aboutsummaryrefslogtreecommitdiffstats
path: root/test/CodeGen/X86/movtopush.ll
blob: 4a5d9037394a0f27b15f19e16de50a2ca5401062 (plain)
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
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
; RUN: llc < %s -mtriple=i686-windows | FileCheck %s -check-prefix=NORMAL
; RUN: llc < %s -mtriple=x86_64-windows | FileCheck %s -check-prefix=X64
; RUN: llc < %s -mtriple=i686-windows -force-align-stack -stack-alignment=32 | FileCheck %s -check-prefix=ALIGNED 

declare void @good(i32 %a, i32 %b, i32 %c, i32 %d)
declare void @inreg(i32 %a, i32 inreg %b, i32 %c, i32 %d)
declare void @oneparam(i32 %a)
declare void @eightparams(i32 %a, i32 %b, i32 %c, i32 %d, i32 %e, i32 %f, i32 %g, i32 %h)


; Here, we should have a reserved frame, so we don't expect pushes
; NORMAL-LABEL: test1:
; NORMAL: subl    $16, %esp
; NORMAL-NEXT: movl    $4, 12(%esp)
; NORMAL-NEXT: movl    $3, 8(%esp)
; NORMAL-NEXT: movl    $2, 4(%esp)
; NORMAL-NEXT: movl    $1, (%esp)
; NORMAL-NEXT: call
; NORMAL-NEXT: addl $16, %esp
define void @test1() {
entry:
  call void @good(i32 1, i32 2, i32 3, i32 4)
  ret void
}

; We're optimizing for code size, so we should get pushes for x86,
; even though there is a reserved call frame.
; Make sure we don't touch x86-64
; NORMAL-LABEL: test1b:
; NORMAL-NOT: subl {{.*}} %esp
; NORMAL: pushl   $4
; NORMAL-NEXT: pushl   $3
; NORMAL-NEXT: pushl   $2
; NORMAL-NEXT: pushl   $1
; NORMAL-NEXT: call
; NORMAL-NEXT: addl $16, %esp
; X64-LABEL: test1b:
; X64: movl    $1, %ecx
; X64-NEXT: movl    $2, %edx
; X64-NEXT: movl    $3, %r8d
; X64-NEXT: movl    $4, %r9d
; X64-NEXT: callq   good
define void @test1b() optsize {
entry:
  call void @good(i32 1, i32 2, i32 3, i32 4)
  ret void
}

; Same as above, but for minsize
; NORMAL-LABEL: test1c:
; NORMAL-NOT: subl {{.*}} %esp
; NORMAL: pushl   $4
; NORMAL-NEXT: pushl   $3
; NORMAL-NEXT: pushl   $2
; NORMAL-NEXT: pushl   $1
; NORMAL-NEXT: call
; NORMAL-NEXT: addl $16, %esp
define void @test1c() minsize {
entry:
  call void @good(i32 1, i32 2, i32 3, i32 4)
  ret void
}

; If we have a reserved frame, we should have pushes
; NORMAL-LABEL: test2:
; NORMAL-NOT: subl {{.*}} %esp
; NORMAL: pushl   $4
; NORMAL-NEXT: pushl   $3
; NORMAL-NEXT: pushl   $2
; NORMAL-NEXT: pushl   $1
; NORMAL-NEXT: call
define void @test2(i32 %k) {
entry:
  %a = alloca i32, i32 %k
  call void @good(i32 1, i32 2, i32 3, i32 4)
  ret void
}

; Again, we expect a sequence of 4 immediate pushes
; Checks that we generate the right pushes for >8bit immediates
; NORMAL-LABEL: test2b:
; NORMAL-NOT: subl {{.*}} %esp
; NORMAL: pushl   $4096
; NORMAL-NEXT: pushl   $3072
; NORMAL-NEXT: pushl   $2048
; NORMAL-NEXT: pushl   $1024
; NORMAL-NEXT: call
; NORMAL-NEXT: addl $16, %esp
define void @test2b() optsize {
entry:
  call void @good(i32 1024, i32 2048, i32 3072, i32 4096)
  ret void
}

; The first push should push a register
; NORMAL-LABEL: test3:
; NORMAL-NOT: subl {{.*}} %esp
; NORMAL: pushl   $4
; NORMAL-NEXT: pushl   $3
; NORMAL-NEXT: pushl   $2
; NORMAL-NEXT: pushl   %e{{..}}
; NORMAL-NEXT: call
; NORMAL-NEXT: addl $16, %esp
define void @test3(i32 %k) optsize {
entry:
  %f = add i32 %k, 1
  call void @good(i32 %f, i32 2, i32 3, i32 4)
  ret void
}

; We don't support weird calling conventions
; NORMAL-LABEL: test4:
; NORMAL: subl    $12, %esp
; NORMAL-NEXT: movl    $4, 8(%esp)
; NORMAL-NEXT: movl    $3, 4(%esp)
; NORMAL-NEXT: movl    $1, (%esp)
; NORMAL-NEXT: movl    $2, %eax
; NORMAL-NEXT: call
; NORMAL-NEXT: addl $12, %esp
define void @test4() optsize {
entry:
  call void @inreg(i32 1, i32 2, i32 3, i32 4)
  ret void
}

; When there is no reserved call frame, check that additional alignment
; is added when the pushes don't add up to the required alignment.
; ALIGNED-LABEL: test5:
; ALIGNED: subl    $16, %esp
; ALIGNED-NEXT: pushl   $4
; ALIGNED-NEXT: pushl   $3
; ALIGNED-NEXT: pushl   $2
; ALIGNED-NEXT: pushl   $1
; ALIGNED-NEXT: call
define void @test5(i32 %k) {
entry:
  %a = alloca i32, i32 %k
  call void @good(i32 1, i32 2, i32 3, i32 4)
  ret void
}

; When the alignment adds up, do the transformation
; ALIGNED-LABEL: test5b:
; ALIGNED: pushl   $8
; ALIGNED-NEXT: pushl   $7
; ALIGNED-NEXT: pushl   $6
; ALIGNED-NEXT: pushl   $5
; ALIGNED-NEXT: pushl   $4
; ALIGNED-NEXT: pushl   $3
; ALIGNED-NEXT: pushl   $2
; ALIGNED-NEXT: pushl   $1
; ALIGNED-NEXT: call
define void @test5b() optsize {
entry:
  call void @eightparams(i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8)
  ret void
}

; When having to compensate for the alignment isn't worth it,
; don't use pushes.
; ALIGNED-LABEL: test5c:
; ALIGNED: movl $1, (%esp)
; ALIGNED-NEXT: call
define void @test5c() optsize {
entry:
  call void @oneparam(i32 1)
  ret void
}

; Check that pushing the addresses of globals (Or generally, things that 
; aren't exactly immediates) isn't broken.
; Fixes PR21878.
; NORMAL-LABEL: test6:
; NORMAL: pushl    $_ext
; NORMAL-NEXT: call
declare void @f(i8*)
@ext = external constant i8

define void @test6() {
  call void @f(i8* @ext)
  br label %bb
bb:
  alloca i32
  ret void
}

; Check that we fold simple cases into the push
; NORMAL-LABEL: test7:
; NORMAL-NOT: subl {{.*}} %esp
; NORMAL: movl 4(%esp), [[EAX:%e..]]
; NORMAL-NEXT: pushl   $4
; NORMAL-NEXT: pushl   ([[EAX]])
; NORMAL-NEXT: pushl   $2
; NORMAL-NEXT: pushl   $1
; NORMAL-NEXT: call
; NORMAL-NEXT: addl $16, %esp
define void @test7(i32* %ptr) optsize {
entry:
  %val = load i32* %ptr
  call void @good(i32 1, i32 2, i32 %val, i32 4)
  ret void
}

; Fold stack-relative loads into the push, with correct offset
; In particular, at the second push, %b was at 12(%esp) and
; %a wast at 8(%esp), but the second push bumped %esp, so %a
; is now it at 12(%esp)
; NORMAL-LABEL: test8:
; NORMAL: pushl   $4
; NORMAL-NEXT: pushl   12(%esp)
; NORMAL-NEXT: pushl   12(%esp)
; NORMAL-NEXT: pushl   $1
; NORMAL-NEXT: call
; NORMAL-NEXT: addl $16, %esp
define void @test8(i32 %a, i32 %b) optsize {
entry:
  call void @good(i32 1, i32 %a, i32 %b, i32 4)
  ret void
}

; If one function is using push instructions, and the other isn't
; (because it has frame-index references), then we must resolve
; these references correctly.
; NORMAL-LABEL: test9:
; NORMAL-NOT: leal (%esp), 
; NORMAL: pushl $4
; NORMAL-NEXT: pushl $3
; NORMAL-NEXT: pushl $2
; NORMAL-NEXT: pushl $1
; NORMAL-NEXT: call
; NORMAL-NEXT: addl $16, %esp
; NORMAL-NEXT: subl $16, %esp
; NORMAL-NEXT: leal 16(%esp), [[EAX:%e..]]
; NORMAL-NEXT: movl    [[EAX]], 12(%esp)
; NORMAL-NEXT: movl    $7, 8(%esp)
; NORMAL-NEXT: movl    $6, 4(%esp)
; NORMAL-NEXT: movl    $5, (%esp)
; NORMAL-NEXT: call
; NORMAL-NEXT: addl $16, %esp
define void @test9() optsize {
entry:
  %p = alloca i32, align 4
  call void @good(i32 1, i32 2, i32 3, i32 4)
  %0 = ptrtoint i32* %p to i32
  call void @good(i32 5, i32 6, i32 7, i32 %0)
  ret void
}

; We can end up with an indirect call which gets reloaded on the spot.
; Make sure we reference the correct stack slot - we spill into (%esp)
; and reload from 16(%esp) due to the pushes.
; NORMAL-LABEL: test10:
; NORMAL: movl $_good, [[ALLOC:.*]]
; NORMAL-NEXT: movl [[ALLOC]], [[EAX:%e..]]
; NORMAL-NEXT: movl [[EAX]], (%esp) # 4-byte Spill
; NORMAL: nop
; NORMAL: pushl $4
; NORMAL-NEXT: pushl $3
; NORMAL-NEXT: pushl $2
; NORMAL-NEXT: pushl $1
; NORMAL-NEXT: calll *16(%esp)
; NORMAL-NEXT: addl $16, %esp
define void @test10() optsize {
  %stack_fptr = alloca void (i32, i32, i32, i32)*
  store void (i32, i32, i32, i32)* @good, void (i32, i32, i32, i32)** %stack_fptr
  %good_ptr = load volatile void (i32, i32, i32, i32)** %stack_fptr
  call void asm sideeffect "nop", "~{ax},~{bx},~{cx},~{dx},~{bp},~{si},~{di}"()
  call void (i32, i32, i32, i32)* %good_ptr(i32 1, i32 2, i32 3, i32 4)
  ret void
}

; We can't fold the load from the global into the push because of 
; interference from the store
; NORMAL-LABEL: test11:
; NORMAL: movl    _the_global, [[EAX:%e..]]
; NORMAL-NEXT: movl    $42, _the_global
; NORMAL-NEXT: pushl $4
; NORMAL-NEXT: pushl $3
; NORMAL-NEXT: pushl $2
; NORMAL-NEXT: pushl [[EAX]]
; NORMAL-NEXT: call
; NORMAL-NEXT: addl $16, %esp
@the_global = external global i32
define void @test11() optsize {
  %myload = load i32* @the_global
  store i32 42, i32* @the_global
  call void @good(i32 %myload, i32 2, i32 3, i32 4)
  ret void
}

; Converting one mov into a push isn't worth it when 
; doing so forces too much overhead for other calls.
; NORMAL-LABEL: test12:
; NORMAL: subl    $16, %esp
; NORMAL-NEXT: movl    $4, 8(%esp)
; NORMAL-NEXT: movl    $3, 4(%esp)
; NORMAL-NEXT: movl    $1, (%esp)
; NORMAL-NEXT: movl    $2, %eax
; NORMAL-NEXT: calll _inreg
; NORMAL-NEXT: movl    $8, 12(%esp)
; NORMAL-NEXT: movl    $7, 8(%esp)
; NORMAL-NEXT: movl    $6, 4(%esp)
; NORMAL-NEXT: movl    $5, (%esp)
; NORMAL-NEXT: calll _good
; NORMAL-NEXT: movl    $12, 8(%esp)
; NORMAL-NEXT: movl    $11, 4(%esp)
; NORMAL-NEXT: movl    $9, (%esp)
; NORMAL-NEXT: movl    $10, %eax
; NORMAL-NEXT: calll _inreg
; NORMAL-NEXT: addl $16, %esp
define void @test12() optsize {
entry:
  call void @inreg(i32 1, i32 2, i32 3, i32 4)
  call void @good(i32 5, i32 6, i32 7, i32 8)
  call void @inreg(i32 9, i32 10, i32 11, i32 12)
  ret void
}

; But if the gains outweigh the overhead, we should do it
; NORMAL-LABEL: test12b:
; NORMAL: pushl    $4
; NORMAL-NEXT: pushl    $3
; NORMAL-NEXT: pushl    $2
; NORMAL-NEXT: pushl    $1
; NORMAL-NEXT: calll _good
; NORMAL-NEXT: addl    $16, %esp
; NORMAL-NEXT: subl    $12, %esp
; NORMAL-NEXT: movl    $8, 8(%esp)
; NORMAL-NEXT: movl    $7, 4(%esp)
; NORMAL-NEXT: movl    $5, (%esp)
; NORMAL-NEXT: movl    $6, %eax
; NORMAL-NEXT: calll _inreg
; NORMAL-NEXT: addl    $12, %esp
; NORMAL-NEXT: pushl    $12
; NORMAL-NEXT: pushl    $11
; NORMAL-NEXT: pushl    $10
; NORMAL-NEXT: pushl    $9
; NORMAL-NEXT: calll _good
; NORMAL-NEXT: addl $16, %esp
define void @test12b() optsize {
entry:
  call void @good(i32 1, i32 2, i32 3, i32 4)
  call void @inreg(i32 5, i32 6, i32 7, i32 8)
  call void @good(i32 9, i32 10, i32 11, i32 12)
  ret void
}