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
|
// DEFINE: %{option} = enable-runtime-library=true
// DEFINE: %{compile} = mlir-opt %s --sparse-compiler=%{option}
// DEFINE: %{run} = mlir-cpu-runner \
// DEFINE: -e entry -entry-point-result=void \
// DEFINE: -shared-libs=%mlir_c_runner_utils | \
// DEFINE: FileCheck %s
//
// RUN: %{compile} | %{run}
//
// Do the same run, but now with direct IR generation.
// REDEFINE: %{option} = enable-runtime-library=false
// RUN: %{compile} | %{run}
//
// Do the same run, but now with direct IR generation and vectorization.
// REDEFINE: %{option} = "enable-runtime-library=false vl=2 reassociate-fp-reductions=true enable-index-optimizations=true"
// RUN: %{compile} | %{run}
// Do the same run, but now with direct IR generation and, if available, VLA
// vectorization.
// REDEFINE: %{option} = "enable-runtime-library=false vl=4 enable-arm-sve=%ENABLE_VLA"
// REDEFINE: %{run} = %lli_host_or_aarch64_cmd \
// REDEFINE: --entry-function=entry_lli \
// REDEFINE: --extra-module=%S/Inputs/main_for_lli.ll \
// REDEFINE: %VLA_ARCH_ATTR_OPTIONS \
// REDEFINE: --dlopen=%mlir_native_utils_lib_dir/libmlir_c_runner_utils%shlibext | \
// REDEFINE: FileCheck %s
// RUN: %{compile} | mlir-translate -mlir-to-llvmir | %{run}
!Filename = !llvm.ptr<i8>
#SparseMatrix = #sparse_tensor.encoding<{
lvlTypes = [ "compressed", "compressed" ]
}>
#trait_sum_reduce = {
indexing_maps = [
affine_map<(i,j) -> (i,j)>, // A
affine_map<(i,j) -> ()> // x (out)
],
iterator_types = ["reduction", "reduction"],
doc = "x += A(i,j)"
}
module {
//
// A kernel that sum-reduces a matrix to a single scalar.
//
func.func @kernel_sum_reduce(%arga: tensor<?x?xf16, #SparseMatrix>,
%argx: tensor<f16>) -> tensor<f16> {
%0 = linalg.generic #trait_sum_reduce
ins(%arga: tensor<?x?xf16, #SparseMatrix>)
outs(%argx: tensor<f16>) {
^bb(%a: f16, %x: f16):
%0 = arith.addf %x, %a : f16
linalg.yield %0 : f16
} -> tensor<f16>
return %0 : tensor<f16>
}
func.func private @getTensorFilename(index) -> (!Filename)
//
// Main driver that reads matrix from file and calls the sparse kernel.
//
func.func @entry() {
// Setup input sparse matrix from compressed constant.
%d = arith.constant dense <[
[ 1.1, 1.2, 0.0, 1.4 ],
[ 0.0, 0.0, 0.0, 0.0 ],
[ 3.1, 0.0, 3.3, 3.4 ]
]> : tensor<3x4xf16>
%a = sparse_tensor.convert %d : tensor<3x4xf16> to tensor<?x?xf16, #SparseMatrix>
%d0 = arith.constant 0.0 : f16
// Setup memory for a single reduction scalar,
// initialized to zero.
%x = tensor.from_elements %d0 : tensor<f16>
// Call the kernel.
%0 = call @kernel_sum_reduce(%a, %x)
: (tensor<?x?xf16, #SparseMatrix>, tensor<f16>) -> tensor<f16>
// Print the result for verification.
//
// CHECK: 13.5
//
%v = tensor.extract %0[] : tensor<f16>
%vf = arith.extf %v: f16 to f32
vector.print %vf : f32
// Release the resources.
bufferization.dealloc_tensor %a : tensor<?x?xf16, #SparseMatrix>
return
}
}
|
