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
|
; RUN: opt %loadPolly -polly-import-jscop -polly-print-ast -polly-ast-detect-parallel -disable-output < %s | FileCheck %s
;
; Verify that only the outer dimension needs privatization
;
; CHECK: #pragma known-parallel reduction
; CHECK: for (int c1 = 0; c1 <= 1023; c1 += 1) {
; CHECK: if ((c1 + 1) % 2 == 0) {
; CHECK-NOT: #pragma simd reduction
; CHECK: #pragma simd
; CHECK: for (int c3 = -2 * n + 1; c3 <= 0; c3 += 1)
; CHECK: Stmt_for_body3(-c3, c1);
; CHECK: } else {
; CHECK-NOT: #pragma simd reduction
; CHECK: #pragma simd
; CHECK: for (int c3 = 0; c3 < 2 * n; c3 += 1)
; CHECK: Stmt_for_body3(c3, c1);
; CHECK: }
; CHECK: }
;
; void rmsmd5(int *A, long n) {
; for (long i = 0; i < 2 * n; i++)
; for (long j = 0; j < 1024; j++)
; A[i] += i;
; }
;
target datalayout = "e-m:e-p:32:32-i64:64-v128:64:128-n32-S64"
define void @rmsmd5(i32* %A, i32 %n) {
entry:
br label %for.cond
for.cond: ; preds = %for.inc4, %entry
%i.0 = phi i32 [ 0, %entry ], [ %inc5, %for.inc4 ]
%mul = shl nsw i32 %n, 1
%cmp = icmp slt i32 %i.0, %mul
br i1 %cmp, label %for.body, label %for.end6
for.body: ; preds = %for.cond
br label %for.cond1
for.cond1: ; preds = %for.inc, %for.body
%j.0 = phi i32 [ 0, %for.body ], [ %inc, %for.inc ]
%exitcond = icmp ne i32 %j.0, 1024
br i1 %exitcond, label %for.body3, label %for.end
for.body3: ; preds = %for.cond1
%arrayidx = getelementptr inbounds i32, i32* %A, i32 %i.0
%tmp = load i32, i32* %arrayidx, align 4
%add = add nsw i32 %tmp, %i.0
store i32 %add, i32* %arrayidx, align 4
br label %for.inc
for.inc: ; preds = %for.body3
%inc = add nsw i32 %j.0, 1
br label %for.cond1
for.end: ; preds = %for.cond1
br label %for.inc4
for.inc4: ; preds = %for.end
%inc5 = add nsw i32 %i.0, 1
br label %for.cond
for.end6: ; preds = %for.cond
ret void
}
|
