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
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -mattr=-flat-for-global -amdgpu-sroa=0 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,VI,MESA %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=hawaii -amdgpu-sroa=0 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,CI,MESA %s
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -mattr=-flat-for-global -amdgpu-sroa=0 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9,VI,MESA %s
; GCN-LABEL: {{^}}i32_fastcc_i32_i32:
; GCN: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-NEXT: v_add_i32_e32 v0, vcc, v1, v0
; GCN-NEXT: s_setpc_b64
define fastcc i32 @i32_fastcc_i32_i32(i32 %arg0, i32 %arg1) #1 {
%add0 = add i32 %arg0, %arg1
ret i32 %add0
}
; GCN-LABEL: {{^}}sibling_call_i32_fastcc_i32_i32:
define fastcc i32 @sibling_call_i32_fastcc_i32_i32(i32 %a, i32 %b, i32 %c) #1 {
entry:
%ret = tail call fastcc i32 @i32_fastcc_i32_i32(i32 %a, i32 %b)
ret i32 %ret
}
; GCN-LABEL: {{^}}sibling_call_i32_fastcc_i32_i32_stack_object:
; GCN: v_mov_b32_e32 [[NINE:v[0-9]+]], 9
; GCN: buffer_store_dword [[NINE]], off, s[0:3], s5 offset:24
; GCN: s_setpc_b64
define fastcc i32 @sibling_call_i32_fastcc_i32_i32_stack_object(i32 %a, i32 %b, i32 %c) #1 {
entry:
%alloca = alloca [16 x i32], align 4
%gep = getelementptr inbounds [16 x i32], [16 x i32]* %alloca, i32 0, i32 5
store volatile i32 9, i32* %gep
%ret = tail call fastcc i32 @i32_fastcc_i32_i32(i32 %a, i32 %b)
ret i32 %ret
}
; GCN-LABEL: {{^}}sibling_call_i32_fastcc_i32_i32_unused_result:
define fastcc void @sibling_call_i32_fastcc_i32_i32_unused_result(i32 %a, i32 %b, i32 %c) #1 {
entry:
%ret = tail call fastcc i32 @i32_fastcc_i32_i32(i32 %a, i32 %b)
ret void
}
; It doesn't make sense to do a tail from a kernel
; GCN-LABEL: {{^}}kernel_call_i32_fastcc_i32_i32_unused_result:
;define amdgpu_kernel void @kernel_call_i32_fastcc_i32_i32_unused_result(i32 %a, i32 %b, i32 %c) #1 {
define amdgpu_kernel void @kernel_call_i32_fastcc_i32_i32_unused_result(i32 %a, i32 %b, i32 %c) #1 {
entry:
%ret = tail call fastcc i32 @i32_fastcc_i32_i32(i32 %a, i32 %b)
ret void
}
; GCN-LABEL: {{^}}i32_fastcc_i32_byval_i32:
; GCN: s_waitcnt
; GCN-NEXT: s_mov_b32 s5, s32
; GCN-NEXT: buffer_load_dword v1, off, s[0:3], s5 offset:4
; GCN-NEXT: s_waitcnt vmcnt(0)
; GCN-NEXT: v_add_i32_e32 v0, vcc, v1, v0
; GCN-NEXT: s_setpc_b64 s[30:31]
define fastcc i32 @i32_fastcc_i32_byval_i32(i32 %arg0, i32* byval align 4 %arg1) #1 {
%arg1.load = load i32, i32* %arg1, align 4
%add0 = add i32 %arg0, %arg1.load
ret i32 %add0
}
; Tail call disallowed with byval in parent.
; GCN-LABEL: {{^}}sibling_call_i32_fastcc_i32_byval_i32_byval_parent:
; GCN: buffer_store_dword v{{[0-9]+}}, off, s[0:3], s32 offset:4
; GCN: s_swappc_b64
; GCN: s_setpc_b64
define fastcc i32 @sibling_call_i32_fastcc_i32_byval_i32_byval_parent(i32 %a, i32* byval %b.byval, i32 %c) #1 {
entry:
%ret = tail call fastcc i32 @i32_fastcc_i32_byval_i32(i32 %a, i32* %b.byval)
ret i32 %ret
}
; Tail call disallowed with byval in parent, not callee.
; GCN-LABEL: {{^}}sibling_call_i32_fastcc_i32_byval_i32:
; GCN-NOT: v0
; GCN-NOT: s32
; GCN: buffer_load_dword v1, off, s[0:3], s4 offset:16
; GCN: s_mov_b32 s5, s32
; GCN: buffer_store_dword v1, off, s[0:3], s5 offset:4
; GCN-NEXT: s_setpc_b64
define fastcc i32 @sibling_call_i32_fastcc_i32_byval_i32(i32 %a, [16 x i32] %large) #1 {
entry:
%ret = tail call fastcc i32 @i32_fastcc_i32_byval_i32(i32 %a, i32* inttoptr (i32 16 to i32*))
ret i32 %ret
}
; GCN-LABEL: {{^}}i32_fastcc_i32_i32_a32i32:
; GCN: s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
; GCN-DAG: buffer_load_dword [[LOAD_0:v[0-9]+]], off, s[0:3], s5 offset:4
; GCN-DAG: buffer_load_dword [[LOAD_1:v[0-9]+]], off, s[0:3], s5 offset:8
; GCN-DAG: v_add_i32_e32 v0, vcc, v1, v0
; GCN: v_add_i32_e32 v0, vcc, [[LOAD_0]], v0
; GCN: v_add_i32_e32 v0, vcc, [[LOAD_1]], v0
; GCN-NEXT: s_setpc_b64
define fastcc i32 @i32_fastcc_i32_i32_a32i32(i32 %arg0, i32 %arg1, [32 x i32] %large) #1 {
%val_firststack = extractvalue [32 x i32] %large, 30
%val_laststack = extractvalue [32 x i32] %large, 31
%add0 = add i32 %arg0, %arg1
%add1 = add i32 %add0, %val_firststack
%add2 = add i32 %add1, %val_laststack
ret i32 %add2
}
; FIXME: Why load and store same location for stack args?
; GCN-LABEL: {{^}}sibling_call_i32_fastcc_i32_i32_a32i32:
; GCN: s_mov_b32 s5, s32
; GCN-DAG: buffer_store_dword v32, off, s[0:3], s5 offset:16 ; 4-byte Folded Spill
; GCN-DAG: buffer_store_dword v33, off, s[0:3], s5 offset:12 ; 4-byte Folded Spill
; GCN-DAG: buffer_load_dword [[LOAD_0:v[0-9]+]], off, s[0:3], s5 offset:4
; GCN-DAG: buffer_load_dword [[LOAD_1:v[0-9]+]], off, s[0:3], s5 offset:8
; GCN-NOT: s32
; GCN-DAG: buffer_store_dword [[LOAD_0]], off, s[0:3], s5 offset:4
; GCN-DAG: buffer_store_dword [[LOAD_1]], off, s[0:3], s5 offset:8
; GCN-DAG: buffer_load_dword v32, off, s[0:3], s5 offset:16 ; 4-byte Folded Reload
; GCN-DAG: buffer_load_dword v33, off, s[0:3], s5 offset:12 ; 4-byte Folded Reload
; GCN-NOT: s32
; GCN: s_setpc_b64
define fastcc i32 @sibling_call_i32_fastcc_i32_i32_a32i32(i32 %a, i32 %b, [32 x i32] %c) #1 {
entry:
%ret = tail call fastcc i32 @i32_fastcc_i32_i32_a32i32(i32 %a, i32 %b, [32 x i32] %c)
ret i32 %ret
}
; GCN-LABEL: {{^}}sibling_call_i32_fastcc_i32_i32_a32i32_stack_object:
; GCN-DAG: s_mov_b32 s5, s32
; GCN-NOT: s32
; GCN-DAG: v_mov_b32_e32 [[NINE:v[0-9]+]], 9
; GCN: buffer_store_dword [[NINE]], off, s[0:3], s5 offset:44
; GCN-NOT: s32
; GCN: s_setpc_b64
define fastcc i32 @sibling_call_i32_fastcc_i32_i32_a32i32_stack_object(i32 %a, i32 %b, [32 x i32] %c) #1 {
entry:
%alloca = alloca [16 x i32], align 4
%gep = getelementptr inbounds [16 x i32], [16 x i32]* %alloca, i32 0, i32 5
store volatile i32 9, i32* %gep
%ret = tail call fastcc i32 @i32_fastcc_i32_i32_a32i32(i32 %a, i32 %b, [32 x i32] %c)
ret i32 %ret
}
; If the callee requires more stack argument space than the caller,
; don't do a tail call.
; TODO: Do we really need this restriction?
; GCN-LABEL: {{^}}no_sibling_call_callee_more_stack_space:
; GCN: s_swappc_b64
; GCN: s_setpc_b64
define fastcc i32 @no_sibling_call_callee_more_stack_space(i32 %a, i32 %b) #1 {
entry:
%ret = tail call fastcc i32 @i32_fastcc_i32_i32_a32i32(i32 %a, i32 %b, [32 x i32] zeroinitializer)
ret i32 %ret
}
; Have another non-tail in the function
; GCN-LABEL: {{^}}sibling_call_i32_fastcc_i32_i32_other_call:
; GCN: s_mov_b32 s5, s32
; GCN: buffer_store_dword v34, off, s[0:3], s5 offset:12
; GCN: buffer_store_dword v32, off, s[0:3], s5 offset:8 ; 4-byte Folded Spill
; GCN: buffer_store_dword v33, off, s[0:3], s5 offset:4 ; 4-byte Folded Spill
; GCN-DAG: v_writelane_b32 v34, s33, 0
; GCN-DAG: v_writelane_b32 v34, s34, 1
; GCN-DAG: v_writelane_b32 v34, s35, 2
; GCN-DAG: s_add_u32 s32, s32, 0x400
; GCN: s_getpc_b64
; GCN: s_swappc_b64
; GCN: s_getpc_b64 s[6:7]
; GCN: s_add_u32 s6, s6, sibling_call_i32_fastcc_i32_i32@rel32@lo+4
; GCN: s_addc_u32 s7, s7, sibling_call_i32_fastcc_i32_i32@rel32@hi+4
; GCN-DAG: v_readlane_b32 s33, v34, 0
; GCN-DAG: v_readlane_b32 s34, v34, 1
; GCN-DAG: v_readlane_b32 s35, v34, 2
; GCN: buffer_load_dword v33, off, s[0:3], s5 offset:4
; GCN: buffer_load_dword v32, off, s[0:3], s5 offset:8
; GCN: buffer_load_dword v34, off, s[0:3], s5 offset:12
; GCN: s_sub_u32 s32, s32, 0x400
; GCN: s_setpc_b64 s[6:7]
define fastcc i32 @sibling_call_i32_fastcc_i32_i32_other_call(i32 %a, i32 %b, i32 %c) #1 {
entry:
%other.call = tail call fastcc i32 @i32_fastcc_i32_i32(i32 %a, i32 %b)
%ret = tail call fastcc i32 @sibling_call_i32_fastcc_i32_i32(i32 %a, i32 %b, i32 %other.call)
ret i32 %ret
}
; Have stack object in caller and stack passed arguments. SP should be
; in same place at function exit.
; GCN-LABEL: {{^}}sibling_call_stack_objecti32_fastcc_i32_i32_a32i32:
; GCN: s_mov_b32 s5, s32
; GCN-NOT: s32
; GCN: s_setpc_b64 s[6:7]
define fastcc i32 @sibling_call_stack_objecti32_fastcc_i32_i32_a32i32(i32 %a, i32 %b, [32 x i32] %c) #1 {
entry:
%alloca = alloca [16 x i32], align 4
%gep = getelementptr inbounds [16 x i32], [16 x i32]* %alloca, i32 0, i32 5
store volatile i32 9, i32* %gep
%ret = tail call fastcc i32 @i32_fastcc_i32_i32_a32i32(i32 %a, i32 %b, [32 x i32] %c)
ret i32 %ret
}
; GCN-LABEL: {{^}}sibling_call_stack_objecti32_fastcc_i32_i32_a32i32_larger_arg_area:
; GCN: s_mov_b32 s5, s32
; GCN-NOT: s32
; GCN: s_setpc_b64 s[6:7]
define fastcc i32 @sibling_call_stack_objecti32_fastcc_i32_i32_a32i32_larger_arg_area(i32 %a, i32 %b, [36 x i32] %c) #1 {
entry:
%alloca = alloca [16 x i32], align 4
%gep = getelementptr inbounds [16 x i32], [16 x i32]* %alloca, i32 0, i32 5
store volatile i32 9, i32* %gep
%ret = tail call fastcc i32 @i32_fastcc_i32_i32_a32i32(i32 %a, i32 %b, [32 x i32] zeroinitializer)
ret i32 %ret
}
attributes #0 = { nounwind }
attributes #1 = { nounwind noinline }
|
