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
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
|
; RUN: opt %loadPolly -polly-print-scops -polly-allow-differing-element-types -disable-output < %s | FileCheck %s
;
; void multiple_types(i8 *A) {
; for (long i = 0; i < 100; i++) {
; A[i] = *(i1 *)&A[1 * i] +
; *(i16 *)&A[2 * i] +
; *(i24 *)&A[4 * i] +
; *(i32 *)&A[4 * i] +
; *(i40 *)&A[8 * i] +
; *(i48 *)&A[8 * i] +
; *(i56 *)&A[8 * i] +
; *(i64 *)&A[8 * i] +
; *(i120 *)&A[16 * i] +
; *(i192 *)&A[24 * i] +
; *(i248 *)&A[32 * i];
; }
; }
;
; Verify that different data type sizes are correctly modeled. Specifically,
; we want to verify that type i1 is modeled with allocation size i8,
; type i24 is modeled with allocation size i32 and that i40, i48 and i56 are
; modeled with allocation size i64. Larger types, e.g., i120, i192 and i248 are
; not rounded up to the next power-of-two allocation size, but rather to the
; next multiple of 64.
; The allocation size discussed above defines the number of canonical array
; elements accessed. For example, even though i24 only consists of 3 bytes,
; its allocation size is 4 bytes. Consequently, we model the access to an
; i24 element as an access to four canonical elements resulting in access
; relation constraints '4i0 <= o0 <= 3 + 4i0' instead of '3i0 <= o0 <= 2 + 3i0'.
; CHECK: Statements {
; CHECK: Stmt_bb2
; CHECK: Domain :=
; CHECK: { Stmt_bb2[i0] : 0 <= i0 <= 99 };
; CHECK: Schedule :=
; CHECK: { Stmt_bb2[i0] -> [i0] };
; CHECK: ReadAccess := [Reduction Type: NONE] [Scalar: 0]
; CHECK: { Stmt_bb2[i0] -> MemRef_A[o0] : 2i0 <= o0 <= 1 + 2i0 };
; CHECK: ReadAccess := [Reduction Type: NONE] [Scalar: 0]
; CHECK: { Stmt_bb2[i0] -> MemRef_A[o0] : 4i0 <= o0 <= 3 + 4i0 };
; CHECK: ReadAccess := [Reduction Type: NONE] [Scalar: 0]
; CHECK: { Stmt_bb2[i0] -> MemRef_A[o0] : 4i0 <= o0 <= 3 + 4i0 };
; CHECK: ReadAccess := [Reduction Type: NONE] [Scalar: 0]
; CHECK: { Stmt_bb2[i0] -> MemRef_A[o0] : 8i0 <= o0 <= 7 + 8i0 };
; CHECK: ReadAccess := [Reduction Type: NONE] [Scalar: 0]
; CHECK: { Stmt_bb2[i0] -> MemRef_A[o0] : 8i0 <= o0 <= 7 + 8i0 };
; CHECK: ReadAccess := [Reduction Type: NONE] [Scalar: 0]
; CHECK: { Stmt_bb2[i0] -> MemRef_A[o0] : 8i0 <= o0 <= 7 + 8i0 };
; CHECK: ReadAccess := [Reduction Type: NONE] [Scalar: 0]
; CHECK: { Stmt_bb2[i0] -> MemRef_A[o0] : 8i0 <= o0 <= 7 + 8i0 };
; CHECK: ReadAccess := [Reduction Type: NONE] [Scalar: 0]
; CHECK: { Stmt_bb2[i0] -> MemRef_A[o0] : 16i0 <= o0 <= 15 + 16i0 };
; CHECK: ReadAccess := [Reduction Type: NONE] [Scalar: 0]
; CHECK: { Stmt_bb2[i0] -> MemRef_A[o0] : 24i0 <= o0 <= 23 + 24i0 };
; CHECK: ReadAccess := [Reduction Type: NONE] [Scalar: 0]
; CHECK: { Stmt_bb2[i0] -> MemRef_A[o0] : 32i0 <= o0 <= 31 + 32i0 };
; CHECK: MustWriteAccess := [Reduction Type: NONE] [Scalar: 0]
; CHECK: { Stmt_bb2[i0] -> MemRef_A[i0] };
; CHECK: }
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
define void @multiple_types(ptr %A) {
bb:
br label %bb1
bb1: ; preds = %bb20, %bb
%i.0 = phi i64 [ 0, %bb ], [ %tmp21, %bb20 ]
%exitcond = icmp ne i64 %i.0, 100
br i1 %exitcond, label %bb2, label %bb22
bb2: ; preds = %bb1
%load.i1.offset = mul i64 %i.0, 1
%load.i1.ptr = getelementptr inbounds i8, ptr %A, i64 %load.i1.offset
%load.i1.val = load i1, ptr %load.i1.ptr
%load.i1.val.trunc = zext i1 %load.i1.val to i8
%load.i16.offset = mul i64 %i.0, 2
%load.i16.ptr = getelementptr inbounds i8, ptr %A, i64 %load.i16.offset
%load.i16.val = load i16, ptr %load.i16.ptr
%load.i16.val.trunc = trunc i16 %load.i16.val to i8
%load.i24.offset = mul i64 %i.0, 4
%load.i24.ptr = getelementptr inbounds i8, ptr %A, i64 %load.i24.offset
%load.i24.val = load i24, ptr %load.i24.ptr
%load.i24.val.trunc = trunc i24 %load.i24.val to i8
%load.i32.offset = mul i64 %i.0, 4
%load.i32.ptr = getelementptr inbounds i8, ptr %A, i64 %load.i32.offset
%load.i32.val = load i32, ptr %load.i32.ptr
%load.i32.val.trunc = trunc i32 %load.i32.val to i8
%load.i40.offset = mul i64 %i.0, 8
%load.i40.ptr = getelementptr inbounds i8, ptr %A, i64 %load.i40.offset
%load.i40.val = load i40, ptr %load.i40.ptr
%load.i40.val.trunc = trunc i40 %load.i40.val to i8
%load.i48.offset = mul i64 %i.0, 8
%load.i48.ptr = getelementptr inbounds i8, ptr %A, i64 %load.i48.offset
%load.i48.val = load i48, ptr %load.i48.ptr
%load.i48.val.trunc = trunc i48 %load.i48.val to i8
%load.i56.offset = mul i64 %i.0, 8
%load.i56.ptr = getelementptr inbounds i8, ptr %A, i64 %load.i56.offset
%load.i56.val = load i56, ptr %load.i56.ptr
%load.i56.val.trunc = trunc i56 %load.i56.val to i8
%load.i64.offset = mul i64 %i.0, 8
%load.i64.ptr = getelementptr inbounds i8, ptr %A, i64 %load.i64.offset
%load.i64.val = load i64, ptr %load.i64.ptr
%load.i64.val.trunc = trunc i64 %load.i64.val to i8
%load.i120.offset = mul i64 %i.0, 16
%load.i120.ptr = getelementptr inbounds i8, ptr %A, i64 %load.i120.offset
%load.i120.val = load i120, ptr %load.i120.ptr
%load.i120.val.trunc = trunc i120 %load.i120.val to i8
%load.i192.offset = mul i64 %i.0, 24
%load.i192.ptr = getelementptr inbounds i8, ptr %A, i64 %load.i192.offset
%load.i192.val = load i192, ptr %load.i192.ptr
%load.i192.val.trunc = trunc i192 %load.i192.val to i8
%load.i248.offset = mul i64 %i.0, 32
%load.i248.ptr = getelementptr inbounds i8, ptr %A, i64 %load.i248.offset
%load.i248.val = load i248, ptr %load.i248.ptr
%load.i248.val.trunc = trunc i248 %load.i248.val to i8
%sum = add i8 %load.i1.val.trunc, %load.i16.val.trunc
%sum0 = add i8 %sum, %load.i24.val.trunc
%sum1 = add i8 %sum0, %load.i32.val.trunc
%sum2 = add i8 %sum1, %load.i40.val.trunc
%sum3 = add i8 %sum2, %load.i48.val.trunc
%sum4 = add i8 %sum3, %load.i56.val.trunc
%sum5 = add i8 %sum4, %load.i64.val.trunc
%sum6 = add i8 %sum5, %load.i120.val.trunc
%sum7 = add i8 %sum6, %load.i192.val.trunc
%sum8 = add i8 %sum7, %load.i248.val.trunc
%tmp7 = getelementptr inbounds i8, ptr %A, i64 %i.0
store i8 %sum8, ptr %tmp7
br label %bb20
bb20: ; preds = %bb2
%tmp21 = add nuw nsw i64 %i.0, 1
br label %bb1
bb22: ; preds = %bb1
ret void
}
|
