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
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=i686-unknown-unknown | FileCheck %s --check-prefixes=X86,X86-NOBMI
; RUN: llc < %s -mtriple=i686-unknown-unknown -mattr=+bmi2 | FileCheck %s --check-prefixes=X86,X86-BMI
; RUN: llc < %s -mtriple=x86_64-unknown-unknown | FileCheck %s --check-prefixes=X64,X64-NOBMI
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+bmi2 | FileCheck %s --check-prefixes=X64,X64-BMI
; PR1198
define i64 @foo(i64 %x, i64 %y) nounwind {
; X86-LABEL: foo:
; X86: # %bb.0:
; X86-NEXT: pushl %ebp
; X86-NEXT: pushl %ebx
; X86-NEXT: pushl %edi
; X86-NEXT: pushl %esi
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %esi
; X86-NEXT: movl {{[0-9]+}}(%esp), %ebp
; X86-NEXT: movl {{[0-9]+}}(%esp), %edi
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: mull %ebp
; X86-NEXT: movl %edx, %ebx
; X86-NEXT: movl %esi, %eax
; X86-NEXT: mull %ebp
; X86-NEXT: movl %edx, %ebp
; X86-NEXT: movl %eax, %esi
; X86-NEXT: addl %ebx, %esi
; X86-NEXT: adcl $0, %ebp
; X86-NEXT: movl %ecx, %eax
; X86-NEXT: mull %edi
; X86-NEXT: movl %edx, %ebx
; X86-NEXT: addl %esi, %eax
; X86-NEXT: adcl %ebp, %ebx
; X86-NEXT: setb %al
; X86-NEXT: movzbl %al, %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: mull %edi
; X86-NEXT: movl %edx, %esi
; X86-NEXT: movl %eax, %ebp
; X86-NEXT: addl %ebx, %ebp
; X86-NEXT: adcl %ecx, %esi
; X86-NEXT: xorl %ecx, %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: mull %ecx
; X86-NEXT: movl %edx, %edi
; X86-NEXT: movl %eax, %ebx
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: mull %ecx
; X86-NEXT: addl %ebx, %eax
; X86-NEXT: adcl %edi, %edx
; X86-NEXT: addl %ebp, %eax
; X86-NEXT: adcl %esi, %edx
; X86-NEXT: popl %esi
; X86-NEXT: popl %edi
; X86-NEXT: popl %ebx
; X86-NEXT: popl %ebp
; X86-NEXT: retl
;
; X64-LABEL: foo:
; X64: # %bb.0:
; X64-NEXT: movq %rdi, %rax
; X64-NEXT: mulq %rsi
; X64-NEXT: movq %rdx, %rax
; X64-NEXT: retq
%tmp0 = zext i64 %x to i128
%tmp1 = zext i64 %y to i128
%tmp2 = mul i128 %tmp0, %tmp1
%tmp7 = zext i32 64 to i128
%tmp3 = lshr i128 %tmp2, %tmp7
%tmp4 = trunc i128 %tmp3 to i64
ret i64 %tmp4
}
; <rdar://problem/14096009> superfluous multiply by high part of
; zero-extended value.
define i64 @mul1(i64 %n, i64* nocapture %z, i64* nocapture %x, i64 %y) nounwind {
; X86-LABEL: mul1:
; X86: # %bb.0: # %entry
; X86-NEXT: pushl %ebp
; X86-NEXT: pushl %ebx
; X86-NEXT: pushl %edi
; X86-NEXT: pushl %esi
; X86-NEXT: subl $28, %esp
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: orl %ecx, %eax
; X86-NEXT: je .LBB1_3
; X86-NEXT: # %bb.1: # %for.body.preheader
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: xorl %ebx, %ebx
; X86-NEXT: movl $0, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Folded Spill
; X86-NEXT: .p2align 4, 0x90
; X86-NEXT: .LBB1_2: # %for.body
; X86-NEXT: # =>This Inner Loop Header: Depth=1
; X86-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: movl %eax, %ecx
; X86-NEXT: movl (%eax,%ebx,8), %ebp
; X86-NEXT: movl 4(%eax,%ebx,8), %esi
; X86-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-NEXT: movl %ebp, %eax
; X86-NEXT: movl %ebp, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: mull %ecx
; X86-NEXT: movl %edx, %edi
; X86-NEXT: movl %eax, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-NEXT: movl %esi, %eax
; X86-NEXT: mull %ecx
; X86-NEXT: movl %edx, %ecx
; X86-NEXT: movl %eax, %esi
; X86-NEXT: addl %edi, %esi
; X86-NEXT: adcl $0, %ecx
; X86-NEXT: movl %ebp, %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %edx
; X86-NEXT: mull %edx
; X86-NEXT: movl %edx, %ebp
; X86-NEXT: movl %eax, %edi
; X86-NEXT: addl %esi, %edi
; X86-NEXT: adcl %ecx, %ebp
; X86-NEXT: setb {{[-0-9]+}}(%e{{[sb]}}p) # 1-byte Folded Spill
; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
; X86-NEXT: mull {{[0-9]+}}(%esp)
; X86-NEXT: movl %edx, %ecx
; X86-NEXT: movl %eax, %esi
; X86-NEXT: addl %ebp, %esi
; X86-NEXT: movzbl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 1-byte Folded Reload
; X86-NEXT: adcl %eax, %ecx
; X86-NEXT: movl {{[0-9]+}}(%esp), %eax
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: mull %edx
; X86-NEXT: movl %edx, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-NEXT: movl %eax, %ebp
; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %eax # 4-byte Reload
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: mull %edx
; X86-NEXT: addl %ebp, %eax
; X86-NEXT: movl {{[0-9]+}}(%esp), %ebp
; X86-NEXT: adcl {{[-0-9]+}}(%e{{[sb]}}p), %edx # 4-byte Folded Reload
; X86-NEXT: addl %esi, %eax
; X86-NEXT: adcl %ecx, %edx
; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
; X86-NEXT: addl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Folded Reload
; X86-NEXT: adcl {{[-0-9]+}}(%e{{[sb]}}p), %edi # 4-byte Folded Reload
; X86-NEXT: adcl $0, %eax
; X86-NEXT: adcl $0, %edx
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl %esi, (%ecx,%ebx,8)
; X86-NEXT: movl %edi, 4(%ecx,%ebx,8)
; X86-NEXT: movl {{[0-9]+}}(%esp), %ecx
; X86-NEXT: movl %ecx, %edi
; X86-NEXT: addl $1, %ebx
; X86-NEXT: movl {{[-0-9]+}}(%e{{[sb]}}p), %esi # 4-byte Reload
; X86-NEXT: adcl $0, %esi
; X86-NEXT: movl %ebx, %ecx
; X86-NEXT: xorl %ebp, %ecx
; X86-NEXT: movl %esi, {{[-0-9]+}}(%e{{[sb]}}p) # 4-byte Spill
; X86-NEXT: xorl %edi, %esi
; X86-NEXT: orl %ecx, %esi
; X86-NEXT: jne .LBB1_2
; X86-NEXT: .LBB1_3: # %for.end
; X86-NEXT: xorl %eax, %eax
; X86-NEXT: xorl %edx, %edx
; X86-NEXT: addl $28, %esp
; X86-NEXT: popl %esi
; X86-NEXT: popl %edi
; X86-NEXT: popl %ebx
; X86-NEXT: popl %ebp
; X86-NEXT: retl
;
; X64-LABEL: mul1:
; X64: # %bb.0: # %entry
; X64-NEXT: testq %rdi, %rdi
; X64-NEXT: je .LBB1_3
; X64-NEXT: # %bb.1: # %for.body.preheader
; X64-NEXT: movq %rcx, %r8
; X64-NEXT: movq %rdx, %r9
; X64-NEXT: xorl %r10d, %r10d
; X64-NEXT: xorl %ecx, %ecx
; X64-NEXT: .p2align 4, 0x90
; X64-NEXT: .LBB1_2: # %for.body
; X64-NEXT: # =>This Inner Loop Header: Depth=1
; X64-NEXT: movq %r8, %rax
; X64-NEXT: mulq (%r9,%rcx,8)
; X64-NEXT: addq %r10, %rax
; X64-NEXT: adcq $0, %rdx
; X64-NEXT: movq %rax, (%rsi,%rcx,8)
; X64-NEXT: incq %rcx
; X64-NEXT: cmpq %rcx, %rdi
; X64-NEXT: movq %rdx, %r10
; X64-NEXT: jne .LBB1_2
; X64-NEXT: .LBB1_3: # %for.end
; X64-NEXT: xorl %eax, %eax
; X64-NEXT: retq
entry:
%conv = zext i64 %y to i128
%cmp11 = icmp eq i64 %n, 0
br i1 %cmp11, label %for.end, label %for.body
for.body: ; preds = %entry, %for.body
%carry.013 = phi i64 [ %conv6, %for.body ], [ 0, %entry ]
%i.012 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds i64, i64* %x, i64 %i.012
%0 = load i64, i64* %arrayidx, align 8
%conv2 = zext i64 %0 to i128
%mul = mul i128 %conv2, %conv
%conv3 = zext i64 %carry.013 to i128
%add = add i128 %mul, %conv3
%conv4 = trunc i128 %add to i64
%arrayidx5 = getelementptr inbounds i64, i64* %z, i64 %i.012
store i64 %conv4, i64* %arrayidx5, align 8
%shr = lshr i128 %add, 64
%conv6 = trunc i128 %shr to i64
%inc = add i64 %i.012, 1
%exitcond = icmp eq i64 %inc, %n
br i1 %exitcond, label %for.end, label %for.body
for.end: ; preds = %for.body, %entry
ret i64 0
}
|
