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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt -passes=loop-versioning -S < %s | FileCheck %s
; NB: addrspaces 10-13 are non-integral
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128-ni:10:11:12:13"
; This matches the test case from PR38290
; Check that we expand the SCEV predicate check using GEP, rather
; than ptrtoint.
%jl_value_t = type opaque
%jl_array_t = type { ptr addrspace(13), i64, i16, i16, i32 }
declare i64 @julia_steprange_last_4949()
define void @wrapping_ptr_nonint_addrspace(ptr %arg) {
; CHECK-LABEL: define void @wrapping_ptr_nonint_addrspace(
; CHECK-SAME: ptr [[ARG:%.*]]) {
; CHECK-NEXT: [[LOOP_LVER_CHECK:.*:]]
; CHECK-NEXT: [[LOAD0:%.*]] = load ptr addrspace(10), ptr [[ARG]], align 8
; CHECK-NEXT: [[LOAD1:%.*]] = load i32, ptr inttoptr (i64 12 to ptr), align 4
; CHECK-NEXT: [[SUB:%.*]] = sub i32 0, [[LOAD1]]
; CHECK-NEXT: [[CALL:%.*]] = call i64 @julia_steprange_last_4949()
; CHECK-NEXT: [[CAST0:%.*]] = addrspacecast ptr addrspace(10) [[LOAD0]] to ptr addrspace(11)
; CHECK-NEXT: [[LOAD2:%.*]] = load ptr addrspace(10), ptr addrspace(11) [[CAST0]], align 8
; CHECK-NEXT: [[CAST1:%.*]] = addrspacecast ptr addrspace(10) [[LOAD2]] to ptr addrspace(11)
; CHECK-NEXT: [[LOAD3:%.*]] = load ptr addrspace(13), ptr addrspace(11) [[CAST1]], align 8
; CHECK-NEXT: [[SEXT:%.*]] = sext i32 [[SUB]] to i64
; CHECK-NEXT: [[TMP0:%.*]] = shl i64 [[CALL]], 2
; CHECK-NEXT: [[TMP1:%.*]] = shl nsw i64 [[SEXT]], 2
; CHECK-NEXT: [[TMP2:%.*]] = add i64 [[TMP0]], [[TMP1]]
; CHECK-NEXT: [[TMP3:%.*]] = add i64 [[TMP2]], -4
; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, ptr addrspace(13) [[LOAD3]], i64 [[TMP3]]
; CHECK-NEXT: [[SCEVGEP1:%.*]] = getelementptr i8, ptr addrspace(13) [[LOAD3]], i64 [[TMP1]]
; CHECK-NEXT: [[TMP4:%.*]] = add i64 [[TMP0]], -4
; CHECK-NEXT: [[SCEVGEP2:%.*]] = getelementptr i8, ptr addrspace(13) [[LOAD3]], i64 [[TMP4]]
; CHECK-NEXT: [[BOUND0:%.*]] = icmp ult ptr addrspace(13) [[SCEVGEP]], [[LOAD3]]
; CHECK-NEXT: [[BOUND1:%.*]] = icmp ult ptr addrspace(13) [[SCEVGEP2]], [[SCEVGEP1]]
; CHECK-NEXT: [[FOUND_CONFLICT:%.*]] = and i1 [[BOUND0]], [[BOUND1]]
; CHECK-NEXT: br i1 [[FOUND_CONFLICT]], label %[[LOOP_PH_LVER_ORIG:.*]], label %[[LOOP_PH:.*]]
; CHECK: [[LOOP_PH_LVER_ORIG]]:
; CHECK-NEXT: br label %[[LOOP_LVER_ORIG:.*]]
; CHECK: [[LOOP_LVER_ORIG]]:
; CHECK-NEXT: [[VALUE_PHI3_LVER_ORIG:%.*]] = phi i64 [ 0, %[[LOOP_PH_LVER_ORIG]] ], [ [[ADD0_LVER_ORIG:%.*]], %[[LOOP_LVER_ORIG]] ]
; CHECK-NEXT: [[ADD0_LVER_ORIG]] = add i64 [[VALUE_PHI3_LVER_ORIG]], -1
; CHECK-NEXT: [[GEP0_LVER_ORIG:%.*]] = getelementptr inbounds i32, ptr addrspace(13) [[LOAD3]], i64 [[ADD0_LVER_ORIG]]
; CHECK-NEXT: [[LOAD4_LVER_ORIG:%.*]] = load i32, ptr addrspace(13) [[GEP0_LVER_ORIG]], align 4
; CHECK-NEXT: [[ADD1_LVER_ORIG:%.*]] = add i64 [[ADD0_LVER_ORIG]], [[SEXT]]
; CHECK-NEXT: [[GEP1_LVER_ORIG:%.*]] = getelementptr inbounds i32, ptr addrspace(13) [[LOAD3]], i64 [[ADD1_LVER_ORIG]]
; CHECK-NEXT: store i32 [[LOAD4_LVER_ORIG]], ptr addrspace(13) [[GEP1_LVER_ORIG]], align 4
; CHECK-NEXT: [[CMP_LVER_ORIG:%.*]] = icmp eq i64 [[VALUE_PHI3_LVER_ORIG]], [[CALL]]
; CHECK-NEXT: br i1 [[CMP_LVER_ORIG]], label %[[EXIT_LOOPEXIT:.*]], label %[[LOOP_LVER_ORIG]]
; CHECK: [[LOOP_PH]]:
; CHECK-NEXT: br label %[[LOOP:.*]]
; CHECK: [[LOOP]]:
; CHECK-NEXT: [[VALUE_PHI3:%.*]] = phi i64 [ 0, %[[LOOP_PH]] ], [ [[ADD0:%.*]], %[[LOOP]] ]
; CHECK-NEXT: [[ADD0]] = add i64 [[VALUE_PHI3]], -1
; CHECK-NEXT: [[GEP0:%.*]] = getelementptr inbounds i32, ptr addrspace(13) [[LOAD3]], i64 [[ADD0]]
; CHECK-NEXT: [[LOAD4:%.*]] = load i32, ptr addrspace(13) [[GEP0]], align 4, !alias.scope [[META0:![0-9]+]]
; CHECK-NEXT: [[ADD1:%.*]] = add i64 [[ADD0]], [[SEXT]]
; CHECK-NEXT: [[GEP1:%.*]] = getelementptr inbounds i32, ptr addrspace(13) [[LOAD3]], i64 [[ADD1]]
; CHECK-NEXT: store i32 [[LOAD4]], ptr addrspace(13) [[GEP1]], align 4, !alias.scope [[META3:![0-9]+]], !noalias [[META0]]
; CHECK-NEXT: [[CMP:%.*]] = icmp eq i64 [[VALUE_PHI3]], [[CALL]]
; CHECK-NEXT: br i1 [[CMP]], label %[[EXIT_LOOPEXIT3:.*]], label %[[LOOP]]
; CHECK: [[EXIT_LOOPEXIT]]:
; CHECK-NEXT: br label %[[EXIT:.*]]
; CHECK: [[EXIT_LOOPEXIT3]]:
; CHECK-NEXT: br label %[[EXIT]]
; CHECK: [[EXIT]]:
; CHECK-NEXT: ret void
;
top:
%load0 = load ptr addrspace(10), ptr %arg, align 8
%load1 = load i32, ptr inttoptr (i64 12 to ptr), align 4
%sub = sub i32 0, %load1
%call = call i64 @julia_steprange_last_4949()
%cast0 = addrspacecast ptr addrspace(10) %load0 to ptr addrspace(11)
%load2 = load ptr addrspace(10), ptr addrspace(11) %cast0, align 8
%cast1 = addrspacecast ptr addrspace(10) %load2 to ptr addrspace(11)
%load3 = load ptr addrspace(13), ptr addrspace(11) %cast1, align 8
%sext = sext i32 %sub to i64
br label %loop
loop:
%value_phi3 = phi i64 [ 0, %top ], [ %add0, %loop ]
%add0 = add i64 %value_phi3, -1
%gep0 = getelementptr inbounds i32, ptr addrspace(13) %load3, i64 %add0
%load4 = load i32, ptr addrspace(13) %gep0, align 4
%add1 = add i64 %add0, %sext
%gep1 = getelementptr inbounds i32, ptr addrspace(13) %load3, i64 %add1
store i32 %load4, ptr addrspace(13) %gep1, align 4
%cmp = icmp eq i64 %value_phi3, %call
br i1 %cmp, label %exit, label %loop
exit:
ret void
}
;.
; CHECK: [[META0]] = !{[[META1:![0-9]+]]}
; CHECK: [[META1]] = distinct !{[[META1]], [[META2:![0-9]+]]}
; CHECK: [[META2]] = distinct !{[[META2]], !"LVerDomain"}
; CHECK: [[META3]] = !{[[META4:![0-9]+]]}
; CHECK: [[META4]] = distinct !{[[META4]], [[META2]]}
;.
|
