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
|
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx900 -verify-machineinstrs -o - %s | FileCheck %s
@lds0 = addrspace(3) global [512 x float] undef
@lds1 = addrspace(3) global [256 x float] undef
@lds2 = addrspace(3) global [4096 x float] undef
@lds3 = addrspace(3) global [67 x i8] undef
@dynamic_shared0 = external addrspace(3) global [0 x float]
@dynamic_shared1 = external addrspace(3) global [0 x double]
@dynamic_shared2 = external addrspace(3) global [0 x double], align 4
@dynamic_shared3 = external addrspace(3) global [0 x double], align 16
; CHECK-LABEL: {{^}}dynamic_shared_array_0:
; CHECK: v_add_u32_e32 v{{[0-9]+}}, 0x800, v{{[0-9]+}}
define amdgpu_kernel void @dynamic_shared_array_0(float addrspace(1)* %out) {
%tid.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds0, i32 0, i32 %tid.x
%val0 = load float, float addrspace(3)* %arrayidx0, align 4
%arrayidx1 = getelementptr inbounds [0 x float], [0 x float] addrspace(3)* @dynamic_shared0, i32 0, i32 %tid.x
store float %val0, float addrspace(3)* %arrayidx1, align 4
ret void
}
; CHECK-LABEL: {{^}}dynamic_shared_array_1:
; CHECK: v_mov_b32_e32 [[DYNLDS:v[0-9]+]], 0xc00
; CHECK: v_lshl_add_u32 {{v[0-9]+}}, {{v[0-9]+}}, 2, [[DYNLDS]]
define amdgpu_kernel void @dynamic_shared_array_1(float addrspace(1)* %out, i32 %cond) {
entry:
%tid.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%idx.0 = add nsw i32 %tid.x, 64
%tmp = icmp eq i32 %cond, 0
br i1 %tmp, label %if, label %else
if: ; preds = %entry
%arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds0, i32 0, i32 %idx.0
%val0 = load float, float addrspace(3)* %arrayidx0, align 4
br label %endif
else: ; preds = %entry
%arrayidx1 = getelementptr inbounds [256 x float], [256 x float] addrspace(3)* @lds1, i32 0, i32 %idx.0
%val1 = load float, float addrspace(3)* %arrayidx1, align 4
br label %endif
endif: ; preds = %else, %if
%val = phi float [ %val0, %if ], [ %val1, %else ]
%arrayidx = getelementptr inbounds [0 x float], [0 x float] addrspace(3)* @dynamic_shared0, i32 0, i32 %tid.x
store float %val, float addrspace(3)* %arrayidx, align 4
ret void
}
; CHECK-LABEL: {{^}}dynamic_shared_array_2:
; CHECK: v_mov_b32_e32 [[DYNLDS:v[0-9]+]], 0x4000
; CHECK: v_lshl_add_u32 {{v[0-9]+}}, {{v[0-9]+}}, 2, [[DYNLDS]]
define amdgpu_kernel void @dynamic_shared_array_2(i32 %idx) {
%tid.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%vidx = add i32 %tid.x, %idx
%arrayidx0 = getelementptr inbounds [4096 x float], [4096 x float] addrspace(3)* @lds2, i32 0, i32 %vidx
%val0 = load float, float addrspace(3)* %arrayidx0, align 4
%arrayidx1 = getelementptr inbounds [0 x float], [0 x float] addrspace(3)* @dynamic_shared0, i32 0, i32 %tid.x
store float %val0, float addrspace(3)* %arrayidx1, align 4
ret void
}
; The offset to the dynamic shared memory array should be aligned on the type
; specified.
; CHECK-LABEL: {{^}}dynamic_shared_array_3:
; CHECK: v_mov_b32_e32 [[DYNLDS:v[0-9]+]], 0x44
; CHECK: v_lshl_add_u32 {{v[0-9]+}}, {{v[0-9]+}}, 2, [[DYNLDS]]
define amdgpu_kernel void @dynamic_shared_array_3(i32 %idx) {
%tid.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%vidx = add i32 %tid.x, %idx
%arrayidx0 = getelementptr inbounds [67 x i8], [67 x i8] addrspace(3)* @lds3, i32 0, i32 %vidx
%val0 = load i8, i8 addrspace(3)* %arrayidx0, align 4
%val1 = uitofp i8 %val0 to float
%arrayidx1 = getelementptr inbounds [0 x float], [0 x float] addrspace(3)* @dynamic_shared0, i32 0, i32 %tid.x
store float %val1, float addrspace(3)* %arrayidx1, align 4
ret void
}
; The offset to the dynamic shared memory array should be aligned on the
; maximal one.
; CHECK-LABEL: {{^}}dynamic_shared_array_4:
; CHECK: v_mov_b32_e32 [[DYNLDS:v[0-9]+]], 0x48
; CHECK-DAG: v_lshl_add_u32 {{v[0-9]+}}, {{v[0-9]+}}, 2, [[DYNLDS]]
; CHECK-DAG: v_lshl_add_u32 {{v[0-9]+}}, {{v[0-9]+}}, 3, [[DYNLDS]]
define amdgpu_kernel void @dynamic_shared_array_4(i32 %idx) {
%tid.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%vidx = add i32 %tid.x, %idx
%arrayidx0 = getelementptr inbounds [67 x i8], [67 x i8] addrspace(3)* @lds3, i32 0, i32 %vidx
%val0 = load i8, i8 addrspace(3)* %arrayidx0, align 4
%val1 = uitofp i8 %val0 to float
%val2 = uitofp i8 %val0 to double
%arrayidx1 = getelementptr inbounds [0 x float], [0 x float] addrspace(3)* @dynamic_shared0, i32 0, i32 %tid.x
store float %val1, float addrspace(3)* %arrayidx1, align 4
%arrayidx2 = getelementptr inbounds [0 x double], [0 x double] addrspace(3)* @dynamic_shared1, i32 0, i32 %tid.x
store double %val2, double addrspace(3)* %arrayidx2, align 4
ret void
}
; Honor the explicit alignment from the specified variable.
; CHECK-LABEL: {{^}}dynamic_shared_array_5:
; CHECK: v_mov_b32_e32 [[DYNLDS:v[0-9]+]], 0x44
; CHECK-DAG: v_lshl_add_u32 {{v[0-9]+}}, {{v[0-9]+}}, 2, [[DYNLDS]]
; CHECK-DAG: v_lshl_add_u32 {{v[0-9]+}}, {{v[0-9]+}}, 3, [[DYNLDS]]
define amdgpu_kernel void @dynamic_shared_array_5(i32 %idx) {
%tid.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%vidx = add i32 %tid.x, %idx
%arrayidx0 = getelementptr inbounds [67 x i8], [67 x i8] addrspace(3)* @lds3, i32 0, i32 %vidx
%val0 = load i8, i8 addrspace(3)* %arrayidx0, align 4
%val1 = uitofp i8 %val0 to float
%val2 = uitofp i8 %val0 to double
%arrayidx1 = getelementptr inbounds [0 x float], [0 x float] addrspace(3)* @dynamic_shared0, i32 0, i32 %tid.x
store float %val1, float addrspace(3)* %arrayidx1, align 4
%arrayidx2 = getelementptr inbounds [0 x double], [0 x double] addrspace(3)* @dynamic_shared2, i32 0, i32 %tid.x
store double %val2, double addrspace(3)* %arrayidx2, align 4
ret void
}
; Honor the explicit alignment from the specified variable.
; CHECK-LABEL: {{^}}dynamic_shared_array_6:
; CHECK: v_mov_b32_e32 [[DYNLDS:v[0-9]+]], 0x50
; CHECK-DAG: v_lshl_add_u32 {{v[0-9]+}}, {{v[0-9]+}}, 2, [[DYNLDS]]
; CHECK-DAG: v_lshl_add_u32 {{v[0-9]+}}, {{v[0-9]+}}, 3, [[DYNLDS]]
define amdgpu_kernel void @dynamic_shared_array_6(i32 %idx) {
%tid.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%vidx = add i32 %tid.x, %idx
%arrayidx0 = getelementptr inbounds [67 x i8], [67 x i8] addrspace(3)* @lds3, i32 0, i32 %vidx
%val0 = load i8, i8 addrspace(3)* %arrayidx0, align 4
%val1 = uitofp i8 %val0 to float
%val2 = uitofp i8 %val0 to double
%arrayidx1 = getelementptr inbounds [0 x float], [0 x float] addrspace(3)* @dynamic_shared0, i32 0, i32 %tid.x
store float %val1, float addrspace(3)* %arrayidx1, align 4
%arrayidx2 = getelementptr inbounds [0 x double], [0 x double] addrspace(3)* @dynamic_shared3, i32 0, i32 %tid.x
store double %val2, double addrspace(3)* %arrayidx2, align 4
ret void
}
; CHECK-LABEL: dynamic_shared_array_with_call:
; CHECK-NOT: s_swappc_b64
define amdgpu_kernel void @dynamic_shared_array_with_call(float addrspace(1)* nocapture readnone %out) local_unnamed_addr {
%tid.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%1 = sext i32 %tid.x to i64
%arrayidx0 = getelementptr inbounds [512 x float], [512 x float] addrspace(3)* @lds0, i64 0, i64 %1
%val0 = load float, float addrspace(3)* %arrayidx0, align 4
tail call void @store_value(float %val0)
ret void
}
; CHECK-NOT: store_value
define linkonce_odr hidden void @store_value(float %val1) local_unnamed_addr {
entry:
%tid.x = tail call i32 @llvm.amdgcn.workitem.id.x()
%0 = sext i32 %tid.x to i64
%arrayidx1 = getelementptr inbounds [0 x float], [0 x float] addrspace(3)* @dynamic_shared0, i64 0, i64 %0
store float %val1, float addrspace(3)* %arrayidx1, align 4
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x()
|
