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
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -mtriple=s390x-unknown-linux -mcpu=z13 -passes=loop-vectorize,dce,instcombine -force-vector-width=2 < %s | FileCheck %s
;
; Test that loop vectorizer does not generate vector addresses that must then
; always be extracted.
; Check that the addresses for a scalarized memory access is not extracted
; from a vector register.
define i32 @foo(ptr nocapture %A) {
; CHECK-LABEL: @foo(
; 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 i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = shl i64 [[INDEX]], 2
; CHECK-NEXT: [[TMP1:%.*]] = or disjoint i64 [[TMP0]], 4
; CHECK-NEXT: [[DOTIDX:%.*]] = shl nsw i64 [[INDEX]], 4
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds i8, ptr [[A:%.*]], i64 [[DOTIDX]]
; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds i32, ptr [[A]], i64 [[TMP1]]
; CHECK-NEXT: store i32 4, ptr [[TMP2]], align 4
; CHECK-NEXT: store i32 4, ptr [[TMP3]], align 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
; CHECK-NEXT: [[TMP4:%.*]] = icmp eq i64 [[INDEX_NEXT]], 10000
; CHECK-NEXT: br i1 [[TMP4]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP0:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: br i1 poison, label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP3:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: ret i32 poison
;
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%0 = shl nsw i64 %indvars.iv, 2
%arrayidx = getelementptr inbounds i32, ptr %A, i64 %0
store i32 4, ptr %arrayidx, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, 10000
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret i32 poison
}
; Check that a load of address is scalarized.
define i32 @foo1(ptr nocapture noalias %A, ptr nocapture %PtrPtr) {
; CHECK-LABEL: @foo1(
; 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 i64 [ 0, [[VECTOR_PH]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY]] ]
; CHECK-NEXT: [[TMP0:%.*]] = or disjoint i64 [[INDEX]], 1
; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds ptr, ptr [[PTRPTR:%.*]], i64 [[INDEX]]
; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds ptr, ptr [[PTRPTR]], i64 [[TMP0]]
; CHECK-NEXT: [[TMP3:%.*]] = load ptr, ptr [[TMP1]], align 8
; CHECK-NEXT: [[TMP4:%.*]] = load ptr, ptr [[TMP2]], align 8
; CHECK-NEXT: [[TMP5:%.*]] = load i32, ptr [[TMP3]], align 4
; CHECK-NEXT: [[TMP6:%.*]] = load i32, ptr [[TMP4]], align 4
; CHECK-NEXT: [[TMP7:%.*]] = insertelement <2 x i32> poison, i32 [[TMP5]], i64 0
; CHECK-NEXT: [[TMP8:%.*]] = insertelement <2 x i32> [[TMP7]], i32 [[TMP6]], i64 1
; CHECK-NEXT: [[TMP9:%.*]] = getelementptr inbounds i32, ptr [[A:%.*]], i64 [[INDEX]]
; CHECK-NEXT: store <2 x i32> [[TMP8]], ptr [[TMP9]], align 4
; CHECK-NEXT: [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 2
; CHECK-NEXT: [[TMP10:%.*]] = icmp eq i64 [[INDEX_NEXT]], 10000
; CHECK-NEXT: br i1 [[TMP10]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop [[LOOP4:![0-9]+]]
; CHECK: middle.block:
; CHECK-NEXT: br i1 true, label [[FOR_END:%.*]], label [[SCALAR_PH]]
; CHECK: scalar.ph:
; CHECK-NEXT: br label [[FOR_BODY:%.*]]
; CHECK: for.body:
; CHECK-NEXT: br i1 poison, label [[FOR_END]], label [[FOR_BODY]], !llvm.loop [[LOOP5:![0-9]+]]
; CHECK: for.end:
; CHECK-NEXT: ret i32 poison
;
entry:
br label %for.body
for.body:
%indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
%ptr = getelementptr inbounds ptr, ptr %PtrPtr, i64 %indvars.iv
%el = load ptr, ptr %ptr
%v = load i32, ptr %el
%arrayidx = getelementptr inbounds i32, ptr %A, i64 %indvars.iv
store i32 %v, ptr %arrayidx, align 4
%indvars.iv.next = add i64 %indvars.iv, 1
%lftr.wideiv = trunc i64 %indvars.iv.next to i32
%exitcond = icmp eq i32 %lftr.wideiv, 10000
br i1 %exitcond, label %for.end, label %for.body
for.end:
ret i32 poison
}
|
