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
|
// RUN: mlir-opt %s \
// RUN: --sparsification --sparse-tensor-conversion \
// RUN: --convert-vector-to-scf --convert-scf-to-std \
// RUN: --func-bufferize --tensor-constant-bufferize --tensor-bufferize \
// RUN: --std-bufferize --finalizing-bufferize \
// RUN: --convert-vector-to-llvm --convert-memref-to-llvm --convert-std-to-llvm | \
// RUN: TENSOR0="%mlir_integration_test_dir/data/wide.mtx" \
// RUN: mlir-cpu-runner \
// RUN: -e entry -entry-point-result=void \
// RUN: -shared-libs=%mlir_integration_test_dir/libmlir_c_runner_utils%shlibext | \
// RUN: FileCheck %s
!Filename = type !llvm.ptr<i8>
#SparseMatrix = #sparse_tensor.encoding<{
dimLevelType = [ "dense", "compressed" ],
pointerBitWidth = 8,
indexBitWidth = 8
}>
#matvec = {
indexing_maps = [
affine_map<(i,j) -> (i,j)>, // A
affine_map<(i,j) -> (j)>, // b
affine_map<(i,j) -> (i)> // x (out)
],
iterator_types = ["parallel", "reduction"],
doc = "X(i) += A(i,j) * B(j)"
}
//
// Integration test that lowers a kernel annotated as sparse to
// actual sparse code, initializes a matching sparse storage scheme
// from file, and runs the resulting code with the JIT compiler.
//
module {
//
// A kernel that multiplies a sparse matrix A with a dense vector b
// into a dense vector x.
//
func @kernel_matvec(%arga: tensor<?x?xi32, #SparseMatrix>,
%argb: tensor<?xi32>,
%argx: tensor<?xi32>) -> tensor<?xi32> {
%0 = linalg.generic #matvec
ins(%arga, %argb: tensor<?x?xi32, #SparseMatrix>, tensor<?xi32>)
outs(%argx: tensor<?xi32>) {
^bb(%a: i32, %b: i32, %x: i32):
%0 = muli %a, %b : i32
%1 = addi %x, %0 : i32
linalg.yield %1 : i32
} -> tensor<?xi32>
return %0 : tensor<?xi32>
}
func private @getTensorFilename(index) -> (!Filename)
//
// Main driver that reads matrix from file and calls the sparse kernel.
//
func @entry() {
%i0 = constant 0 : i32
%c0 = constant 0 : index
%c1 = constant 1 : index
%c4 = constant 4 : index
%c256 = constant 256 : index
// Read the sparse matrix from file, construct sparse storage.
%fileName = call @getTensorFilename(%c0) : (index) -> (!Filename)
%a = sparse_tensor.new %fileName : !llvm.ptr<i8> to tensor<?x?xi32, #SparseMatrix>
// Initialize dense vectors.
%bdata = memref.alloc(%c256) : memref<?xi32>
%xdata = memref.alloc(%c4) : memref<?xi32>
scf.for %i = %c0 to %c256 step %c1 {
%k = addi %i, %c1 : index
%j = index_cast %k : index to i32
memref.store %j, %bdata[%i] : memref<?xi32>
}
scf.for %i = %c0 to %c4 step %c1 {
memref.store %i0, %xdata[%i] : memref<?xi32>
}
%b = memref.tensor_load %bdata : memref<?xi32>
%x = memref.tensor_load %xdata : memref<?xi32>
// Call kernel.
%0 = call @kernel_matvec(%a, %b, %x)
: (tensor<?x?xi32, #SparseMatrix>, tensor<?xi32>, tensor<?xi32>) -> tensor<?xi32>
// Print the result for verification.
//
// CHECK: ( 889, 1514, -21, -3431 )
//
%m = memref.buffer_cast %0 : memref<?xi32>
%v = vector.transfer_read %m[%c0], %i0: memref<?xi32>, vector<4xi32>
vector.print %v : vector<4xi32>
// Release the resources.
memref.dealloc %bdata : memref<?xi32>
memref.dealloc %xdata : memref<?xi32>
return
}
}
|
