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
|
// RUN: mlir-opt %s --gpu-to-llvm="gpu-binary-annotation=nvvm.cubin use-opaque-pointers=1" | FileCheck %s
// RUN: mlir-opt %s --gpu-to-llvm="gpu-binary-annotation=rocdl.hsaco use-opaque-pointers=1" | 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<f32>,
%arg2: !llvm.ptr<f32>, %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: [[MODULE:%.*]] = llvm.call @mgpuModuleLoad([[BINARY]])
// 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.null : !llvm.ptr
// CHECK: llvm.call @mgpuLaunchKernel([[FUNC]], [[C8]], [[C8]], [[C8]],
// CHECK-SAME: [[C8]], [[C8]], [[C8]], [[C256]], [[STREAM]],
// CHECK-SAME: [[PARAMS]], [[EXTRA_PARAMS]])
// CHECK: llvm.call @mgpuStreamSynchronize
// CHECK: llvm.call @mgpuStreamDestroy
// CHECK: llvm.call @mgpuModuleUnload
}
|
