partally-redundant-left-shift-input-masking-variant-d.ll
5.96 KB
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
137
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -instcombine -S | FileCheck %s
; If we have some pattern that leaves only some low bits set, and then performs
; left-shift of those bits, we can combine those two shifts into a shift+mask.
; There are many variants to this pattern:
; d) (x & ((-1 << maskNbits) >> maskNbits)) << shiftNbits
; simplify to:
; (x << shiftNbits) & (-1 >> ((-(maskNbits+shiftNbits))+32))
; Simple tests.
declare void @use32(i32)
define i32 @t0_basic(i32 %x, i32 %nbits) {
; CHECK-LABEL: @t0_basic(
; CHECK-NEXT: [[T0:%.*]] = shl i32 -1, [[NBITS:%.*]]
; CHECK-NEXT: [[T1:%.*]] = lshr i32 [[T0]], [[NBITS]]
; CHECK-NEXT: [[T3:%.*]] = add i32 [[NBITS]], -1
; CHECK-NEXT: call void @use32(i32 [[T0]])
; CHECK-NEXT: call void @use32(i32 [[T1]])
; CHECK-NEXT: call void @use32(i32 [[T3]])
; CHECK-NEXT: [[TMP1:%.*]] = shl i32 [[X:%.*]], [[T3]]
; CHECK-NEXT: [[T4:%.*]] = and i32 [[TMP1]], 2147483647
; CHECK-NEXT: ret i32 [[T4]]
;
%t0 = shl i32 -1, %nbits
%t1 = lshr i32 %t0, %nbits
%t2 = and i32 %t1, %x
%t3 = add i32 %nbits, -1
call void @use32(i32 %t0)
call void @use32(i32 %t1)
call void @use32(i32 %t3)
%t4 = shl i32 %t2, %t3 ; shift is smaller than mask
ret i32 %t4
}
; Vectors
declare void @use8xi32(<8 x i32>)
define <8 x i32> @t2_vec_splat(<8 x i32> %x, <8 x i32> %nbits) {
; CHECK-LABEL: @t2_vec_splat(
; CHECK-NEXT: [[T0:%.*]] = shl <8 x i32> <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>, [[NBITS:%.*]]
; CHECK-NEXT: [[T1:%.*]] = lshr <8 x i32> [[T0]], [[NBITS]]
; CHECK-NEXT: [[T3:%.*]] = add <8 x i32> [[NBITS]], <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T0]])
; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T1]])
; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T3]])
; CHECK-NEXT: [[TMP1:%.*]] = shl <8 x i32> [[X:%.*]], [[T3]]
; CHECK-NEXT: [[T4:%.*]] = and <8 x i32> [[TMP1]], <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647>
; CHECK-NEXT: ret <8 x i32> [[T4]]
;
%t0 = shl <8 x i32> <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>, %nbits
%t1 = lshr <8 x i32> %t0, %nbits
%t2 = and <8 x i32> %t1, %x
%t3 = add <8 x i32> %nbits, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>
call void @use8xi32(<8 x i32> %t0)
call void @use8xi32(<8 x i32> %t1)
call void @use8xi32(<8 x i32> %t3)
%t4 = shl <8 x i32> %t2, %t3 ; shift is smaller than mask
ret <8 x i32> %t4
}
define <8 x i32> @t2_vec_splat_undef(<8 x i32> %x, <8 x i32> %nbits) {
; CHECK-LABEL: @t2_vec_splat_undef(
; CHECK-NEXT: [[T0:%.*]] = shl <8 x i32> <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>, [[NBITS:%.*]]
; CHECK-NEXT: [[T1:%.*]] = lshr <8 x i32> [[T0]], [[NBITS]]
; CHECK-NEXT: [[T3:%.*]] = add <8 x i32> [[NBITS]], <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>
; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T0]])
; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T1]])
; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T3]])
; CHECK-NEXT: [[TMP1:%.*]] = shl <8 x i32> [[X:%.*]], [[T3]]
; CHECK-NEXT: [[T4:%.*]] = and <8 x i32> [[TMP1]], <i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 2147483647, i32 undef, i32 2147483647>
; CHECK-NEXT: ret <8 x i32> [[T4]]
;
%t0 = shl <8 x i32> <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>, %nbits
%t1 = lshr <8 x i32> %t0, %nbits
%t2 = and <8 x i32> %t1, %x
%t3 = add <8 x i32> %nbits, <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef, i32 -1>
call void @use8xi32(<8 x i32> %t0)
call void @use8xi32(<8 x i32> %t1)
call void @use8xi32(<8 x i32> %t3)
%t4 = shl <8 x i32> %t2, %t3 ; shift is smaller than mask
ret <8 x i32> %t4
}
define <8 x i32> @t2_vec_nonsplat(<8 x i32> %x, <8 x i32> %nbits) {
; CHECK-LABEL: @t2_vec_nonsplat(
; CHECK-NEXT: [[T0:%.*]] = shl <8 x i32> <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>, [[NBITS:%.*]]
; CHECK-NEXT: [[T1:%.*]] = lshr <8 x i32> [[T0]], [[NBITS]]
; CHECK-NEXT: [[T3:%.*]] = add <8 x i32> [[NBITS]], <i32 -32, i32 -31, i32 -1, i32 0, i32 1, i32 31, i32 32, i32 33>
; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T0]])
; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T1]])
; CHECK-NEXT: call void @use8xi32(<8 x i32> [[T3]])
; CHECK-NEXT: [[TMP1:%.*]] = shl <8 x i32> [[X:%.*]], [[T3]]
; CHECK-NEXT: [[T4:%.*]] = and <8 x i32> [[TMP1]], <i32 undef, i32 1, i32 2147483647, i32 -1, i32 -1, i32 -1, i32 -1, i32 undef>
; CHECK-NEXT: ret <8 x i32> [[T4]]
;
%t0 = shl <8 x i32> <i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1, i32 -1>, %nbits
%t1 = lshr <8 x i32> %t0, %nbits
%t2 = and <8 x i32> %t1, %x
%t3 = add <8 x i32> %nbits, <i32 -32, i32 -31, i32 -1, i32 0, i32 1, i32 31, i32 32, i32 33>
call void @use8xi32(<8 x i32> %t0)
call void @use8xi32(<8 x i32> %t1)
call void @use8xi32(<8 x i32> %t3)
%t4 = shl <8 x i32> %t2, %t3 ; shift is smaller than mask
ret <8 x i32> %t4
}
; Extra uses.
define i32 @n3_extrause(i32 %x, i32 %nbits) {
; CHECK-LABEL: @n3_extrause(
; CHECK-NEXT: [[T0:%.*]] = shl i32 -1, [[NBITS:%.*]]
; CHECK-NEXT: [[T1:%.*]] = lshr i32 [[T0]], [[NBITS]]
; CHECK-NEXT: [[T2:%.*]] = and i32 [[T1]], [[X:%.*]]
; CHECK-NEXT: [[T3:%.*]] = add i32 [[NBITS]], -1
; CHECK-NEXT: call void @use32(i32 [[T0]])
; CHECK-NEXT: call void @use32(i32 [[T1]])
; CHECK-NEXT: call void @use32(i32 [[T2]])
; CHECK-NEXT: call void @use32(i32 [[T3]])
; CHECK-NEXT: [[T4:%.*]] = shl i32 [[T2]], [[T3]]
; CHECK-NEXT: ret i32 [[T4]]
;
%t0 = shl i32 -1, %nbits
%t1 = lshr i32 %t0, %nbits
%t2 = and i32 %t1, %x
%t3 = add i32 %nbits, -1
call void @use32(i32 %t0)
call void @use32(i32 %t1)
call void @use32(i32 %t2) ; BAD
call void @use32(i32 %t3)
%t4 = shl i32 %t2, %t3 ; shift is smaller than mask
ret i32 %t4
}