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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -function-specialization -deadargelim -force-function-specialization -S < %s | FileCheck %s
; RUN: opt -function-specialization -func-specialization-max-iters=1 -deadargelim -force-function-specialization -S < %s | FileCheck %s
; RUN: opt -function-specialization -func-specialization-max-iters=0 -deadargelim -force-function-specialization -S < %s | FileCheck %s --check-prefix=DISABLED
; RUN: opt -function-specialization -func-specialization-avg-iters-cost=1 -deadargelim -force-function-specialization -S < %s | FileCheck %s
; DISABLED-NOT: @func.1(
; DISABLED-NOT: @func.2(
define internal i32 @func(i32* %0, i32 %1, void (i32*)* nocapture %2) {
%4 = alloca i32, align 4
store i32 %1, i32* %4, align 4
%5 = load i32, i32* %4, align 4
%6 = icmp slt i32 %5, 1
br i1 %6, label %14, label %7
7: ; preds = %3
%8 = load i32, i32* %4, align 4
%9 = sext i32 %8 to i64
%10 = getelementptr inbounds i32, i32* %0, i64 %9
call void %2(i32* %10)
%11 = load i32, i32* %4, align 4
%12 = add nsw i32 %11, -1
%13 = call i32 @func(i32* %0, i32 %12, void (i32*)* %2)
br label %14
14: ; preds = %3, %7
ret i32 0
}
define internal void @increment(i32* nocapture %0) {
%2 = load i32, i32* %0, align 4
%3 = add nsw i32 %2, 1
store i32 %3, i32* %0, align 4
ret void
}
define internal void @decrement(i32* nocapture %0) {
%2 = load i32, i32* %0, align 4
%3 = add nsw i32 %2, -1
store i32 %3, i32* %0, align 4
ret void
}
define i32 @main(i32* %0, i32 %1) {
; CHECK: [[TMP3:%.*]] = call i32 @func.2(i32* [[TMP0:%.*]], i32 [[TMP1:%.*]])
%3 = call i32 @func(i32* %0, i32 %1, void (i32*)* nonnull @increment)
; CHECK: [[TMP4:%.*]] = call i32 @func.1(i32* [[TMP0]], i32 [[TMP3]])
%4 = call i32 @func(i32* %0, i32 %3, void (i32*)* nonnull @decrement)
ret i32 %4
}
; CHECK: @func.1(
; CHECK: [[TMP3:%.*]] = alloca i32, align 4
; CHECK: store i32 [[TMP1:%.*]], i32* [[TMP3]], align 4
; CHECK: [[TMP4:%.*]] = load i32, i32* [[TMP3]], align 4
; CHECK: [[TMP5:%.*]] = icmp slt i32 [[TMP4]], 1
; CHECK: br i1 [[TMP5]], label [[TMP13:%.*]], label [[TMP6:%.*]]
; CHECK: 6:
; CHECK: [[TMP7:%.*]] = load i32, i32* [[TMP3]], align 4
; CHECK: [[TMP8:%.*]] = sext i32 [[TMP7]] to i64
; CHECK: [[TMP9:%.*]] = getelementptr inbounds i32, i32* [[TMP0:%.*]], i64 [[TMP8]]
; CHECK: call void @decrement(i32* [[TMP9]])
; CHECK: [[TMP10:%.*]] = load i32, i32* [[TMP3]], align 4
; CHECK: [[TMP11:%.*]] = add nsw i32 [[TMP10]], -1
; CHECK: [[TMP12:%.*]] = call i32 @func.1(i32* [[TMP0]], i32 [[TMP11]])
; CHECK: br label [[TMP13]]
; CHECK: 13:
; CHECK: ret i32 0
;
;
; CHECK: @func.2(
; CHECK: [[TMP3:%.*]] = alloca i32, align 4
; CHECK: store i32 [[TMP1:%.*]], i32* [[TMP3]], align 4
; CHECK: [[TMP4:%.*]] = load i32, i32* [[TMP3]], align 4
; CHECK: [[TMP5:%.*]] = icmp slt i32 [[TMP4]], 1
; CHECK: br i1 [[TMP5]], label [[TMP13:%.*]], label [[TMP6:%.*]]
; CHECK: 6:
; CHECK: [[TMP7:%.*]] = load i32, i32* [[TMP3]], align 4
; CHECK: [[TMP8:%.*]] = sext i32 [[TMP7]] to i64
; CHECK: [[TMP9:%.*]] = getelementptr inbounds i32, i32* [[TMP0:%.*]], i64 [[TMP8]]
; CHECK: call void @increment(i32* [[TMP9]])
; CHECK: [[TMP10:%.*]] = load i32, i32* [[TMP3]], align 4
; CHECK: [[TMP11:%.*]] = add nsw i32 [[TMP10]], -1
; CHECK: [[TMP12:%.*]] = call i32 @func.2(i32* [[TMP0]], i32 [[TMP11]])
; CHECK: br label [[TMP13]]
; CHECK: ret i32 0
|
