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
|
// RUN: mlir-opt %s --gpu-to-llvm="gpu-binary-annotation=nvvm.cubin" -split-input-file | FileCheck %s
// RUN: mlir-opt %s --gpu-to-llvm="gpu-binary-annotation=rocdl.hsaco" -split-input-file | FileCheck %s --check-prefix=ROCDL
module attributes {gpu.container_module} {
// CHECK: llvm.mlir.global internal constant @[[KERNEL_NAME:.*]]("kernel\00")
// CHECK: llvm.mlir.global internal constant @[[GLOBAL:.*]]("CUBIN")
// ROCDL: llvm.mlir.global internal constant @[[GLOBAL:.*]]("HSACO")
gpu.module @kernel_module attributes {
nvvm.cubin = "CUBIN", rocdl.hsaco = "HSACO"
} {
llvm.func @kernel(%arg0: i32, %arg1: !llvm.ptr,
%arg2: !llvm.ptr, %arg3: i64, %arg4: i64,
%arg5: i64) attributes {gpu.kernel} {
llvm.return
}
}
func.func @foo(%buffer: memref<?xf32>) {
%c8 = arith.constant 8 : index
%c32 = arith.constant 32 : i32
%c256 = arith.constant 256 : i32
gpu.launch_func @kernel_module::@kernel
blocks in (%c8, %c8, %c8)
threads in (%c8, %c8, %c8)
dynamic_shared_memory_size %c256
args(%c32 : i32, %buffer : memref<?xf32>)
return
}
// CHECK-DAG: [[C256:%.*]] = llvm.mlir.constant(256 : i32) : i32
// CHECK-DAG: [[C8:%.*]] = llvm.mlir.constant(8 : index) : i64
// CHECK: [[ADDRESSOF:%.*]] = llvm.mlir.addressof @[[GLOBAL]]
// CHECK: [[BINARY:%.*]] = llvm.getelementptr [[ADDRESSOF]]{{\[}}0, 0]
// CHECK-SAME: -> !llvm.ptr
// CHECK: [[BINARYSIZE:%.*]] = llvm.mlir.constant
// CHECK: [[MODULE:%.*]] = llvm.call @mgpuModuleLoad([[BINARY]], [[BINARYSIZE]])
// CHECK: [[PARAMSCOUNT:%.*]] = llvm.mlir.constant
// CHECK: [[FUNC:%.*]] = llvm.call @mgpuModuleGetFunction([[MODULE]], {{.*}})
// CHECK: [[STREAM:%.*]] = llvm.call @mgpuStreamCreate
// CHECK: %[[ONE:.*]] = llvm.mlir.constant(1 : i32)
// CHECK: %[[MEMREF:.*]] = llvm.alloca %[[ONE]] x !llvm.struct[[STRUCT_BODY:<.*>]]
// CHECK: [[NUM_PARAMS:%.*]] = llvm.mlir.constant(6 : i32) : i32
// CHECK-NEXT: [[PARAMS:%.*]] = llvm.alloca [[NUM_PARAMS]] x !llvm.ptr
// CHECK: llvm.getelementptr %[[MEMREF]][0, 0] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct[[STRUCT_BODY:<.*>]]
// CHECK: llvm.getelementptr %[[MEMREF]][0, 1] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct[[STRUCT_BODY:<.*>]]
// CHECK: llvm.getelementptr %[[MEMREF]][0, 2] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct[[STRUCT_BODY:<.*>]]
// CHECK: llvm.getelementptr %[[MEMREF]][0, 3] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct[[STRUCT_BODY:<.*>]]
// CHECK: llvm.getelementptr %[[MEMREF]][0, 4] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct[[STRUCT_BODY:<.*>]]
// CHECK: llvm.getelementptr %[[MEMREF]][0, 5] : (!llvm.ptr) -> !llvm.ptr, !llvm.struct[[STRUCT_BODY:<.*>]]
// CHECK: [[EXTRA_PARAMS:%.*]] = llvm.mlir.zero : !llvm.ptr
// CHECK: llvm.call @mgpuLaunchKernel([[FUNC]], [[C8]], [[C8]], [[C8]],
// CHECK-SAME: [[C8]], [[C8]], [[C8]], [[C256]], [[STREAM]],
// CHECK-SAME: [[PARAMS]], [[EXTRA_PARAMS]], [[PARAMSCOUNT]])
// CHECK: llvm.call @mgpuStreamSynchronize
// CHECK: llvm.call @mgpuStreamDestroy
// CHECK: llvm.call @mgpuModuleUnload
}
// -----
module attributes {gpu.container_module} {
// CHECK: gpu.module
// ROCDL: gpu.module
gpu.module @kernel_module [#nvvm.target] {
llvm.func @kernel(%arg0: i32, %arg1: !llvm.ptr,
%arg2: !llvm.ptr, %arg3: i64, %arg4: i64,
%arg5: i64) attributes {gpu.kernel} {
llvm.return
}
}
func.func @foo(%buffer: memref<?xf32>) {
// CHECK: [[C8:%.*]] = llvm.mlir.constant(8 : index) : i64
// CHECK: [[C32:%.*]] = llvm.mlir.constant(32 : i32) : i32
// CHECK: [[C256:%.*]] = llvm.mlir.constant(256 : i32) : i32
%c8 = arith.constant 8 : index
%c32 = arith.constant 32 : i32
%c256 = arith.constant 256 : i32
// CHECK: gpu.launch_func @kernel_module::@kernel
// CHECK: blocks in ([[C8]], [[C8]], [[C8]]) threads in ([[C8]], [[C8]], [[C8]]) : i64
// CHECK: dynamic_shared_memory_size [[C256]]
// CHECK: args([[C32]] : i32, %{{.*}} : !llvm.ptr, %{{.*}} : !llvm.ptr, %{{.*}} : i64, %{{.*}} : i64, %{{.*}} : i64)
gpu.launch_func @kernel_module::@kernel
blocks in (%c8, %c8, %c8)
threads in (%c8, %c8, %c8)
dynamic_shared_memory_size %c256
args(%c32 : i32, %buffer : memref<?xf32>)
return
}
}
// -----
module attributes {gpu.container_module} {
// CHECK: gpu.module
gpu.module @kernel_module [#nvvm.target] {
llvm.func @kernel(%arg0: i32, %arg1: !llvm.ptr,
%arg2: !llvm.ptr, %arg3: i64, %arg4: i64,
%arg5: i64) attributes {gpu.kernel} {
llvm.return
}
}
func.func @foo(%buffer: memref<?xf32>) {
// CHECK: [[C8:%.*]] = llvm.mlir.constant(8 : index) : i64
// CHECK: [[C32:%.*]] = llvm.mlir.constant(32 : i32) : i32
// CHECK: [[C256:%.*]] = llvm.mlir.constant(256 : i32) : i32
// CHECK: [[C2:%.*]] = llvm.mlir.constant(2 : index) : i64
%c8 = arith.constant 8 : index
%c32 = arith.constant 32 : i32
%c256 = arith.constant 256 : i32
%c2 = arith.constant 2 : index
// CHECK: gpu.launch_func @kernel_module::@kernel
// CHECK: clusters in ([[C2]], [[C2]], [[C2]])
// CHECK: blocks in ([[C8]], [[C8]], [[C8]]) threads in ([[C8]], [[C8]], [[C8]]) : i64
// CHECK: dynamic_shared_memory_size [[C256]]
// CHECK: args([[C32]] : i32, %{{.*}} : !llvm.ptr, %{{.*}} : !llvm.ptr, %{{.*}} : i64, %{{.*}} : i64, %{{.*}} : i64)
gpu.launch_func @kernel_module::@kernel
clusters in (%c2, %c2, %c2)
blocks in (%c8, %c8, %c8)
threads in (%c8, %c8, %c8)
dynamic_shared_memory_size %c256
args(%c32 : i32, %buffer : memref<?xf32>)
return
}
}
|
