split-offsets.ll
4.12 KB
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
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=riscv32 -verify-machineinstrs < %s \
; RUN: | FileCheck %s -check-prefix=RV32I
; RUN: llc -mtriple=riscv64 -verify-machineinstrs < %s \
; RUN: | FileCheck %s -check-prefix=RV64I
; Check that memory accesses to array elements with large offsets have those
; offsets split into a base offset, plus a smaller offset that is folded into
; the memory operation. We should also only compute that base offset once,
; since it can be shared for all memory operations in this test.
define void @test1([65536 x i32]** %sp, [65536 x i32]* %t, i32 %n) {
; RV32I-LABEL: test1:
; RV32I: # %bb.0: # %entry
; RV32I-NEXT: lw a0, 0(a0)
; RV32I-NEXT: lui a2, 20
; RV32I-NEXT: addi a2, a2, -1920
; RV32I-NEXT: add a1, a1, a2
; RV32I-NEXT: add a0, a0, a2
; RV32I-NEXT: addi a2, zero, 2
; RV32I-NEXT: sw a2, 0(a0)
; RV32I-NEXT: addi a3, zero, 1
; RV32I-NEXT: sw a3, 4(a0)
; RV32I-NEXT: sw a3, 0(a1)
; RV32I-NEXT: sw a2, 4(a1)
; RV32I-NEXT: ret
;
; RV64I-LABEL: test1:
; RV64I: # %bb.0: # %entry
; RV64I-NEXT: ld a0, 0(a0)
; RV64I-NEXT: lui a2, 20
; RV64I-NEXT: addiw a2, a2, -1920
; RV64I-NEXT: add a1, a1, a2
; RV64I-NEXT: add a0, a0, a2
; RV64I-NEXT: addi a2, zero, 2
; RV64I-NEXT: sw a2, 0(a0)
; RV64I-NEXT: addi a3, zero, 1
; RV64I-NEXT: sw a3, 4(a0)
; RV64I-NEXT: sw a3, 0(a1)
; RV64I-NEXT: sw a2, 4(a1)
; RV64I-NEXT: ret
entry:
%s = load [65536 x i32]*, [65536 x i32]** %sp
%gep0 = getelementptr [65536 x i32], [65536 x i32]* %s, i64 0, i32 20000
%gep1 = getelementptr [65536 x i32], [65536 x i32]* %s, i64 0, i32 20001
%gep2 = getelementptr [65536 x i32], [65536 x i32]* %t, i64 0, i32 20000
%gep3 = getelementptr [65536 x i32], [65536 x i32]* %t, i64 0, i32 20001
store i32 2, i32* %gep0
store i32 1, i32* %gep1
store i32 1, i32* %gep2
store i32 2, i32* %gep3
ret void
}
; Ditto. Check it when the GEPs are not in the entry block.
define void @test2([65536 x i32]** %sp, [65536 x i32]* %t, i32 %n) {
; RV32I-LABEL: test2:
; RV32I: # %bb.0: # %entry
; RV32I-NEXT: mv a3, zero
; RV32I-NEXT: lw a4, 0(a0)
; RV32I-NEXT: lui a0, 20
; RV32I-NEXT: addi a5, a0, -1920
; RV32I-NEXT: add a0, a1, a5
; RV32I-NEXT: add a1, a4, a5
; RV32I-NEXT: bge a3, a2, .LBB1_2
; RV32I-NEXT: .LBB1_1: # %while_body
; RV32I-NEXT: # =>This Inner Loop Header: Depth=1
; RV32I-NEXT: addi a4, a3, 1
; RV32I-NEXT: sw a4, 0(a1)
; RV32I-NEXT: sw a3, 4(a1)
; RV32I-NEXT: sw a4, 0(a0)
; RV32I-NEXT: sw a3, 4(a0)
; RV32I-NEXT: mv a3, a4
; RV32I-NEXT: blt a3, a2, .LBB1_1
; RV32I-NEXT: .LBB1_2: # %while_end
; RV32I-NEXT: ret
;
; RV64I-LABEL: test2:
; RV64I: # %bb.0: # %entry
; RV64I-NEXT: mv a3, zero
; RV64I-NEXT: ld a4, 0(a0)
; RV64I-NEXT: lui a0, 20
; RV64I-NEXT: addiw a5, a0, -1920
; RV64I-NEXT: add a0, a1, a5
; RV64I-NEXT: add a1, a4, a5
; RV64I-NEXT: sext.w a2, a2
; RV64I-NEXT: sext.w a4, a3
; RV64I-NEXT: bge a4, a2, .LBB1_2
; RV64I-NEXT: .LBB1_1: # %while_body
; RV64I-NEXT: # =>This Inner Loop Header: Depth=1
; RV64I-NEXT: addi a4, a3, 1
; RV64I-NEXT: sw a4, 0(a1)
; RV64I-NEXT: sw a3, 4(a1)
; RV64I-NEXT: sw a4, 0(a0)
; RV64I-NEXT: sw a3, 4(a0)
; RV64I-NEXT: mv a3, a4
; RV64I-NEXT: sext.w a4, a3
; RV64I-NEXT: blt a4, a2, .LBB1_1
; RV64I-NEXT: .LBB1_2: # %while_end
; RV64I-NEXT: ret
entry:
%s = load [65536 x i32]*, [65536 x i32]** %sp
br label %while_cond
while_cond:
%phi = phi i32 [ 0, %entry ], [ %i, %while_body ]
%gep0 = getelementptr [65536 x i32], [65536 x i32]* %s, i64 0, i32 20000
%gep1 = getelementptr [65536 x i32], [65536 x i32]* %s, i64 0, i32 20001
%gep2 = getelementptr [65536 x i32], [65536 x i32]* %t, i64 0, i32 20000
%gep3 = getelementptr [65536 x i32], [65536 x i32]* %t, i64 0, i32 20001
%cmp = icmp slt i32 %phi, %n
br i1 %cmp, label %while_body, label %while_end
while_body:
%i = add i32 %phi, 1
%j = add i32 %phi, 2
store i32 %i, i32* %gep0
store i32 %phi, i32* %gep1
store i32 %i, i32* %gep2
store i32 %phi, i32* %gep3
br label %while_cond
while_end:
ret void
}