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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-- | FileCheck %s --check-prefix=X86
; RUN: llc < %s -mtriple=x86_64-- | FileCheck %s --check-prefix=X64
; Make sure none of these crash, and that the power-of-two transformations
; trigger correctly.
define i128 @test1(i128 %x) nounwind {
; X86-LABEL: test1:
; X86: # %bb.0:
; X86-NEXT: pushl %edi
; X86-NEXT: pushl %esi
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl %ecx, %esi
; X86-NEXT: sarl $31, %esi
; X86-NEXT: movl %esi, %edx
; X86-NEXT: shrl $30, %edx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
; X86-NEXT: addl %esi, %edi
; X86-NEXT: adcl {{[0-9]+}}(%esp), %esi
; X86-NEXT: adcl {{[0-9]+}}(%esp), %edx
; X86-NEXT: adcl $0, %ecx
; X86-NEXT: shrdl $2, %ecx, %edx
; X86-NEXT: movl %ecx, %esi
; X86-NEXT: sarl $2, %esi
; X86-NEXT: sarl $31, %ecx
; X86-NEXT: movl %ecx, 12(%eax)
; X86-NEXT: movl %ecx, 8(%eax)
; X86-NEXT: movl %esi, 4(%eax)
; X86-NEXT: movl %edx, (%eax)
; X86-NEXT: popl %esi
; X86-NEXT: popl %edi
; X86-NEXT: retl $4
;
; X64-LABEL: test1:
; X64: # %bb.0:
; X64-NEXT: movq %rsi, %rax
; X64-NEXT: sarq $63, %rax
; X64-NEXT: movq %rax, %rdx
; X64-NEXT: shrq $62, %rdx
; X64-NEXT: addq %rdi, %rax
; X64-NEXT: adcq %rsi, %rdx
; X64-NEXT: movq %rdx, %rax
; X64-NEXT: sarq $2, %rax
; X64-NEXT: sarq $63, %rdx
; X64-NEXT: retq
%tmp = sdiv i128 %x, 73786976294838206464
ret i128 %tmp
}
define i128 @test2(i128 %x) nounwind {
; X86-LABEL: test2:
; X86: # %bb.0:
; X86-NEXT: pushl %ebx
; X86-NEXT: pushl %edi
; X86-NEXT: pushl %esi
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: movl %edx, %esi
; X86-NEXT: sarl $31, %esi
; X86-NEXT: movl %esi, %ecx
; X86-NEXT: shrl $30, %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
; X86-NEXT: addl %esi, %edi
; X86-NEXT: adcl {{[0-9]+}}(%esp), %esi
; X86-NEXT: adcl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: adcl $0, %edx
; X86-NEXT: shrdl $2, %edx, %ecx
; X86-NEXT: movl %edx, %esi
; X86-NEXT: sarl $31, %esi
; X86-NEXT: sarl $2, %edx
; X86-NEXT: xorl %edi, %edi
; X86-NEXT: negl %ecx
; X86-NEXT: movl $0, %ebx
; X86-NEXT: sbbl %edx, %ebx
; X86-NEXT: movl $0, %edx
; X86-NEXT: sbbl %esi, %edx
; X86-NEXT: sbbl %esi, %edi
; X86-NEXT: movl %ecx, (%eax)
; X86-NEXT: movl %ebx, 4(%eax)
; X86-NEXT: movl %edx, 8(%eax)
; X86-NEXT: movl %edi, 12(%eax)
; X86-NEXT: popl %esi
; X86-NEXT: popl %edi
; X86-NEXT: popl %ebx
; X86-NEXT: retl $4
;
; X64-LABEL: test2:
; X64: # %bb.0:
; X64-NEXT: movq %rsi, %rcx
; X64-NEXT: sarq $63, %rcx
; X64-NEXT: movq %rcx, %rax
; X64-NEXT: shrq $62, %rax
; X64-NEXT: addq %rdi, %rcx
; X64-NEXT: adcq %rsi, %rax
; X64-NEXT: movq %rax, %rcx
; X64-NEXT: sarq $63, %rcx
; X64-NEXT: sarq $2, %rax
; X64-NEXT: xorl %edx, %edx
; X64-NEXT: negq %rax
; X64-NEXT: sbbq %rcx, %rdx
; X64-NEXT: retq
%tmp = sdiv i128 %x, -73786976294838206464
ret i128 %tmp
}
define i128 @test3(i128 %x) nounwind {
; X86-LABEL: test3:
; X86 doesn't have __divti3, so the urem is expanded into a loop.
; X86: udiv-do-while
;
; X64-LABEL: test3:
; X64: # %bb.0:
; X64-NEXT: pushq %rax
; X64-NEXT: movq $-3, %rdx
; X64-NEXT: movq $-5, %rcx
; X64-NEXT: callq __divti3@PLT
; X64-NEXT: popq %rcx
; X64-NEXT: retq
%tmp = sdiv i128 %x, -73786976294838206467
ret i128 %tmp
}
|
