File: loop-body-references-outer-values-3.ll

package info (click to toggle)
llvm-toolchain-13 1%3A13.0.1-11
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 1,418,840 kB
  • sloc: cpp: 5,290,826; ansic: 996,570; asm: 544,593; python: 188,212; objc: 72,027; lisp: 30,291; f90: 25,395; sh: 24,898; javascript: 9,780; pascal: 9,398; perl: 7,484; ml: 5,432; awk: 3,523; makefile: 2,913; xml: 953; cs: 573; fortran: 539
file content (67 lines) | stat: -rw-r--r-- 2,264 bytes parent folder | download | duplicates (7)
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
; RUN: opt %loadPolly -basic-aa -polly-parallel -polly-parallel-force -polly-invariant-load-hoisting=true -polly-ast -analyze < %s | FileCheck %s -check-prefix=AST
; RUN: opt %loadPolly -basic-aa -polly-parallel -polly-parallel-force -polly-invariant-load-hoisting=true -polly-codegen -S -verify-dom-info < %s | FileCheck %s -check-prefix=IR

; The interesting part of this test case is the instruction:
;   %tmp = bitcast i8* %call to i64**
; which is not part of the scop. In the SCEV based code generation not '%tmp',
; but %call is a parameter of the SCoP and we need to make sure its value is
; properly forwarded to the subfunction.

; AST: #pragma omp parallel for
; AST: for (int c0 = 0; c0 < cols; c0 += 1)
; AST:   Stmt_for_body(c0);
; AST: if (cols <= 0)
; AST:   Stmt_for_body(0);

; IR: @foo_polly_subfn

target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"

define void @foo(i64 %cols, i8* noalias %call) {
entry:
  %tmp = bitcast i8* %call to i64**
  br label %for.body

for.body:
  %indvar = phi i64 [ %indvar.next, %for.body ], [ 0, %entry ]
  %arrayidx = getelementptr inbounds i64*, i64** %tmp, i64 0
  %tmp1 = load i64*, i64** %arrayidx, align 8
  %arrayidx.2 = getelementptr inbounds i64, i64* %tmp1, i64 %indvar
  store i64 1, i64* %arrayidx.2, align 4
  %indvar.next = add nsw i64 %indvar, 1
  %cmp = icmp slt i64 %indvar.next, %cols
  br i1 %cmp, label %for.body, label %end

end:
  ret void
}

; Another variation of this test case, now with even more of the index
; expression defined outside of the scop.

; AST: #pragma omp parallel for
; AST: for (int c0 = 0; c0 < cols; c0 += 1)
; AST:   Stmt_for_body(c0);
; AST: if (cols <= 0)
; AST:   Stmt_for_body(0);

; IR: @bar_polly_subfn

define void @bar(i64 %cols, i8* noalias %call) {
entry:
  %tmp = bitcast i8* %call to i64**
  %arrayidx = getelementptr inbounds i64*, i64** %tmp, i64 0
  br label %for.body

for.body:
  %indvar = phi i64 [ %indvar.next, %for.body ], [ 0, %entry ]
  %tmp1 = load i64*, i64** %arrayidx, align 8
  %arrayidx.2 = getelementptr inbounds i64, i64* %tmp1, i64 %indvar
  store i64 1, i64* %arrayidx.2, align 4
  %indvar.next = add nsw i64 %indvar, 1
  %cmp = icmp slt i64 %indvar.next, %cols
  br i1 %cmp, label %for.body, label %end

end:
  ret void
}