llvm.org GIT mirror llvm / release_90 test / CodeGen / AMDGPU / callee-frame-setup.ll
release_90

Tree @release_90 (Download .tar.gz)

callee-frame-setup.ll @release_90raw · history · blame

  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
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
; RUN: llc -march=amdgcn -mcpu=hawaii -verify-machineinstrs < %s | FileCheck  -enable-var-scope -check-prefix=GCN -check-prefix=CI %s
; RUN: llc -march=amdgcn -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck  -enable-var-scope -check-prefix=GCN -check-prefix=GFX9 %s

; GCN-LABEL: {{^}}callee_no_stack:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt
; GCN-NEXT: s_setpc_b64
define void @callee_no_stack() #0 {
  ret void
}

; GCN-LABEL: {{^}}callee_no_stack_no_fp_elim_all:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt
; GCN-NEXT: s_mov_b32 s4, s34
; GCN-NEXT: s_mov_b32 s34, s32
; GCN-NEXT: s_mov_b32 s34, s4
; GCN-NEXT: s_setpc_b64
define void @callee_no_stack_no_fp_elim_all() #1 {
  ret void
}

; GCN-LABEL: {{^}}callee_no_stack_no_fp_elim_nonleaf:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt
; GCN-NEXT: s_setpc_b64
define void @callee_no_stack_no_fp_elim_nonleaf() #2 {
  ret void
}

; GCN-LABEL: {{^}}callee_with_stack:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt
; GCN-NEXT: v_mov_b32_e32 v0, 0{{$}}
; GCN-NEXT: buffer_store_dword v0, off, s[0:3], s32{{$}}
; GCN-NEXT: s_waitcnt
; GCN-NEXT: s_setpc_b64
define void @callee_with_stack() #0 {
  %alloca = alloca i32, addrspace(5)
  store volatile i32 0, i32 addrspace(5)* %alloca
  ret void
}

; Can use free call clobbered register to preserve original FP value.

; GCN-LABEL: {{^}}callee_with_stack_no_fp_elim_all:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt
; GCN-NEXT: s_mov_b32 s4, s34
; GCN-NEXT: s_mov_b32 s34, s32
; GCN-NEXT: s_add_u32 s32, s32, 0x200
; GCN-NEXT: v_mov_b32_e32 v0, 0{{$}}
; GCN-NEXT: buffer_store_dword v0, off, s[0:3], s34 offset:4{{$}}
; GCN-NEXT: s_sub_u32 s32, s32, 0x200
; GCN-NEXT: s_mov_b32 s34, s4
; GCN-NEXT: s_waitcnt vmcnt(0)
; GCN-NEXT: s_setpc_b64
define void @callee_with_stack_no_fp_elim_all() #1 {
  %alloca = alloca i32, addrspace(5)
  store volatile i32 0, i32 addrspace(5)* %alloca
  ret void
}

; GCN-LABEL: {{^}}callee_with_stack_no_fp_elim_non_leaf:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt
; GCN-NEXT: v_mov_b32_e32 v0, 0{{$}}
; GCN-NEXT: buffer_store_dword v0, off, s[0:3], s32{{$}}
; GCN-NEXT: s_waitcnt
; GCN-NEXT: s_setpc_b64
define void @callee_with_stack_no_fp_elim_non_leaf() #2 {
  %alloca = alloca i32, addrspace(5)
  store volatile i32 0, i32 addrspace(5)* %alloca
  ret void
}

; GCN-LABEL: {{^}}callee_with_stack_and_call:
; GCN: ; %bb.0:
; GCN-NEXT: s_waitcnt
; GCN: s_or_saveexec_b64 [[COPY_EXEC0:s\[[0-9]+:[0-9]+\]]], -1{{$}}
; GCN-NEXT: buffer_store_dword [[CSR_VGPR:v[0-9]+]], off, s[0:3], s32 offset:4 ; 4-byte Folded Spill
; GCN-NEXT: s_mov_b64 exec, [[COPY_EXEC0]]
; GCN: v_writelane_b32 [[CSR_VGPR]], s34, 2
; GCN-DAG: s_mov_b32 s34, s32
; GCN-DAG: s_add_u32 s32, s32, 0x400{{$}}
; GCN-DAG: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0{{$}}
; GCN-DAG: v_writelane_b32 [[CSR_VGPR]], s30,
; GCN-DAG: v_writelane_b32 [[CSR_VGPR]], s31,

; GCN-DAG: buffer_store_dword [[ZERO]], off, s[0:3], s34{{$}}

; GCN: s_swappc_b64

; GCN-DAG: v_readlane_b32 s5, [[CSR_VGPR]]
; GCN-DAG: v_readlane_b32 s4, [[CSR_VGPR]]

; GCN: s_sub_u32 s32, s32, 0x400{{$}}
; GCN-NEXT: v_readlane_b32 s34, [[CSR_VGPR]], 2
; GCN-NEXT: s_or_saveexec_b64 [[COPY_EXEC1:s\[[0-9]+:[0-9]+\]]], -1{{$}}
; GCN-NEXT: buffer_load_dword [[CSR_VGPR]], off, s[0:3], s32 offset:4 ; 4-byte Folded Reload
; GCN-NEXT: s_mov_b64 exec, [[COPY_EXEC1]]
; GCN-NEXT: s_waitcnt vmcnt(0)

; GCN-NEXT: s_setpc_b64
define void @callee_with_stack_and_call() #0 {
  %alloca = alloca i32, addrspace(5)
  store volatile i32 0, i32 addrspace(5)* %alloca
  call void @external_void_func_void()
  ret void
}

; Should be able to copy incoming stack pointer directly to inner
; call's stack pointer argument.

; There is stack usage only because of the need to evict a VGPR for
; spilling CSR SGPRs.

; GCN-LABEL: {{^}}callee_no_stack_with_call:
; GCN: s_waitcnt
; GCN-NEXT: s_or_saveexec_b64 [[COPY_EXEC0:s\[[0-9]+:[0-9]+\]]], -1{{$}}
; GCN-NEXT: buffer_store_dword [[CSR_VGPR:v[0-9]+]], off, s[0:3], s32 ; 4-byte Folded Spill
; GCN-NEXT: s_mov_b64 exec, [[COPY_EXEC0]]
; GCN-DAG: s_add_u32 s32, s32, 0x400
; GCN-DAG: v_writelane_b32 [[CSR_VGPR]], s34, [[FP_SPILL_LANE:[0-9]+]]

; GCN-DAG: v_writelane_b32 [[CSR_VGPR]], s30, 0
; GCN-DAG: v_writelane_b32 [[CSR_VGPR]], s31, 1
; GCN: s_swappc_b64

; GCN-DAG: v_readlane_b32 s4, v32, 0
; GCN-DAG: v_readlane_b32 s5, v32, 1

; GCN: s_sub_u32 s32, s32, 0x400
; GCN-NEXT: v_readlane_b32 s34, [[CSR_VGPR]], [[FP_SPILL_LANE]]
; GCN-NEXT: s_or_saveexec_b64 [[COPY_EXEC1:s\[[0-9]+:[0-9]+\]]], -1{{$}}
; GCN-NEXT: buffer_load_dword [[CSR_VGPR]], off, s[0:3], s32 ; 4-byte Folded Reload
; GCN-NEXT: s_mov_b64 exec, [[COPY_EXEC1]]
; GCN-NEXT: s_waitcnt vmcnt(0)
; GCN-NEXT: s_setpc_b64
define void @callee_no_stack_with_call() #0 {
  call void @external_void_func_void()
  ret void
}

declare hidden void @external_void_func_void() #0

; Make sure if a CSR vgpr is used for SGPR spilling, it is saved and
; restored. No FP is required.
;
; GCN-LABEL: {{^}}callee_func_sgpr_spill_no_calls:
; GCN: s_or_saveexec_b64 [[COPY_EXEC0:s\[[0-9]+:[0-9]+\]]], -1{{$}}
; GCN-NEXT: buffer_store_dword [[CSR_VGPR:v[0-9]+]], off, s[0:3], s32 ; 4-byte Folded Spill
; GCN-NEXT: s_mov_b64 exec, [[COPY_EXEC0]]
; GCN: v_writelane_b32 [[CSR_VGPR]], s
; GCN: v_writelane_b32 [[CSR_VGPR]], s

; GCN: ;;#ASMSTART
; GCN: v_readlane_b32 s{{[0-9]+}}, [[CSR_VGPR]]
; GCN: v_readlane_b32 s{{[0-9]+}}, [[CSR_VGPR]]

; GCN: s_or_saveexec_b64 [[COPY_EXEC1:s\[[0-9]+:[0-9]+\]]], -1{{$}}
; GCN-NEXT: buffer_load_dword [[CSR_VGPR]], off, s[0:3], s32 ; 4-byte Folded Reload
; GCN-NEXT: s_mov_b64 exec, [[COPY_EXEC1]]
; GCN-NEXT: s_waitcnt
; GCN-NEXT: s_setpc_b64
define void @callee_func_sgpr_spill_no_calls(i32 %in) #0 {
  call void asm sideeffect "", "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7}"() #0
  call void asm sideeffect "", "~{v8},~{v9},~{v10},~{v11},~{v12},~{v13},~{v14},~{v15}"() #0
  call void asm sideeffect "", "~{v16},~{v17},~{v18},~{v19},~{v20},~{v21},~{v22},~{v23}"() #0
  call void asm sideeffect "", "~{v24},~{v25},~{v26},~{v27},~{v28},~{v29},~{v30},~{v31}"() #0

  %wide.sgpr0 = call <16 x i32> asm sideeffect "; def $0", "=s" () #0
  %wide.sgpr1 = call <16 x i32> asm sideeffect "; def $0", "=s" () #0
  %wide.sgpr2 = call <16 x i32> asm sideeffect "; def $0", "=s" () #0
  %wide.sgpr5 = call <16 x i32> asm sideeffect "; def $0", "=s" () #0
  %wide.sgpr3 = call <8 x i32> asm sideeffect "; def $0", "=s" () #0
  %wide.sgpr4 = call <2 x i32> asm sideeffect "; def $0", "=s" () #0

  call void asm sideeffect "; use $0", "s"(<16 x i32> %wide.sgpr0) #0
  call void asm sideeffect "; use $0", "s"(<16 x i32> %wide.sgpr1) #0
  call void asm sideeffect "; use $0", "s"(<16 x i32> %wide.sgpr2) #0
  call void asm sideeffect "; use $0", "s"(<8 x i32> %wide.sgpr3) #0
  call void asm sideeffect "; use $0", "s"(<2 x i32> %wide.sgpr4) #0
  call void asm sideeffect "; use $0", "s"(<16 x i32> %wide.sgpr5) #0
  ret void
}

; Has no spilled CSR VGPRs used for SGPR spilling, so no need to
; enable all lanes and restore.

; GCN-LABEL: {{^}}spill_only_csr_sgpr:
; GCN: s_waitcnt
; GCN-NEXT: v_writelane_b32 v0, s42, 0
; GCN-NEXT: ;;#ASMSTART
; GCN-NEXT: ; clobber s42
; GCN-NEXT: ;;#ASMEND
; GCN-NEXT: v_readlane_b32 s42, v0, 0
; GCN-NEXT: s_setpc_b64
define void @spill_only_csr_sgpr() {
  call void asm sideeffect "; clobber s42", "~{s42}"()
  ret void
}

; TODO: Can the SP inc/deec be remvoed?
; GCN-LABEL: {{^}}callee_with_stack_no_fp_elim_csr_vgpr:
; GCN: s_waitcnt
; GCN-NEXT:s_mov_b32 [[FP_COPY:s[0-9]+]], s34
; GCN-NEXT: s_mov_b32 s34, s32
; GCN: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0
; GCN-DAG: buffer_store_dword v33, off, s[0:3], s34 ; 4-byte Folded Spill
; GCN-DAG: buffer_store_dword [[ZERO]], off, s[0:3], s34 offset:8

; GCN:	;;#ASMSTART
; GCN-NEXT: ; clobber v33
; GCN-NEXT: ;;#ASMEND

; GCN: buffer_load_dword v33, off, s[0:3], s34 ; 4-byte Folded Reload
; GCN: s_add_u32 s32, s32, 0x300
; GCN-NEXT: s_sub_u32 s32, s32, 0x300
; GCN-NEXT: s_mov_b32 s34, s4
; GCN-NEXT: s_waitcnt vmcnt(0)
; GCN-NEXT: s_setpc_b64
define void @callee_with_stack_no_fp_elim_csr_vgpr() #1 {
  %alloca = alloca i32, addrspace(5)
  store volatile i32 0, i32 addrspace(5)* %alloca
  call void asm sideeffect "; clobber v33", "~{v33}"()
  ret void
}

; Use a copy to a free SGPR instead of introducing a second CSR VGPR.
; GCN-LABEL: {{^}}last_lane_vgpr_for_fp_csr:
; GCN: s_waitcnt
; GCN-NEXT: v_writelane_b32 v1, s34, 63
; GCN-NEXT: s_mov_b32 s34, s32
; GCN: buffer_store_dword v33, off, s[0:3], s34 ; 4-byte Folded Spill
; GCN-COUNT-63: v_writelane_b32 v1
; GCN: buffer_store_dword v{{[0-9]+}}, off, s[0:3], s34 offset:8
; GCN: ;;#ASMSTART
; GCN-COUNT-63: v_readlane_b32 s{{[0-9]+}}, v1

; GCN: s_add_u32 s32, s32, 0x300
; GCN-NEXT: s_sub_u32 s32, s32, 0x300
; GCN-NEXT: v_readlane_b32 s34, v1, 63
; GCN-NEXT: s_waitcnt vmcnt(0)
; GCN-NEXT: s_setpc_b64
define void @last_lane_vgpr_for_fp_csr() #1 {
  %alloca = alloca i32, addrspace(5)
  store volatile i32 0, i32 addrspace(5)* %alloca
  call void asm sideeffect "; clobber v33", "~{v33}"()
  call void asm sideeffect "",
    "~{s40},~{s41},~{s42},~{s43},~{s44},~{s45},~{s46},~{s47},~{s48},~{s49}
    ,~{s50},~{s51},~{s52},~{s53},~{s54},~{s55},~{s56},~{s57},~{s58},~{s59}
    ,~{s60},~{s61},~{s62},~{s63},~{s64},~{s65},~{s66},~{s67},~{s68},~{s69}
    ,~{s70},~{s71},~{s72},~{s73},~{s74},~{s75},~{s76},~{s77},~{s78},~{s79}
    ,~{s80},~{s81},~{s82},~{s83},~{s84},~{s85},~{s86},~{s87},~{s88},~{s89}
    ,~{s90},~{s91},~{s92},~{s93},~{s94},~{s95},~{s96},~{s97},~{s98},~{s99}
    ,~{s100},~{s101},~{s102}"() #1

  ret void
}

; Use a copy to a free SGPR instead of introducing a second CSR VGPR.
; GCN-LABEL: {{^}}no_new_vgpr_for_fp_csr:
; GCN: s_waitcnt
; GCN-NEXT: s_mov_b32 [[FP_COPY:s[0-9]+]], s34
; GCN-NEXT: s_mov_b32 s34, s32
; GCN-NEXT: buffer_store_dword v33, off, s[0:3], s34 ; 4-byte Folded Spill
; GCN-COUNT-64: v_writelane_b32 v1,

; GCN: buffer_store_dword
; GCN: ;;#ASMSTART
; GCN-COUNT-64: v_readlane_b32 s{{[0-9]+}}, v1

; GCN: buffer_load_dword v33, off, s[0:3], s34 ; 4-byte Folded Reload
; GCN: s_add_u32 s32, s32, 0x300
; GCN-NEXT: s_sub_u32 s32, s32, 0x300
; GCN-NEXT: s_mov_b32 s34, [[FP_COPY]]
; GCN-NEXT: s_waitcnt vmcnt(0)
; GCN-NEXT: s_setpc_b64
define void @no_new_vgpr_for_fp_csr() #1 {
  %alloca = alloca i32, addrspace(5)
  store volatile i32 0, i32 addrspace(5)* %alloca
  call void asm sideeffect "; clobber v33", "~{v33}"()
  call void asm sideeffect "",
    "~{s39},~{s40},~{s41},~{s42},~{s43},~{s44},~{s45},~{s46},~{s47},~{s48},~{s49}
    ,~{s50},~{s51},~{s52},~{s53},~{s54},~{s55},~{s56},~{s57},~{s58},~{s59}
    ,~{s60},~{s61},~{s62},~{s63},~{s64},~{s65},~{s66},~{s67},~{s68},~{s69}
    ,~{s70},~{s71},~{s72},~{s73},~{s74},~{s75},~{s76},~{s77},~{s78},~{s79}
    ,~{s80},~{s81},~{s82},~{s83},~{s84},~{s85},~{s86},~{s87},~{s88},~{s89}
    ,~{s90},~{s91},~{s92},~{s93},~{s94},~{s95},~{s96},~{s97},~{s98},~{s99}
    ,~{s100},~{s101},~{s102}"() #1

  ret void
}

; GCN-LABEL: {{^}}realign_stack_no_fp_elim:
; GCN: s_waitcnt
; GCN-NEXT: s_add_u32 [[SCRATCH:s[0-9]+]], s32, 0x7ffc0
; GCN-NEXT: s_mov_b32 s4, s34
; GCN-NEXT: s_and_b32 s34, [[SCRATCH]], 0xfff80000
; GCN-NEXT: s_add_u32 s32, s32, 0x100000
; GCN-NEXT: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0
; GCN-NEXT: buffer_store_dword [[ZERO]], off, s[0:3], s34
; GCN-NEXT: s_sub_u32 s32, s32, 0x100000
; GCN-NEXT: s_mov_b32 s34, s4
; GCN-NEXT: s_waitcnt vmcnt(0)
; GCN-NEXT: s_setpc_b64
define void @realign_stack_no_fp_elim() #1 {
  %alloca = alloca i32, align 8192, addrspace(5)
  store volatile i32 0, i32 addrspace(5)* %alloca
  ret void
}

; GCN-LABEL: {{^}}no_unused_non_csr_sgpr_for_fp:
; GCN: s_waitcnt
; GCN-NEXT: v_writelane_b32 v1, s34, 2
; GCN-NEXT: v_writelane_b32 v1, s30, 0
; GCN-NEXT: s_mov_b32 s34, s32
; GCN: v_mov_b32_e32 [[ZERO:v[0-9]+]], 0
; GCN: v_writelane_b32 v1, s31, 1
; GCN: buffer_store_dword [[ZERO]], off, s[0:3], s34 offset:4
; GCN: ;;#ASMSTART
; GCN: v_readlane_b32 s4, v1, 0
; GCN-NEXT: s_add_u32 s32, s32, 0x200
; GCN-NEXT: v_readlane_b32 s5, v1, 1
; GCN-NEXT: s_sub_u32 s32, s32, 0x200
; GCN-NEXT: v_readlane_b32 s34, v1, 2
; GCN-NEXT: s_waitcnt vmcnt(0)
; GCN-NEXT: s_setpc_b64 s[4:5]
define void @no_unused_non_csr_sgpr_for_fp() #1 {
  %alloca = alloca i32, addrspace(5)
  store volatile i32 0, i32 addrspace(5)* %alloca

  ; Use all clobberable registers, so FP has to spill to a VGPR.
  call void asm sideeffect "",
    "~{s0},~{s1},~{s2},~{s3},~{s4},~{s5},~{s6},~{s7},~{s8},~{s9}
    ,~{s10},~{s11},~{s12},~{s13},~{s14},~{s15},~{s16},~{s17},~{s18},~{s19}
    ,~{s20},~{s21},~{s22},~{s23},~{s24},~{s25},~{s26},~{s27},~{s28},~{s29}
    ,~{s30},~{s31}"() #0

  ret void
}

; Need a new CSR VGPR to satisfy the FP spill.
; GCN-LABEL: {{^}}no_unused_non_csr_sgpr_for_fp_no_scratch_vgpr:
; GCN: s_waitcnt
; GCN-NEXT: s_or_saveexec_b64 [[COPY_EXEC0:s\[[0-9]+:[0-9]+\]]], -1{{$}}
; GCN-NEXT: buffer_store_dword [[CSR_VGPR:v[0-9]+]], off, s[0:3], s32 offset:8 ; 4-byte Folded Spill
; GCN-NEXT: s_mov_b64 exec, [[COPY_EXEC0]]
; GCN-NEXT: v_writelane_b32 v32, s34, 2
; GCN-NEXT: v_writelane_b32 v32, s30, 0
; GCN-NEXT: s_mov_b32 s34, s32

; GCN-DAG: v_writelane_b32 v32, s31, 1
; GCN-DAG: buffer_store_dword
; GCN: s_add_u32 s32, s32, 0x300{{$}}

; GCN: ;;#ASMSTART

; GCN: v_readlane_b32 s4, v32, 0
; GCN-NEXT: v_readlane_b32 s5, v32, 1
; GCN-NEXT: s_sub_u32 s32, s32, 0x300{{$}}
; GCN-NEXT: v_readlane_b32 s34, v32, 2
; GCN-NEXT: s_or_saveexec_b64 [[COPY_EXEC1:s\[[0-9]+:[0-9]+\]]], -1{{$}}
; GCN-NEXT: buffer_load_dword [[CSR_VGPR]], off, s[0:3], s32 offset:8 ; 4-byte Folded Reload
; GCN-NEXT: s_mov_b64 exec, [[COPY_EXEC1]]
; GCN-NEXT: s_waitcnt vmcnt(0)
; GCN-NEXT: s_setpc_b64
define void @no_unused_non_csr_sgpr_for_fp_no_scratch_vgpr() #1 {
  %alloca = alloca i32, addrspace(5)
  store volatile i32 0, i32 addrspace(5)* %alloca

  ; Use all clobberable registers, so FP has to spill to a VGPR.
  call void asm sideeffect "",
    "~{s0},~{s1},~{s2},~{s3},~{s4},~{s5},~{s6},~{s7},~{s8},~{s9}
    ,~{s10},~{s11},~{s12},~{s13},~{s14},~{s15},~{s16},~{s17},~{s18},~{s19}
    ,~{s20},~{s21},~{s22},~{s23},~{s24},~{s25},~{s26},~{s27},~{s28},~{s29}
    ,~{s30},~{s31}"() #0

  call void asm sideeffect "; clobber nonpreserved VGPRs",
    "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9}
    ,~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19}
    ,~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29}
    ,~{v30},~{v31}"() #1

  ret void
}

; The byval argument exceeds the MUBUF constant offset, so a scratch
; register is needed to access the CSR VGPR slot.
; GCN-LABEL: {{^}}scratch_reg_needed_mubuf_offset:
; GCN: s_waitcnt
; GCN-NEXT: s_or_saveexec_b64 [[COPY_EXEC0:s\[[0-9]+:[0-9]+\]]], -1{{$}}
; GCN-NEXT: v_mov_b32_e32 [[SCRATCH_VGPR:v[0-9]+]], 0x1008
; GCN-NEXT: buffer_store_dword [[CSR_VGPR:v[0-9]+]], [[SCRATCH_VGPR]], s[0:3], s32 offen ; 4-byte Folded Spill
; GCN-NEXT: s_mov_b64 exec, [[COPY_EXEC0]]
; GCN-NEXT: v_writelane_b32 v32, s34, 2
; GCN-NEXT: v_writelane_b32 v32, s30, 0
; GCN-NEXT: s_mov_b32 s34, s32
; GCN-DAG: v_writelane_b32 v32, s31, 1
; GCN-DAG: s_add_u32 s32, s32, 0x40300{{$}}
; GCN-DAG: buffer_store_dword

; GCN: ;;#ASMSTART

; GCN: v_readlane_b32 s4, v32, 0
; GCN-NEXT: v_readlane_b32 s5, v32, 1
; GCN-NEXT: s_sub_u32 s32, s32, 0x40300{{$}}
; GCN-NEXT: v_readlane_b32 s34, v32, 2
; GCN-NEXT: s_or_saveexec_b64 [[COPY_EXEC1:s\[[0-9]+:[0-9]+\]]], -1{{$}}
; GCN-NEXT: v_mov_b32_e32 [[SCRATCH_VGPR:v[0-9]+]], 0x1008
; GCN-NEXT: buffer_load_dword [[CSR_VGPR]], [[SCRATCH_VGPR]], s[0:3], s32 offen ; 4-byte Folded Reload
; GCN-NEXT: s_mov_b64 exec, [[COPY_EXEC1]]
; GCN-NEXT: s_waitcnt vmcnt(0)
; GCN-NEXT: s_setpc_b64
define void @scratch_reg_needed_mubuf_offset([4096 x i8] addrspace(5)* byval align 4 %arg) #1 {
  %alloca = alloca i32, addrspace(5)
  store volatile i32 0, i32 addrspace(5)* %alloca

  ; Use all clobberable registers, so FP has to spill to a VGPR.
  call void asm sideeffect "; clobber nonpreserved SGPRs",
    "~{s0},~{s1},~{s2},~{s3},~{s4},~{s5},~{s6},~{s7},~{s8},~{s9}
    ,~{s10},~{s11},~{s12},~{s13},~{s14},~{s15},~{s16},~{s17},~{s18},~{s19}
    ,~{s20},~{s21},~{s22},~{s23},~{s24},~{s25},~{s26},~{s27},~{s28},~{s29}
    ,~{s30},~{s31}"() #0

  ; Use all clobberable VGPRs, so a CSR spill is needed for the VGPR
  call void asm sideeffect "; clobber nonpreserved VGPRs",
    "~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6},~{v7},~{v8},~{v9}
    ,~{v10},~{v11},~{v12},~{v13},~{v14},~{v15},~{v16},~{v17},~{v18},~{v19}
    ,~{v20},~{v21},~{v22},~{v23},~{v24},~{v25},~{v26},~{v27},~{v28},~{v29}
    ,~{v30},~{v31}"() #1

  ret void
}

; GCN-LABEL: {{^}}local_empty_func:
; GCN: s_waitcnt
; GCN-NEXT: s_setpc_b64
define internal void @local_empty_func() #0 {
  ret void
}

; An FP is needed, despite not needing any spills
; TODO: Ccould see callee does not use stack and omit FP.
; GCN-LABEL: {{^}}ipra_call_with_stack:
; GCN: s_mov_b32 [[FP_COPY:s[0-9]+]], s34
; GCN: s_mov_b32 s34, s32
; GCN: s_add_u32 s32, s32, 0x400
; GCN: buffer_store_dword v{{[0-9]+}}, off, s[0:3], s34{{$}}
; GCN: s_swappc_b64
; GCN: s_sub_u32 s32, s32, 0x400
; GCN: s_mov_b32 s34, [[FP_COPY:s[0-9]+]]
define void @ipra_call_with_stack() #0 {
  %alloca = alloca i32, addrspace(5)
  store volatile i32 0, i32 addrspace(5)* %alloca
  call void @local_empty_func()
  ret void
}

attributes #0 = { nounwind }
attributes #1 = { nounwind "frame-pointer"="all" }
attributes #2 = { nounwind "frame-pointer"="non-leaf" }