8
; CHECK-NEXT: smulh z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: lsr z1.s, z0.s, #31
; CHECK-NEXT: add z0.s, z0.s, z1.s
; CHECK-NEXT: ret
%div = sdiv <vscale x 4 x i32> %a, shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> undef, i32 3, i32 0), <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer)
ret <vscale x 4 x i32> %div
}
define <vscale x 2 x i64> @sdiv_i64(<vscale x 2 x i64> %a) #0 {
; CHECK-LABEL: sdiv_i64:
; CHECK: // %bb.0:
; CHECK-NEXT: mov x8, #6148914691236517205
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: movk x8, #21846
; CHECK-NEXT: mov z1.d, x8
; CHECK-NEXT: smulh z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: lsr z1.d, z0.d, #63
; CHECK-NEXT: add z0.d, z0.d, z1.d
; CHECK-NEXT: ret
%div = sdiv <vscale x 2 x i64> %a, shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> undef, i64 3, i32 0), <vscale x 2 x i64> undef, <vscale x 2 x i32> zeroinitializer)
ret <vscale x 2 x i64> %div
}
;
; UDIV
;
define <vscale x 16 x i8> @udiv_i8(<vscale x 16 x i8> %a) #0 {
; CHECK-LABEL: udiv_i8:
; CHECK: // %bb.0:
; CHECK-NEXT: mov z1.b, #-85 // =0xffffffffffffffab
; CHECK-NEXT: ptrue p0.b
; CHECK-NEXT: umulh z0.b, p0/m, z0.b, z1.b
; CHECK-NEXT: lsr z0.b, z0.b, #1
; CHECK-NEXT: ret
%div = udiv <vscale x 16 x i8> %a, shufflevector (<vscale x 16 x i8> insertelement (<vscale x 16 x i8> undef, i8 3, i32 0), <vscale x 16 x i8> undef, <vscale x 16 x i32> zeroinitializer)
ret <vscale x 16 x i8> %div
}
define <vscale x 8 x i16> @udiv_i16(<vscale x 8 x i16> %a) #0 {
; CHECK-LABEL: udiv_i16:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #-21845
; CHECK-NEXT: ptrue p0.h
; CHECK-NEXT: mov z1.h, w8
; CHECK-NEXT: umulh z0.h, p0/m, z0.h, z1.h
; CHECK-NEXT: lsr z0.h, z0.h, #1
; CHECK-NEXT: ret
%div = udiv <vscale x 8 x i16> %a, shufflevector (<vscale x 8 x i16> insertelement (<vscale x 8 x i16> undef, i16 3, i32 0), <vscale x 8 x i16> undef, <vscale x 8 x i32> zeroinitializer)
ret <vscale x 8 x i16> %div
}
define <vscale x 4 x i32> @udiv_i32(<vscale x 4 x i32> %a) #0 {
; CHECK-LABEL: udiv_i32:
; CHECK: // %bb.0:
; CHECK-NEXT: mov w8, #43691
; CHECK-NEXT: ptrue p0.s
; CHECK-NEXT: movk w8, #43690, lsl #16
; CHECK-NEXT: mov z1.s, w8
; CHECK-NEXT: umulh z0.s, p0/m, z0.s, z1.s
; CHECK-NEXT: lsr z0.s, z0.s, #1
; CHECK-NEXT: ret
%div = udiv <vscale x 4 x i32> %a, shufflevector (<vscale x 4 x i32> insertelement (<vscale x 4 x i32> undef, i32 3, i32 0), <vscale x 4 x i32> undef, <vscale x 4 x i32> zeroinitializer)
ret <vscale x 4 x i32> %div
}
define <vscale x 2 x i64> @udiv_i64(<vscale x 2 x i64> %a) #0 {
; CHECK-LABEL: udiv_i64:
; CHECK: // %bb.0:
; CHECK-NEXT: mov x8, #-6148914691236517206
; CHECK-NEXT: ptrue p0.d
; CHECK-NEXT: movk x8, #43691
; CHECK-NEXT: mov z1.d, x8
; CHECK-NEXT: umulh z0.d, p0/m, z0.d, z1.d
; CHECK-NEXT: lsr z0.d, z0.d, #1
; CHECK-NEXT: ret
%div = udiv <vscale x 2 x i64> %a, shufflevector (<vscale x 2 x i64> insertelement (<vscale x 2 x i64> undef, i64 3, i32 0), <vscale x 2 x i64> undef, <vscale x 2 x i32> zeroinitializer)
ret <vscale x 2 x i64> %div
}
attributes #0 = { "target-features"="+sve" }
|
