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
|
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=SI %s
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=GCN -check-prefix=VI %s
; Test that add/sub with a constant is swapped to sub/add with negated
; constant to minimize code size.
; GCN-LABEL: {{^}}v_test_i32_x_sub_64:
; GCN: {{buffer|flat}}_load_dword [[X:v[0-9]+]]
; GCN: v_subrev_{{[iu]}}32_e32 v{{[0-9]+}}, vcc, 64, [[X]]
define amdgpu_kernel void @v_test_i32_x_sub_64(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%tid.ext = sext i32 %tid to i64
%gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %tid.ext
%x = load i32, i32 addrspace(1)* %gep
%result = sub i32 %x, 64
store i32 %result, i32 addrspace(1)* %gep.out
ret void
}
; GCN-LABEL: {{^}}v_test_i32_x_sub_64_multi_use:
; GCN: {{buffer|flat}}_load_dword [[X:v[0-9]+]]
; GCN: {{buffer|flat}}_load_dword [[Y:v[0-9]+]]
; GCN-DAG: v_subrev_{{[iu]}}32_e32 v{{[0-9]+}}, vcc, 64, [[X]]
; GCN-DAG: v_subrev_{{[iu]}}32_e32 v{{[0-9]+}}, vcc, 64, [[Y]]
define amdgpu_kernel void @v_test_i32_x_sub_64_multi_use(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%tid.ext = sext i32 %tid to i64
%gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %tid.ext
%x = load volatile i32, i32 addrspace(1)* %gep
%y = load volatile i32, i32 addrspace(1)* %gep
%result0 = sub i32 %x, 64
%result1 = sub i32 %y, 64
store volatile i32 %result0, i32 addrspace(1)* %gep.out
store volatile i32 %result1, i32 addrspace(1)* %gep.out
ret void
}
; GCN-LABEL: {{^}}v_test_i32_64_sub_x:
; GCN: {{buffer|flat}}_load_dword [[X:v[0-9]+]]
; GCN: v_sub_{{[iu]}}32_e32 v{{[0-9]+}}, vcc, 64, [[X]]
define amdgpu_kernel void @v_test_i32_64_sub_x(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%tid.ext = sext i32 %tid to i64
%gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %tid.ext
%x = load i32, i32 addrspace(1)* %gep
%result = sub i32 64, %x
store i32 %result, i32 addrspace(1)* %gep.out
ret void
}
; GCN-LABEL: {{^}}v_test_i32_x_sub_65:
; GCN: {{buffer|flat}}_load_dword [[X:v[0-9]+]]
; GCN: v_add_{{[iu]}}32_e32 v{{[0-9]+}}, vcc, 0xffffffbf, [[X]]
define amdgpu_kernel void @v_test_i32_x_sub_65(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%tid.ext = sext i32 %tid to i64
%gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %tid.ext
%x = load i32, i32 addrspace(1)* %gep
%result = sub i32 %x, 65
store i32 %result, i32 addrspace(1)* %gep.out
ret void
}
; GCN-LABEL: {{^}}v_test_i32_65_sub_x:
; GCN: {{buffer|flat}}_load_dword [[X:v[0-9]+]]
; GCN: v_sub_{{[iu]}}32_e32 v{{[0-9]+}}, vcc, 0x41, [[X]]
define amdgpu_kernel void @v_test_i32_65_sub_x(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%tid.ext = sext i32 %tid to i64
%gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %tid.ext
%x = load i32, i32 addrspace(1)* %gep
%result = sub i32 65, %x
store i32 %result, i32 addrspace(1)* %gep.out
ret void
}
; GCN-LABEL: {{^}}v_test_i32_x_sub_neg16:
; GCN: {{buffer|flat}}_load_dword [[X:v[0-9]+]]
; GCN: v_add_{{[iu]}}32_e32 v{{[0-9]+}}, vcc, 16, [[X]]
define amdgpu_kernel void @v_test_i32_x_sub_neg16(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%tid.ext = sext i32 %tid to i64
%gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %tid.ext
%x = load i32, i32 addrspace(1)* %gep
%result = sub i32 %x, -16
store i32 %result, i32 addrspace(1)* %gep.out
ret void
}
; GCN-LABEL: {{^}}v_test_i32_neg16_sub_x:
; GCN: {{buffer|flat}}_load_dword [[X:v[0-9]+]]
; GCN: v_sub_{{[iu]}}32_e32 v{{[0-9]+}}, vcc, -16, [[X]]
define amdgpu_kernel void @v_test_i32_neg16_sub_x(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%tid.ext = sext i32 %tid to i64
%gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %tid.ext
%x = load i32, i32 addrspace(1)* %gep
%result = sub i32 -16, %x
store i32 %result, i32 addrspace(1)* %gep.out
ret void
}
; GCN-LABEL: {{^}}v_test_i32_x_sub_neg17:
; GCN: {{buffer|flat}}_load_dword [[X:v[0-9]+]]
; GCN: v_add_{{[iu]}}32_e32 v{{[0-9]+}}, vcc, 17, [[X]]
define amdgpu_kernel void @v_test_i32_x_sub_neg17(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%tid.ext = sext i32 %tid to i64
%gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %tid.ext
%x = load i32, i32 addrspace(1)* %gep
%result = sub i32 %x, -17
store i32 %result, i32 addrspace(1)* %gep.out
ret void
}
; GCN-LABEL: {{^}}v_test_i32_neg17_sub_x:
; GCN: {{buffer|flat}}_load_dword [[X:v[0-9]+]]
; GCN: v_sub_{{[iu]}}32_e32 v{{[0-9]+}}, vcc, 0xffffffef, [[X]]
define amdgpu_kernel void @v_test_i32_neg17_sub_x(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%tid.ext = sext i32 %tid to i64
%gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %tid.ext
%x = load i32, i32 addrspace(1)* %gep
%result = sub i32 -17, %x
store i32 %result, i32 addrspace(1)* %gep.out
ret void
}
; GCN-LABEL: {{^}}s_test_i32_x_sub_64:
; GCN: s_load_dword [[X:s[0-9]+]]
; GCN: s_sub_i32 s{{[0-9]+}}, [[X]], 64
define amdgpu_kernel void @s_test_i32_x_sub_64(i32 %x) #0 {
%result = sub i32 %x, 64
call void asm sideeffect "; use $0", "s"(i32 %result)
ret void
}
; GCN-LABEL: {{^}}v_test_i16_x_sub_64:
; VI: {{buffer|flat}}_load_ushort [[X:v[0-9]+]]
; VI: v_subrev_u16_e32 v{{[0-9]+}}, 64, [[X]]
define amdgpu_kernel void @v_test_i16_x_sub_64(i16 addrspace(1)* %out, i16 addrspace(1)* %in) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%tid.ext = sext i32 %tid to i64
%gep = getelementptr inbounds i16, i16 addrspace(1)* %in, i64 %tid.ext
%gep.out = getelementptr inbounds i16, i16 addrspace(1)* %out, i64 %tid.ext
%x = load i16, i16 addrspace(1)* %gep
%result = sub i16 %x, 64
store i16 %result, i16 addrspace(1)* %gep.out
ret void
}
; GCN-LABEL: {{^}}v_test_i16_x_sub_64_multi_use:
; GCN: {{buffer|flat}}_load_ushort [[X:v[0-9]+]]
; GCN: {{buffer|flat}}_load_ushort [[Y:v[0-9]+]]
; VI-DAG: v_subrev_u16_e32 v{{[0-9]+}}, 64, [[X]]
; VI-DAG: v_subrev_u16_e32 v{{[0-9]+}}, 64, [[Y]]
; SI-DAG: v_subrev_i32_e32 v{{[0-9]+}}, vcc, 64, [[X]]
; SI-DAG: v_subrev_i32_e32 v{{[0-9]+}}, vcc, 64, [[Y]]
define amdgpu_kernel void @v_test_i16_x_sub_64_multi_use(i16 addrspace(1)* %out, i16 addrspace(1)* %in) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%tid.ext = sext i32 %tid to i64
%gep = getelementptr inbounds i16, i16 addrspace(1)* %in, i64 %tid.ext
%gep.out = getelementptr inbounds i16, i16 addrspace(1)* %out, i64 %tid.ext
%x = load volatile i16, i16 addrspace(1)* %gep
%y = load volatile i16, i16 addrspace(1)* %gep
%result0 = sub i16 %x, 64
%result1 = sub i16 %y, 64
store volatile i16 %result0, i16 addrspace(1)* %gep.out
store volatile i16 %result1, i16 addrspace(1)* %gep.out
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x() #1
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }
|
