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
|
// RUN: mlir-opt %s --gpu-to-llvm='use-opaque-pointers=1' | FileCheck %s
module attributes {gpu.container_module} {
// CHECK-LABEL: func @matvec
// CHECK: llvm.call @mgpuStreamCreate
// CHECK: llvm.call @mgpuMemAlloc
// CHECK: llvm.call @mgpuMemAlloc
// CHECK: llvm.call @mgpuCreateCoo
// CHECK: llvm.call @mgpuCreateDnVec
// CHECK: llvm.call @mgpuSpMVBufferSize
// CHECK: llvm.call @mgpuSpMV
// CHECK: llvm.call @mgpuDestroySpMat
// CHECK: llvm.call @mgpuDestroyDnVec
// CHECK: llvm.call @mgpuStreamSynchronize
// CHECK: llvm.call @mgpuStreamDestroy
func.func @matvec(%arg0: index) {
%token0 = gpu.wait async
%mem1, %token1 = gpu.alloc async [%token0] (%arg0) : memref<?xindex>
%mem2, %token2 = gpu.alloc async [%token1] (%arg0) : memref<?xf64>
%spmat, %token4 = gpu.create_coo async [%token2] %arg0, %arg0, %arg0, %mem1, %mem1, %mem2 : memref<?xindex>, memref<?xindex>, memref<?xf64>
%dnvec, %token5 = gpu.create_dn_tensor async [%token4] %mem2, %arg0 : index into memref<?xf64>
%bufferSz, %token6 = gpu.spmv_buffer_size async [%token5] %spmat, %dnvec, %dnvec into f64
%token7 = gpu.spmv async [%token6] %spmat, %dnvec, %dnvec, %mem2 : memref<?xf64> into f64
%token8 = gpu.destroy_sp_mat async [%token7] %spmat
%token9 = gpu.destroy_dn_tensor async [%token8] %dnvec
gpu.wait [%token9]
return
}
// CHECK-LABEL: func @matmul
// CHECK: llvm.call @mgpuStreamCreate
// CHECK: llvm.call @mgpuMemAlloc
// CHECK: llvm.call @mgpuMemAlloc
// CHECK: llvm.call @mgpuCreateCsr
// CHECK: llvm.call @mgpuCreateDnMat
// CHECK: llvm.call @mgpuSpMMBufferSize
// CHECK: llvm.call @mgpuSpMM
// CHECK: llvm.call @mgpuDestroySpMat
// CHECK: llvm.call @mgpuDestroyDnMat
// CHECK: llvm.call @mgpuStreamSynchronize
// CHECK: llvm.call @mgpuStreamDestroy
func.func @matmul(%arg0: index) {
%token0 = gpu.wait async
%mem1, %token1 = gpu.alloc async [%token0] (%arg0) : memref<?xindex>
%mem2, %token2 = gpu.alloc async [%token1] (%arg0) : memref<?xf64>
%spmat, %token4 = gpu.create_csr async [%token2] %arg0, %arg0, %arg0, %mem1, %mem1, %mem2 : memref<?xindex>, memref<?xindex>, memref<?xf64>
%dnmat, %token5 = gpu.create_dn_tensor async [%token4] %mem2, %arg0, %arg0 : index, index into memref<?xf64>
%bufferSz, %token6 = gpu.spmm_buffer_size async [%token5] %spmat, %dnmat, %dnmat : index into f64
%token7 = gpu.spmm async [%token6] %spmat, %dnmat, %dnmat, %mem2 : memref<?xf64> into f64
%token8 = gpu.destroy_sp_mat async [%token7] %spmat
%token9 = gpu.destroy_dn_tensor async [%token8] %dnmat
gpu.wait [%token9]
return
}
// CHECK-LABEL: func @sddmm
// CHECK: llvm.call @mgpuStreamCreate
// CHECK: llvm.call @mgpuMemAlloc
// CHECK: llvm.call @mgpuMemAlloc
// CHECK: llvm.call @mgpuCreateCsr
// CHECK: llvm.call @mgpuCreateDnMat
// CHECK: llvm.call @mgpuSDDMMBufferSize
// CHECK: llvm.call @mgpuSDDMM
// CHECK: llvm.call @mgpuDestroySpMat
// CHECK: llvm.call @mgpuDestroyDnMat
// CHECK: llvm.call @mgpuStreamSynchronize
// CHECK: llvm.call @mgpuStreamDestroy
func.func @sddmm(%arg0: index) {
%token0 = gpu.wait async
%mem1, %token1 = gpu.alloc async [%token0] (%arg0) : memref<?xindex>
%mem2, %token2 = gpu.alloc async [%token1] (%arg0) : memref<?xf64>
%spmat, %token4 = gpu.create_csr async [%token2] %arg0, %arg0, %arg0, %mem1, %mem1, %mem2 : memref<?xindex>, memref<?xindex>, memref<?xf64>
%dnmat, %token5 = gpu.create_dn_tensor async [%token4] %mem2, %arg0, %arg0 : index, index into memref<?xf64>
%bufferSz, %token6 = gpu.sddmm_buffer_size async [%token5] %dnmat, %dnmat, %spmat into f64
%token7 = gpu.sddmm async [%token6] %dnmat, %dnmat, %spmat, %mem2 : memref<?xf64> into f64
%token8 = gpu.destroy_sp_mat async [%token7] %spmat
%token9 = gpu.destroy_dn_tensor async [%token8] %dnmat
gpu.wait [%token9]
return
}
}
|
