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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-module-lds < %s --amdgpu-lower-module-lds-strategy=module | FileCheck -check-prefixes=CHECK,MODULE %s
; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-module-lds < %s --amdgpu-lower-module-lds-strategy=table | FileCheck -check-prefixes=CHECK,TABLE %s
; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-module-lds < %s --amdgpu-lower-module-lds-strategy=kernel | FileCheck -check-prefixes=CHECK,K_OR_HY %s
; RUN: opt -S -mtriple=amdgcn-- -passes=amdgpu-lower-module-lds < %s --amdgpu-lower-module-lds-strategy=hybrid | FileCheck -check-prefixes=CHECK,K_OR_HY %s
;; Same checks for kernel and for hybrid as an unambiguous reference to a variable - one where exactly one kernel
;; can reach it - is the case where hybrid lowering can always prefer the direct access.
;; Single kernel is sole user of single variable, all options codegen as direct access to kernel struct
@k0.lds = addrspace(3) global i8 undef
define amdgpu_kernel void @k0() {
; CHECK-LABEL: @k0(
; CHECK-NEXT: [[LD:%.*]] = load i8, ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, align 1
; CHECK-NEXT: [[MUL:%.*]] = mul i8 [[LD]], 2
; CHECK-NEXT: store i8 [[MUL]], ptr addrspace(3) @llvm.amdgcn.kernel.k0.lds, align 1
; CHECK-NEXT: ret void
;
%ld = load i8, ptr addrspace(3) @k0.lds
%mul = mul i8 %ld, 2
store i8 %mul, ptr addrspace(3) @k0.lds
ret void
}
;; Function is reachable from one kernel. Variable goes in module lds or the kernel struct, but never both.
@f0.lds = addrspace(3) global i16 undef
define void @f0() {
; MODULE-LABEL: @f0(
; MODULE-NEXT: [[LD:%.*]] = load i16, ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_MODULE_LDS_T:%.*]], ptr addrspace(3) @llvm.amdgcn.module.lds, i32 0, i32 1), align 4, !alias.scope [[META1:![0-9]+]], !noalias [[META4:![0-9]+]]
; MODULE-NEXT: [[MUL:%.*]] = mul i16 [[LD]], 3
; MODULE-NEXT: store i16 [[MUL]], ptr addrspace(3) getelementptr inbounds ([[LLVM_AMDGCN_MODULE_LDS_T]], ptr addrspace(3) @llvm.amdgcn.module.lds, i32 0, i32 1), align 4, !alias.scope [[META1]], !noalias [[META4]]
; MODULE-NEXT: ret void
;
; TABLE-LABEL: @f0(
; TABLE-NEXT: [[TMP1:%.*]] = call i32 @llvm.amdgcn.lds.kernel.id()
; TABLE-NEXT: [[F0_LDS2:%.*]] = getelementptr inbounds [2 x [2 x i32]], ptr addrspace(4) @llvm.amdgcn.lds.offset.table, i32 0, i32 [[TMP1]], i32 1
; TABLE-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(4) [[F0_LDS2]], align 4
; TABLE-NEXT: [[F0_LDS3:%.*]] = inttoptr i32 [[TMP2]] to ptr addrspace(3)
; TABLE-NEXT: [[LD:%.*]] = load i16, ptr addrspace(3) [[F0_LDS3]], align 2
; TABLE-NEXT: [[MUL:%.*]] = mul i16 [[LD]], 3
; TABLE-NEXT: [[F0_LDS:%.*]] = getelementptr inbounds [2 x [2 x i32]], ptr addrspace(4) @llvm.amdgcn.lds.offset.table, i32 0, i32 [[TMP1]], i32 1
; TABLE-NEXT: [[TMP3:%.*]] = load i32, ptr addrspace(4) [[F0_LDS]], align 4
; TABLE-NEXT: [[F0_LDS1:%.*]] = inttoptr i32 [[TMP3]] to ptr addrspace(3)
; TABLE-NEXT: store i16 [[MUL]], ptr addrspace(3) [[F0_LDS1]], align 2
; TABLE-NEXT: ret void
;
; K_OR_HY-LABEL: @f0(
; K_OR_HY-NEXT: [[LD:%.*]] = load i16, ptr addrspace(3) @llvm.amdgcn.kernel.k_f0.lds, align 2
; K_OR_HY-NEXT: [[MUL:%.*]] = mul i16 [[LD]], 3
; K_OR_HY-NEXT: store i16 [[MUL]], ptr addrspace(3) @llvm.amdgcn.kernel.k_f0.lds, align 2
; K_OR_HY-NEXT: ret void
;
%ld = load i16, ptr addrspace(3) @f0.lds
%mul = mul i16 %ld, 3
store i16 %mul, ptr addrspace(3) @f0.lds
ret void
}
define amdgpu_kernel void @k_f0() {
; MODULE-LABEL: @k_f0(
; MODULE-NEXT: call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ], !alias.scope [[META5:![0-9]+]], !noalias [[META1]]
; MODULE-NEXT: call void @f0()
; MODULE-NEXT: ret void
;
; TABLE-LABEL: @k_f0(
; TABLE-NEXT: call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k_f0.lds) ]
; TABLE-NEXT: call void @f0()
; TABLE-NEXT: ret void
;
; K_OR_HY-LABEL: @k_f0(
; K_OR_HY-NEXT: call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k_f0.lds) ]
; K_OR_HY-NEXT: call void @f0()
; K_OR_HY-NEXT: ret void
;
call void @f0()
ret void
}
;; As above, but with the kernel also uing the variable.
@both.lds = addrspace(3) global i32 undef
define void @f_both() {
; MODULE-LABEL: @f_both(
; MODULE-NEXT: [[LD:%.*]] = load i32, ptr addrspace(3) @llvm.amdgcn.module.lds, align 4, !alias.scope [[META5]], !noalias [[META4]]
; MODULE-NEXT: [[MUL:%.*]] = mul i32 [[LD]], 4
; MODULE-NEXT: store i32 [[MUL]], ptr addrspace(3) @llvm.amdgcn.module.lds, align 4, !alias.scope [[META5]], !noalias [[META4]]
; MODULE-NEXT: ret void
;
; TABLE-LABEL: @f_both(
; TABLE-NEXT: [[TMP1:%.*]] = call i32 @llvm.amdgcn.lds.kernel.id()
; TABLE-NEXT: [[BOTH_LDS2:%.*]] = getelementptr inbounds [2 x [2 x i32]], ptr addrspace(4) @llvm.amdgcn.lds.offset.table, i32 0, i32 [[TMP1]], i32 0
; TABLE-NEXT: [[TMP2:%.*]] = load i32, ptr addrspace(4) [[BOTH_LDS2]], align 4
; TABLE-NEXT: [[BOTH_LDS3:%.*]] = inttoptr i32 [[TMP2]] to ptr addrspace(3)
; TABLE-NEXT: [[LD:%.*]] = load i32, ptr addrspace(3) [[BOTH_LDS3]], align 4
; TABLE-NEXT: [[MUL:%.*]] = mul i32 [[LD]], 4
; TABLE-NEXT: [[BOTH_LDS:%.*]] = getelementptr inbounds [2 x [2 x i32]], ptr addrspace(4) @llvm.amdgcn.lds.offset.table, i32 0, i32 [[TMP1]], i32 0
; TABLE-NEXT: [[TMP3:%.*]] = load i32, ptr addrspace(4) [[BOTH_LDS]], align 4
; TABLE-NEXT: [[BOTH_LDS1:%.*]] = inttoptr i32 [[TMP3]] to ptr addrspace(3)
; TABLE-NEXT: store i32 [[MUL]], ptr addrspace(3) [[BOTH_LDS1]], align 4
; TABLE-NEXT: ret void
;
; K_OR_HY-LABEL: @f_both(
; K_OR_HY-NEXT: [[LD:%.*]] = load i32, ptr addrspace(3) @llvm.amdgcn.kernel.k0_both.lds, align 4
; K_OR_HY-NEXT: [[MUL:%.*]] = mul i32 [[LD]], 4
; K_OR_HY-NEXT: store i32 [[MUL]], ptr addrspace(3) @llvm.amdgcn.kernel.k0_both.lds, align 4
; K_OR_HY-NEXT: ret void
;
%ld = load i32, ptr addrspace(3) @both.lds
%mul = mul i32 %ld, 4
store i32 %mul, ptr addrspace(3) @both.lds
ret void
}
define amdgpu_kernel void @k0_both() {
; MODULE-LABEL: @k0_both(
; MODULE-NEXT: call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.module.lds) ]
; MODULE-NEXT: [[LD:%.*]] = load i32, ptr addrspace(3) @llvm.amdgcn.module.lds, align 4, !alias.scope [[META5]], !noalias [[META1]]
; MODULE-NEXT: [[MUL:%.*]] = mul i32 [[LD]], 5
; MODULE-NEXT: store i32 [[MUL]], ptr addrspace(3) @llvm.amdgcn.module.lds, align 4, !alias.scope [[META5]], !noalias [[META1]]
; MODULE-NEXT: call void @f_both()
; MODULE-NEXT: ret void
;
; TABLE-LABEL: @k0_both(
; TABLE-NEXT: call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k0_both.lds) ]
; TABLE-NEXT: [[LD:%.*]] = load i32, ptr addrspace(3) @llvm.amdgcn.kernel.k0_both.lds, align 4
; TABLE-NEXT: [[MUL:%.*]] = mul i32 [[LD]], 5
; TABLE-NEXT: store i32 [[MUL]], ptr addrspace(3) @llvm.amdgcn.kernel.k0_both.lds, align 4
; TABLE-NEXT: call void @f_both()
; TABLE-NEXT: ret void
;
; K_OR_HY-LABEL: @k0_both(
; K_OR_HY-NEXT: call void @llvm.donothing() [ "ExplicitUse"(ptr addrspace(3) @llvm.amdgcn.kernel.k0_both.lds) ]
; K_OR_HY-NEXT: [[LD:%.*]] = load i32, ptr addrspace(3) @llvm.amdgcn.kernel.k0_both.lds, align 4
; K_OR_HY-NEXT: [[MUL:%.*]] = mul i32 [[LD]], 5
; K_OR_HY-NEXT: store i32 [[MUL]], ptr addrspace(3) @llvm.amdgcn.kernel.k0_both.lds, align 4
; K_OR_HY-NEXT: call void @f_both()
; K_OR_HY-NEXT: ret void
;
%ld = load i32, ptr addrspace(3) @both.lds
%mul = mul i32 %ld, 5
store i32 %mul, ptr addrspace(3) @both.lds
call void @f_both()
ret void
}
|
