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
|
// Check code generation
// RUN: %clang_cc1 -no-opaque-pointers -verify -triple x86_64-pc-linux-gnu -fopenmp -fopenmp-version=51 -emit-llvm %s -o - | FileCheck %s --check-prefix=IR
// Check same results after serialization round-trip
// RUN: %clang_cc1 -no-opaque-pointers -verify -triple x86_64-pc-linux-gnu -fopenmp -fopenmp-version=51 -emit-pch -o %t %s
// RUN: %clang_cc1 -no-opaque-pointers -verify -triple x86_64-pc-linux-gnu -fopenmp -fopenmp-version=51 -include-pch %t -emit-llvm %s -o - | FileCheck %s --check-prefix=IR
// expected-no-diagnostics
#ifndef HEADER
#define HEADER
// placeholder for loop body code.
extern "C" void body(...) {}
// IR-LABEL: @func(
// IR-NEXT: [[ENTRY:.*]]:
// IR-NEXT: %[[START_ADDR:.+]] = alloca i32, align 4
// IR-NEXT: %[[END_ADDR:.+]] = alloca i32, align 4
// IR-NEXT: %[[STEP_ADDR:.+]] = alloca i32, align 4
// IR-NEXT: %[[I:.+]] = alloca i32, align 4
// IR-NEXT: store i32 %[[START:.+]], i32* %[[START_ADDR]], align 4
// IR-NEXT: store i32 %[[END:.+]], i32* %[[END_ADDR]], align 4
// IR-NEXT: store i32 %[[STEP:.+]], i32* %[[STEP_ADDR]], align 4
// IR-NEXT: %[[TMP0:.+]] = load i32, i32* %[[START_ADDR]], align 4
// IR-NEXT: store i32 %[[TMP0]], i32* %[[I]], align 4
// IR-NEXT: br label %[[FOR_COND:.+]]
// IR-EMPTY:
// IR-NEXT: [[FOR_COND]]:
// IR-NEXT: %[[TMP1:.+]] = load i32, i32* %[[I]], align 4
// IR-NEXT: %[[TMP2:.+]] = load i32, i32* %[[END_ADDR]], align 4
// IR-NEXT: %[[CMP:.+]] = icmp slt i32 %[[TMP1]], %[[TMP2]]
// IR-NEXT: br i1 %[[CMP]], label %[[FOR_BODY:.+]], label %[[FOR_END:.+]]
// IR-EMPTY:
// IR-NEXT: [[FOR_BODY]]:
// IR-NEXT: %[[TMP3:.+]] = load i32, i32* %[[START_ADDR]], align 4
// IR-NEXT: %[[TMP4:.+]] = load i32, i32* %[[END_ADDR]], align 4
// IR-NEXT: %[[TMP5:.+]] = load i32, i32* %[[STEP_ADDR]], align 4
// IR-NEXT: %[[TMP6:.+]] = load i32, i32* %[[I]], align 4
// IR-NEXT: call void (...) @body(i32 noundef %[[TMP3]], i32 noundef %[[TMP4]], i32 noundef %[[TMP5]], i32 noundef %[[TMP6]])
// IR-NEXT: br label %[[FOR_INC:.+]]
// IR-EMPTY:
// IR-NEXT: [[FOR_INC]]:
// IR-NEXT: %[[TMP7:.+]] = load i32, i32* %[[STEP_ADDR]], align 4
// IR-NEXT: %[[TMP8:.+]] = load i32, i32* %[[I]], align 4
// IR-NEXT: %[[ADD:.+]] = add nsw i32 %[[TMP8]], %[[TMP7]]
// IR-NEXT: store i32 %[[ADD]], i32* %[[I]], align 4
// IR-NEXT: br label %[[FOR_COND]], !llvm.loop ![[LOOP2:[0-9]+]]
// IR-EMPTY:
// IR-NEXT: [[FOR_END]]:
// IR-NEXT: ret void
// IR-NEXT: }
extern "C" void func(int start, int end, int step) {
#pragma omp unroll
for (int i = start; i < end; i+=step)
body(start, end, step, i);
}
#endif /* HEADER */
// IR: ![[LOOP2]] = distinct !{![[LOOP2]], ![[LOOPPROP3:[0-9]+]], ![[LOOPPROP4:[0-9]+]]}
// IR: ![[LOOPPROP3]] = !{!"llvm.loop.mustprogress"}
// IR: ![[LOOPPROP4]] = !{!"llvm.loop.unroll.enable"}
|
