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
|
; RUN: llc -march=amdgcn -mcpu=tonga -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefix=VI -check-prefix=GCN %s
; FIXME: Need to handle non-uniform case for function below (load without gep).
; GCN-LABEL: {{^}}v_test_add_i16:
; VI: flat_load_ushort [[A:v[0-9]+]]
; VI: flat_load_ushort [[B:v[0-9]+]]
; VI: v_add_u16_e32 [[ADD:v[0-9]+]], [[A]], [[B]]
; VI-NEXT: buffer_store_short [[ADD]]
define amdgpu_kernel void @v_test_add_i16(i16 addrspace(1)* %out, i16 addrspace(1)* %in0, i16 addrspace(1)* %in1) #1 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%gep.out = getelementptr inbounds i16, i16 addrspace(1)* %out, i32 %tid
%gep.in0 = getelementptr inbounds i16, i16 addrspace(1)* %in0, i32 %tid
%gep.in1 = getelementptr inbounds i16, i16 addrspace(1)* %in1, i32 %tid
%a = load volatile i16, i16 addrspace(1)* %gep.in0
%b = load volatile i16, i16 addrspace(1)* %gep.in1
%add = add i16 %a, %b
store i16 %add, i16 addrspace(1)* %out
ret void
}
; FIXME: Need to handle non-uniform case for function below (load without gep).
; GCN-LABEL: {{^}}v_test_add_i16_constant:
; VI: flat_load_ushort [[A:v[0-9]+]]
; VI: v_add_u16_e32 [[ADD:v[0-9]+]], 0x7b, [[A]]
; VI-NEXT: buffer_store_short [[ADD]]
define amdgpu_kernel void @v_test_add_i16_constant(i16 addrspace(1)* %out, i16 addrspace(1)* %in0) #1 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%gep.out = getelementptr inbounds i16, i16 addrspace(1)* %out, i32 %tid
%gep.in0 = getelementptr inbounds i16, i16 addrspace(1)* %in0, i32 %tid
%a = load volatile i16, i16 addrspace(1)* %gep.in0
%add = add i16 %a, 123
store i16 %add, i16 addrspace(1)* %out
ret void
}
; FIXME: Need to handle non-uniform case for function below (load without gep).
; GCN-LABEL: {{^}}v_test_add_i16_neg_constant:
; VI: flat_load_ushort [[A:v[0-9]+]]
; VI: v_add_u16_e32 [[ADD:v[0-9]+]], 0xfffffcb3, [[A]]
; VI-NEXT: buffer_store_short [[ADD]]
define amdgpu_kernel void @v_test_add_i16_neg_constant(i16 addrspace(1)* %out, i16 addrspace(1)* %in0) #1 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%gep.out = getelementptr inbounds i16, i16 addrspace(1)* %out, i32 %tid
%gep.in0 = getelementptr inbounds i16, i16 addrspace(1)* %in0, i32 %tid
%a = load volatile i16, i16 addrspace(1)* %gep.in0
%add = add i16 %a, -845
store i16 %add, i16 addrspace(1)* %out
ret void
}
; FIXME: Need to handle non-uniform case for function below (load without gep).
; GCN-LABEL: {{^}}v_test_add_i16_inline_neg1:
; VI: flat_load_ushort [[A:v[0-9]+]]
; VI: v_add_u16_e32 [[ADD:v[0-9]+]], -1, [[A]]
; VI-NEXT: buffer_store_short [[ADD]]
define amdgpu_kernel void @v_test_add_i16_inline_neg1(i16 addrspace(1)* %out, i16 addrspace(1)* %in0) #1 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%gep.out = getelementptr inbounds i16, i16 addrspace(1)* %out, i32 %tid
%gep.in0 = getelementptr inbounds i16, i16 addrspace(1)* %in0, i32 %tid
%a = load volatile i16, i16 addrspace(1)* %gep.in0
%add = add i16 %a, -1
store i16 %add, i16 addrspace(1)* %out
ret void
}
; FIXME: Need to handle non-uniform case for function below (load without gep).
; GCN-LABEL: {{^}}v_test_add_i16_zext_to_i32:
; VI: flat_load_ushort [[A:v[0-9]+]]
; VI: flat_load_ushort [[B:v[0-9]+]]
; VI: v_add_u16_e32 [[ADD:v[0-9]+]], [[A]], [[B]]
; VI-NEXT: buffer_store_dword [[ADD]]
define amdgpu_kernel void @v_test_add_i16_zext_to_i32(i32 addrspace(1)* %out, i16 addrspace(1)* %in0, i16 addrspace(1)* %in1) #1 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 %tid
%gep.in0 = getelementptr inbounds i16, i16 addrspace(1)* %in0, i32 %tid
%gep.in1 = getelementptr inbounds i16, i16 addrspace(1)* %in1, i32 %tid
%a = load volatile i16, i16 addrspace(1)* %gep.in0
%b = load volatile i16, i16 addrspace(1)* %gep.in1
%add = add i16 %a, %b
%ext = zext i16 %add to i32
store i32 %ext, i32 addrspace(1)* %out
ret void
}
; FIXME: Need to handle non-uniform case for function below (load without gep).
; GCN-LABEL: {{^}}v_test_add_i16_zext_to_i64:
; VI: flat_load_ushort [[A:v[0-9]+]]
; VI: flat_load_ushort [[B:v[0-9]+]]
; VI-DAG: v_add_u16_e32 v[[ADD:[0-9]+]], [[A]], [[B]]
; VI: buffer_store_dwordx2 v{{\[}}[[ADD]]:{{[0-9]+\]}}, off, {{s\[[0-9]+:[0-9]+\]}}, 0{{$}}
define amdgpu_kernel void @v_test_add_i16_zext_to_i64(i64 addrspace(1)* %out, i16 addrspace(1)* %in0, i16 addrspace(1)* %in1) #1 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%gep.out = getelementptr inbounds i64, i64 addrspace(1)* %out, i32 %tid
%gep.in0 = getelementptr inbounds i16, i16 addrspace(1)* %in0, i32 %tid
%gep.in1 = getelementptr inbounds i16, i16 addrspace(1)* %in1, i32 %tid
%a = load volatile i16, i16 addrspace(1)* %gep.in0
%b = load volatile i16, i16 addrspace(1)* %gep.in1
%add = add i16 %a, %b
%ext = zext i16 %add to i64
store i64 %ext, i64 addrspace(1)* %out
ret void
}
; FIXME: Need to handle non-uniform case for function below (load without gep).
; GCN-LABEL: {{^}}v_test_add_i16_sext_to_i32:
; VI: flat_load_ushort [[A:v[0-9]+]]
; VI: flat_load_ushort [[B:v[0-9]+]]
; VI: v_add_u16_e32 [[ADD:v[0-9]+]], [[A]], [[B]]
; VI-NEXT: v_bfe_i32 [[SEXT:v[0-9]+]], [[ADD]], 0, 16
; VI-NEXT: buffer_store_dword [[SEXT]]
define amdgpu_kernel void @v_test_add_i16_sext_to_i32(i32 addrspace(1)* %out, i16 addrspace(1)* %in0, i16 addrspace(1)* %in1) #1 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%gep.out = getelementptr inbounds i32, i32 addrspace(1)* %out, i32 %tid
%gep.in0 = getelementptr inbounds i16, i16 addrspace(1)* %in0, i32 %tid
%gep.in1 = getelementptr inbounds i16, i16 addrspace(1)* %in1, i32 %tid
%a = load i16, i16 addrspace(1)* %gep.in0
%b = load i16, i16 addrspace(1)* %gep.in1
%add = add i16 %a, %b
%ext = sext i16 %add to i32
store i32 %ext, i32 addrspace(1)* %out
ret void
}
; FIXME: Need to handle non-uniform case for function below (load without gep).
; GCN-LABEL: {{^}}v_test_add_i16_sext_to_i64:
; VI: flat_load_ushort [[A:v[0-9]+]]
; VI: flat_load_ushort [[B:v[0-9]+]]
; VI: v_add_u16_e32 [[ADD:v[0-9]+]], [[A]], [[B]]
; VI-NEXT: v_bfe_i32 v[[LO:[0-9]+]], [[ADD]], 0, 16
; VI-NEXT: v_ashrrev_i32_e32 v[[HI:[0-9]+]], 31, v[[LO]]
; VI-NEXT: buffer_store_dwordx2 v{{\[}}[[LO]]:[[HI]]{{\]}}
define amdgpu_kernel void @v_test_add_i16_sext_to_i64(i64 addrspace(1)* %out, i16 addrspace(1)* %in0, i16 addrspace(1)* %in1) #1 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%gep.out = getelementptr inbounds i64, i64 addrspace(1)* %out, i32 %tid
%gep.in0 = getelementptr inbounds i16, i16 addrspace(1)* %in0, i32 %tid
%gep.in1 = getelementptr inbounds i16, i16 addrspace(1)* %in1, i32 %tid
%a = load i16, i16 addrspace(1)* %gep.in0
%b = load i16, i16 addrspace(1)* %gep.in1
%add = add i16 %a, %b
%ext = sext i16 %add to i64
store i64 %ext, i64 addrspace(1)* %out
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x() #0
attributes #0 = { nounwind readnone }
attributes #1 = { nounwind }
|
