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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -passes=loop-vectorize -force-vector-interleave=3 -force-vector-width=2 -S | FileCheck %s
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
; Make sure the loop is vectorized and unrolled under -Os without folding its
; tail based on its trip-count being provably divisible by chosen VFxIC.
define dso_local void @constTC(ptr noalias nocapture %A) optsize {
; CHECK-LABEL: @constTC(
; CHECK-NEXT: entry:
; CHECK-NEXT: br i1 false, label [[SCALAR_PH:%.*]], label [[VECTOR_PH:%.*]]
; CHECK: vector.ph:
; CHECK-NEXT: br label [[VECTOR_BODY:%.*]]
; CHECK: vector.body:
; CHECK-NEXT: [[INDEX:%.*]] = phi i32 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = add i32 [[INDEX]], 0
; CHECK-NEXT: [[TMP1:%.*]] = add i32 [[INDEX]], 2
; CHECK-NEXT: [[TMP2:%.*]] = add i32 [[INDEX]], 4
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i32 [[TMP0]]
; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds i32, ptr [[A]], i32 [[TMP1]]
; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds i32, ptr [[A]], i32 [[TMP2]]
; CHECK-NEXT: [[TMP6:%.*]] = getelementptr inbounds i32, ptr [[TMP3]], i32 0
; CHECK-NEXT: [[TMP7:%.*]] = getelementptr inbounds i32, ptr [[TMP3]], i32 2
; CHECK-NEXT: [[TMP8:%.*]] = getelementptr inbounds i32, ptr [[TMP3]], i32 4
; CHECK-NEXT: store <2 x i32> <i32 13, i32 13>, ptr [[TMP6]], align 1
; CHECK-NEXT: store <2 x i32> <i32 13, i32 13>, ptr [[TMP7]], align 1
; CHECK-NEXT: store <2 x i32> <i32 13, i32 13>, ptr [[TMP8]], align 1
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i32 [[INDEX]], 6
; CHECK-NEXT: [[TMP9:%.*]] = icmp eq i32 [[INDEX_NEXT]], 1800
; CHECK-NEXT: br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[EXIT:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: [[BC_RESUME_VAL:%.*]] = phi i32 [ 1800, [[MIDDLE_BLOCK]] ], [ 0, [[ENTRY:%.*]] ]
; CHECK-NEXT: br label [[LOOP:%.*]]
; CHECK: loop:
; CHECK-NEXT: [[RIV:%.*]] = phi i32 [ [[BC_RESUME_VAL]], [[SCALAR_PH]] ], [ [[RIVPLUS1:%.*]], [[LOOP]] ]
; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[A]], i32 [[RIV]]
; CHECK-NEXT: store i32 13, ptr [[ARRAYIDX]], align 1
; CHECK-NEXT: [[RIVPLUS1]] = add nuw nsw i32 [[RIV]], 1
; CHECK-NEXT: [[COND:%.*]] = icmp eq i32 [[RIVPLUS1]], 1800
; CHECK-NEXT: br i1 [[COND]], label [[EXIT]], label [[LOOP]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK: exit:
; CHECK-NEXT: ret void
;
entry:
br label %loop
loop:
%riv = phi i32 [ 0, %entry ], [ %rivPlus1, %loop ]
%arrayidx = getelementptr inbounds i32, ptr %A, i32 %riv
store i32 13, ptr %arrayidx, align 1
%rivPlus1 = add nuw nsw i32 %riv, 1
%cond = icmp eq i32 %rivPlus1, 1800
br i1 %cond, label %exit, label %loop
exit:
ret void
}
|
