aboutsummaryrefslogtreecommitdiffstats
path: root/test/Transforms/LoopVectorize/vect.omp.persistence.ll
blob: ea7be9c106b35bda549f6eebfeeadcad73bd15b4 (plain)
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
; RUN: opt < %s -O2 -force-vector-interleave=2 -force-vector-width=4 -debug-only=loop-vectorize -stats -S 2>&1 | FileCheck %s
; REQUIRES: asserts

; Loop from "rotated"
; CHECK: LV: Loop hints: force=enabled
; Loop from "nonrotated"
; CHECK: LV: Loop hints: force=enabled
; No more loops in the module
; CHECK-NOT: LV: Loop hints: force=
; In total only 1 loop should be rotated.
; CHECK: 1 loop-rotate

target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

; See http://reviews.llvm.org/D3348 for details.

;
; Test #1
;
; Ensure that "llvm.loop.vectorize.enable" metadata was not lost prior to LoopVectorize pass.
; In past LoopRotate was clearing that metadata.
;
; The source C code is:
; void rotated(float *a, int size)
; {
;   int t = 0;
;   #pragma omp simd
;   for (int i = 0; i < size; ++i) {
;     a[i] = a[i-5] * a[i+2];
;     ++t;
;   }
;}

define void @rotated(float* nocapture %a, i64 %size) {
entry:
  %cmp1 = icmp sgt i64 %size, 0
  br i1 %cmp1, label %for.header, label %for.end

for.header:
  %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ]
  %cmp2 = icmp sgt i64 %indvars.iv, %size
  br i1 %cmp2, label %for.end, label %for.body

for.body:

  %0 = add nsw i64 %indvars.iv, -5
  %arrayidx = getelementptr inbounds float* %a, i64 %0
  %1 = load float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !1
  %2 = add nsw i64 %indvars.iv, 2
  %arrayidx2 = getelementptr inbounds float* %a, i64 %2
  %3 = load float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !1
  %mul = fmul float %1, %3
  %arrayidx4 = getelementptr inbounds float* %a, i64 %indvars.iv
  store float %mul, float* %arrayidx4, align 4, !llvm.mem.parallel_loop_access !1

  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
  br label %for.header, !llvm.loop !1

for.end:
  ret void
}

!1 = !{!1, !2}
!2 = !{!"llvm.loop.vectorize.enable", i1 true}

;
; Test #2
;
; Ensure that "llvm.loop.vectorize.enable" metadata was not lost even
; if loop was not rotated (see http://reviews.llvm.org/D3348#comment-4).
;
define i32 @nonrotated(i32 %a) {
entry:
  br label %loop_cond
loop_cond:
  %indx = phi i32 [ 1, %entry ], [ %inc, %loop_inc ]
  %cmp = icmp ne i32 %indx, %a
  br i1 %cmp, label %return, label %loop_inc
loop_inc:
  %inc = add i32 %indx, 1
  br label %loop_cond, !llvm.loop !3
return:
  ret i32 0
}

!3 = !{!3, !4}
!4 = !{!"llvm.loop.vectorize.enable", i1 true}