File: narrow.ll

package info (click to toggle)
llvm-toolchain-6.0 1:6.0-1~bpo9+1
  • links: PTS, VCS
  • area: main
  • in suites: stretch-backports
  • size: 594,652 kB
  • sloc: cpp: 3,044,500; ansic: 595,051; asm: 271,890; python: 128,923; objc: 106,554; sh: 21,854; lisp: 10,191; pascal: 6,094; ml: 5,544; perl: 5,265; makefile: 2,214; cs: 2,027; xml: 686; php: 212; csh: 117
file content (239 lines) | stat: -rw-r--r-- 7,813 bytes parent folder | download | duplicates (9)
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
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -instcombine -S | FileCheck %s

target datalayout = "n8:16:32:64"

; Eliminating the casts in this testcase (by narrowing the AND operation)
; allows instcombine to realize the function always returns false.

define i1 @test1(i32 %A, i32 %B) {
; CHECK-LABEL: @test1(
; CHECK-NEXT:    ret i1 false
;
  %C1 = icmp slt i32 %A, %B
  %ELIM1 = zext i1 %C1 to i32
  %C2 = icmp sgt i32 %A, %B
  %ELIM2 = zext i1 %C2 to i32
  %C3 = and i32 %ELIM1, %ELIM2
  %ELIM3 = trunc i32 %C3 to i1
  ret i1 %ELIM3
}

; The next 6 (3 logic ops * (scalar+vector)) tests show potential cases for narrowing a bitwise logic op.

define i32 @shrink_xor(i64 %a) {
; CHECK-LABEL: @shrink_xor(
; CHECK-NEXT:    [[TMP1:%.*]] = trunc i64 %a to i32
; CHECK-NEXT:    [[TRUNC:%.*]] = xor i32 [[TMP1]], 1
; CHECK-NEXT:    ret i32 [[TRUNC]]
;
  %xor = xor i64 %a, 1
  %trunc = trunc i64 %xor to i32
  ret i32 %trunc
}

; Vectors (with splat constants) should get the same transform.

define <2 x i32> @shrink_xor_vec(<2 x i64> %a) {
; CHECK-LABEL: @shrink_xor_vec(
; CHECK-NEXT:    [[TMP1:%.*]] = trunc <2 x i64> %a to <2 x i32>
; CHECK-NEXT:    [[TRUNC:%.*]] = xor <2 x i32> [[TMP1]], <i32 2, i32 2>
; CHECK-NEXT:    ret <2 x i32> [[TRUNC]]
;
  %xor = xor <2 x i64> %a, <i64 2, i64 2>
  %trunc = trunc <2 x i64> %xor to <2 x i32>
  ret <2 x i32> %trunc
}

; Source and dest types are not in the datalayout.

define i3 @shrink_or(i6 %a) {
; CHECK-LABEL: @shrink_or(
; CHECK-NEXT:    [[TMP1:%.*]] = trunc i6 %a to i3
; CHECK-NEXT:    [[TRUNC:%.*]] = or i3 [[TMP1]], 1
; CHECK-NEXT:    ret i3 [[TRUNC]]
;
  %or = or i6 %a, 33
  %trunc = trunc i6 %or to i3
  ret i3 %trunc
}

; Vectors (with non-splat constants) should get the same transform.

define <2 x i8> @shrink_or_vec(<2 x i16> %a) {
; CHECK-LABEL: @shrink_or_vec(
; CHECK-NEXT:    [[TMP1:%.*]] = trunc <2 x i16> %a to <2 x i8>
; CHECK-NEXT:    [[TRUNC:%.*]] = or <2 x i8> [[TMP1]], <i8 -1, i8 0>
; CHECK-NEXT:    ret <2 x i8> [[TRUNC]]
;
  %or = or <2 x i16> %a, <i16 -1, i16 256>
  %trunc = trunc <2 x i16> %or to <2 x i8>
  ret <2 x i8> %trunc
}

; We discriminate against weird types.

define i31 @shrink_and(i64 %a) {
; CHECK-LABEL: @shrink_and(
; CHECK-NEXT:    [[AND:%.*]] = and i64 %a, 42
; CHECK-NEXT:    [[TRUNC:%.*]] = trunc i64 [[AND]] to i31
; CHECK-NEXT:    ret i31 [[TRUNC]]
;
  %and = and i64 %a, 42
  %trunc = trunc i64 %and to i31
  ret i31 %trunc
}

; Chop the top of the constant(s) if needed.

define <2 x i32> @shrink_and_vec(<2 x i33> %a) {
; CHECK-LABEL: @shrink_and_vec(
; CHECK-NEXT:    [[TMP1:%.*]] = trunc <2 x i33> %a to <2 x i32>
; CHECK-NEXT:    [[TRUNC:%.*]] = and <2 x i32> [[TMP1]], <i32 0, i32 6>
; CHECK-NEXT:    ret <2 x i32> [[TRUNC]]
;
  %and = and <2 x i33> %a, <i33 4294967296, i33 6>
  %trunc = trunc <2 x i33> %and to <2 x i32>
  ret <2 x i32> %trunc
}

; FIXME:
; This is based on an 'any_of' loop construct.
; By narrowing the phi and logic op, we simplify away the zext and the final icmp.

define i1 @searchArray1(i32 %needle, i32* %haystack) {
; CHECK-LABEL: @searchArray1(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[INDVAR:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[INDVAR_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[FOUND:%.*]] = phi i8 [ 0, [[ENTRY]] ], [ [[OR:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[TMP0:%.*]] = sext i32 [[INDVAR]] to i64
; CHECK-NEXT:    [[IDX:%.*]] = getelementptr i32, i32* [[HAYSTACK:%.*]], i64 [[TMP0]]
; CHECK-NEXT:    [[LD:%.*]] = load i32, i32* [[IDX]], align 4
; CHECK-NEXT:    [[CMP1:%.*]] = icmp eq i32 [[LD]], [[NEEDLE:%.*]]
; CHECK-NEXT:    [[ZEXT:%.*]] = zext i1 [[CMP1]] to i8
; CHECK-NEXT:    [[OR]] = or i8 [[FOUND]], [[ZEXT]]
; CHECK-NEXT:    [[INDVAR_NEXT]] = add i32 [[INDVAR]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[INDVAR_NEXT]], 1000
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[EXIT:%.*]], label [[LOOP]]
; CHECK:       exit:
; CHECK-NEXT:    [[TOBOOL:%.*]] = icmp ne i8 [[OR]], 0
; CHECK-NEXT:    ret i1 [[TOBOOL]]
;
entry:
  br label %loop

loop:
  %indvar = phi i32 [ 0, %entry ], [ %indvar.next, %loop ]
  %found = phi i8 [ 0, %entry ], [ %or, %loop ]
  %idx = getelementptr i32, i32* %haystack, i32 %indvar
  %ld = load i32, i32* %idx
  %cmp1 = icmp eq i32 %ld, %needle
  %zext = zext i1 %cmp1 to i8
  %or = or i8 %found, %zext
  %indvar.next = add i32 %indvar, 1
  %exitcond = icmp eq i32 %indvar.next, 1000
  br i1 %exitcond, label %exit, label %loop

exit:
  %tobool = icmp ne i8 %or, 0
  ret i1 %tobool
}

; FIXME:
; This is based on an 'all_of' loop construct.
; By narrowing the phi and logic op, we simplify away the zext and the final icmp.

define i1 @searchArray2(i32 %hay, i32* %haystack) {
; CHECK-LABEL: @searchArray2(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br label [[LOOP:%.*]]
; CHECK:       loop:
; CHECK-NEXT:    [[INDVAR:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INDVAR_NEXT:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[FOUND:%.*]] = phi i8 [ 1, [[ENTRY]] ], [ [[AND:%.*]], [[LOOP]] ]
; CHECK-NEXT:    [[IDX:%.*]] = getelementptr i32, i32* [[HAYSTACK:%.*]], i64 [[INDVAR]]
; CHECK-NEXT:    [[LD:%.*]] = load i32, i32* [[IDX]], align 4
; CHECK-NEXT:    [[CMP1:%.*]] = icmp eq i32 [[LD]], [[HAY:%.*]]
; CHECK-NEXT:    [[ZEXT:%.*]] = zext i1 [[CMP1]] to i8
; CHECK-NEXT:    [[AND]] = and i8 [[FOUND]], [[ZEXT]]
; CHECK-NEXT:    [[INDVAR_NEXT]] = add i64 [[INDVAR]], 1
; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i64 [[INDVAR_NEXT]], 1000
; CHECK-NEXT:    br i1 [[EXITCOND]], label [[EXIT:%.*]], label [[LOOP]]
; CHECK:       exit:
; CHECK-NEXT:    [[TOBOOL:%.*]] = icmp ne i8 [[AND]], 0
; CHECK-NEXT:    ret i1 [[TOBOOL]]
;
entry:
  br label %loop

loop:
  %indvar = phi i64 [ 0, %entry ], [ %indvar.next, %loop ]
  %found = phi i8 [ 1, %entry ], [ %and, %loop ]
  %idx = getelementptr i32, i32* %haystack, i64 %indvar
  %ld = load i32, i32* %idx
  %cmp1 = icmp eq i32 %ld, %hay
  %zext = zext i1 %cmp1 to i8
  %and = and i8 %found, %zext
  %indvar.next = add i64 %indvar, 1
  %exitcond = icmp eq i64 %indvar.next, 1000
  br i1 %exitcond, label %exit, label %loop

exit:
  %tobool = icmp ne i8 %and, 0
  ret i1 %tobool
}

; FIXME:
; Narrowing should work with an 'xor' and is not limited to bool types.

define i32 @shrinkLogicAndPhi1(i8 %x, i1 %cond) {
; CHECK-LABEL: @shrinkLogicAndPhi1(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 [[COND:%.*]], label [[IF:%.*]], label [[ENDIF:%.*]]
; CHECK:       if:
; CHECK-NEXT:    br label [[ENDIF]]
; CHECK:       endif:
; CHECK-NEXT:    [[PHI:%.*]] = phi i32 [ 21, [[ENTRY:%.*]] ], [ 33, [[IF]] ]
; CHECK-NEXT:    [[ZEXT:%.*]] = zext i8 [[X:%.*]] to i32
; CHECK-NEXT:    [[LOGIC:%.*]] = xor i32 [[PHI]], [[ZEXT]]
; CHECK-NEXT:    ret i32 [[LOGIC]]
;
entry:
  br i1 %cond, label %if, label %endif
if:
  br label %endif
endif:
  %phi = phi i32 [ 21, %entry], [ 33, %if ]
  %zext = zext i8 %x to i32
  %logic = xor i32 %phi, %zext
  ret i32 %logic
}

; FIXME:
; Narrowing should work with an 'xor' and is not limited to bool types.
; Test that commuting the xor operands does not inhibit optimization.

define i32 @shrinkLogicAndPhi2(i8 %x, i1 %cond) {
; CHECK-LABEL: @shrinkLogicAndPhi2(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    br i1 [[COND:%.*]], label [[IF:%.*]], label [[ENDIF:%.*]]
; CHECK:       if:
; CHECK-NEXT:    br label [[ENDIF]]
; CHECK:       endif:
; CHECK-NEXT:    [[PHI:%.*]] = phi i32 [ 21, [[ENTRY:%.*]] ], [ 33, [[IF]] ]
; CHECK-NEXT:    [[ZEXT:%.*]] = zext i8 [[X:%.*]] to i32
; CHECK-NEXT:    [[LOGIC:%.*]] = xor i32 [[PHI]], [[ZEXT]]
; CHECK-NEXT:    ret i32 [[LOGIC]]
;
entry:
  br i1 %cond, label %if, label %endif
if:
  br label %endif
endif:
  %phi = phi i32 [ 21, %entry], [ 33, %if ]
  %zext = zext i8 %x to i32
  %logic = xor i32 %zext, %phi
  ret i32 %logic
}