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
|
#pragma once
#ifdef __GNUC__
#pragma GCC diagnostic push
#pragma GCC diagnostic ignored "-Wunused-parameter"
#endif
//===- MLModelRunner.h ---- ML model runner interface -----------*- C++ -*-===//
//
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
// See https://llvm.org/LICENSE.txt for license information.
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
//
//===----------------------------------------------------------------------===//
//
#ifndef LLVM_ANALYSIS_MLMODELRUNNER_H
#define LLVM_ANALYSIS_MLMODELRUNNER_H
#include "llvm/Analysis/TensorSpec.h"
#include "llvm/IR/PassManager.h"
namespace llvm {
class LLVMContext;
/// MLModelRunner interface: abstraction of a mechanism for evaluating a
/// ML model. More abstractly, evaluating a function that has as tensors as
/// arguments, described via TensorSpecs, and returns a tensor. Currently, the
/// latter is assumed to be a scalar, in absence of more elaborate scenarios.
/// NOTE: feature indices are expected to be consistent all accross
/// MLModelRunners (pertaining to the same model), and also Loggers (see
/// TFUtils.h)
class MLModelRunner {
public:
// Disallows copy and assign.
MLModelRunner(const MLModelRunner &) = delete;
MLModelRunner &operator=(const MLModelRunner &) = delete;
virtual ~MLModelRunner() = default;
template <typename T> T evaluate() {
return *reinterpret_cast<T *>(evaluateUntyped());
}
template <typename T, typename I> T *getTensor(I FeatureID) {
return reinterpret_cast<T *>(
getTensorUntyped(static_cast<size_t>(FeatureID)));
}
template <typename T, typename I> const T *getTensor(I FeatureID) const {
return reinterpret_cast<const T *>(
getTensorUntyped(static_cast<size_t>(FeatureID)));
}
void *getTensorUntyped(size_t Index) { return InputBuffers[Index]; }
const void *getTensorUntyped(size_t Index) const {
return (const_cast<MLModelRunner *>(this))->getTensorUntyped(Index);
}
enum class Kind : int { Unknown, Release, Development, NoOp, Interactive };
Kind getKind() const { return Type; }
virtual void switchContext(StringRef Name) {}
protected:
MLModelRunner(LLVMContext &Ctx, Kind Type, size_t NrInputs)
: Ctx(Ctx), Type(Type), InputBuffers(NrInputs) {
assert(Type != Kind::Unknown);
}
virtual void *evaluateUntyped() = 0;
void setUpBufferForTensor(size_t Index, const TensorSpec &Spec,
void *Buffer) {
if (!Buffer) {
OwnedBuffers.emplace_back(Spec.getTotalTensorBufferSize());
Buffer = OwnedBuffers.back().data();
}
InputBuffers[Index] = Buffer;
}
LLVMContext &Ctx;
const Kind Type;
private:
std::vector<void *> InputBuffers;
std::vector<std::vector<char *>> OwnedBuffers;
};
} // namespace llvm
#endif // LLVM_ANALYSIS_MLMODELRUNNER_H
#ifdef __GNUC__
#pragma GCC diagnostic pop
#endif
|
