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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -passes='default<O3>' -rotation-max-header-size=0 -S < %s | FileCheck %s --check-prefix=HOIST
; RUN: opt -passes='default<O3>' -rotation-max-header-size=1 -S < %s | FileCheck %s --check-prefix=HOIST
; RUN: opt -passes='default<O3>' -rotation-max-header-size=2 -S < %s | FileCheck %s --check-prefix=ROTATE
; RUN: opt -passes='default<O3>' -rotation-max-header-size=3 -S < %s | FileCheck %s --check-prefix=ROTATE
; This example is produced from a very basic C code:
;
; void f0();
; void f1();
; void f2();
;
; void loop(int width) {
; if(width < 1)
; return;
; for(int i = 0; i < width - 1; ++i) {
; f0();
; f1();
; }
; f0();
; f2();
; }
; We have a choice here. We can either
; * hoist the f0() call into loop header,
; * which potentially makes loop rotation unprofitable since loop header might
; have grown above certain threshold, and such unrotated loops will be
; ignored by LoopVectorizer, preventing vectorization
; * or loop rotation will succeed, resulting in some weird PHIs that will also
; harm vectorization
; * or not hoist f0() call before performing loop rotation,
; at the cost of potential code bloat and/or potentially successfully rotating
; the loops, vectorizing them at the cost of compile time.
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
declare void @f0()
declare void @f1()
declare void @f2()
declare void @llvm.lifetime.start.p0(i64 immarg, ptr nocapture)
declare void @llvm.lifetime.end.p0(i64 immarg, ptr nocapture)
define void @_Z4loopi(i32 %width) {
; HOIST-LABEL: @_Z4loopi(
; HOIST-NEXT: entry:
; HOIST-NEXT: [[CMP:%.*]] = icmp slt i32 [[WIDTH:%.*]], 1
; HOIST-NEXT: br i1 [[CMP]], label [[RETURN:%.*]], label [[FOR_COND_PREHEADER:%.*]]
; HOIST: for.cond.preheader:
; HOIST-NEXT: [[SUB:%.*]] = add nsw i32 [[WIDTH]], -1
; HOIST-NEXT: br label [[FOR_COND:%.*]]
; HOIST: for.cond:
; HOIST-NEXT: [[I_0:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY:%.*]] ], [ 0, [[FOR_COND_PREHEADER]] ]
; HOIST-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i32 [[I_0]], [[SUB]]
; HOIST-NEXT: tail call void @f0()
; HOIST-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY]]
; HOIST: for.cond.cleanup:
; HOIST-NEXT: tail call void @f2()
; HOIST-NEXT: br label [[RETURN]]
; HOIST: for.body:
; HOIST-NEXT: tail call void @f1()
; HOIST-NEXT: [[INC]] = add nuw i32 [[I_0]], 1
; HOIST-NEXT: br label [[FOR_COND]]
; HOIST: return:
; HOIST-NEXT: ret void
;
; ROTATE-LABEL: @_Z4loopi(
; ROTATE-NEXT: entry:
; ROTATE-NEXT: [[CMP:%.*]] = icmp slt i32 [[WIDTH:%.*]], 1
; ROTATE-NEXT: br i1 [[CMP]], label [[RETURN:%.*]], label [[FOR_COND_PREHEADER:%.*]]
; ROTATE: for.cond.preheader:
; ROTATE-NEXT: [[CMP13_NOT:%.*]] = icmp eq i32 [[WIDTH]], 1
; ROTATE-NEXT: br i1 [[CMP13_NOT]], label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY_PREHEADER:%.*]]
; ROTATE: for.body.preheader:
; ROTATE-NEXT: [[TMP0:%.*]] = add nsw i32 [[WIDTH]], -2
; ROTATE-NEXT: br label [[FOR_BODY:%.*]]
; ROTATE: for.cond.cleanup:
; ROTATE-NEXT: tail call void @f0()
; ROTATE-NEXT: tail call void @f2()
; ROTATE-NEXT: br label [[RETURN]]
; ROTATE: for.body:
; ROTATE-NEXT: [[I_04:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_BODY]] ], [ 0, [[FOR_BODY_PREHEADER]] ]
; ROTATE-NEXT: tail call void @f0()
; ROTATE-NEXT: tail call void @f1()
; ROTATE-NEXT: [[INC]] = add nuw nsw i32 [[I_04]], 1
; ROTATE-NEXT: [[EXITCOND_NOT:%.*]] = icmp eq i32 [[I_04]], [[TMP0]]
; ROTATE-NEXT: br i1 [[EXITCOND_NOT]], label [[FOR_COND_CLEANUP]], label [[FOR_BODY]]
; ROTATE: return:
; ROTATE-NEXT: ret void
;
entry:
%width.addr = alloca i32, align 4
%i = alloca i32, align 4
store i32 %width, ptr %width.addr, align 4
%i1 = load i32, ptr %width.addr, align 4
%cmp = icmp slt i32 %i1, 1
br i1 %cmp, label %if.then, label %if.end
if.then:
br label %return
if.end:
call void @llvm.lifetime.start.p0(i64 4, ptr %i)
store i32 0, ptr %i, align 4
br label %for.cond
for.cond:
%i3 = load i32, ptr %i, align 4
%i4 = load i32, ptr %width.addr, align 4
%sub = sub nsw i32 %i4, 1
%cmp1 = icmp slt i32 %i3, %sub
br i1 %cmp1, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
call void @llvm.lifetime.end.p0(i64 4, ptr %i)
br label %for.end
for.body:
call void @f0()
call void @f1()
br label %for.inc
for.inc:
%i6 = load i32, ptr %i, align 4
%inc = add nsw i32 %i6, 1
store i32 %inc, ptr %i, align 4
br label %for.cond
for.end:
call void @f0()
call void @f2()
br label %return
return:
ret void
}
|
