C plus plus Code Generation for Fast Inference of Deep Learning Models in ROOT/TMVA

被引：0

作者：

An, Sitong ^{[1
,2
]}

Moneta, Lorenzo ^{[1
]}

Sengupta, Sanjiban ^{[3
]}

Hamdan, Ahmat ^{[4
]}

Sossai, Federico ^{[5
]}

Saxena, Aaradhya ^{[6
]}

机构：

[1] CERN, Esplanade Particules 1, CH-1211 Geneva, Switzerland

[2] Carnegie Mellon Univ, 5000 Forbes Ave, Pittsburgh, PA USA

[3] IIT Bhubaneswar, Bhubaneswar 751029, Odisha, India

[4] ISSEA, Rue Pasteur, Yaounde, Cameroon

[5] Univ Padua, Via VIII Febbraio,2, I-35122 Padua, PD, Italy

[6] IIT Roorkee, Roorkee 247667, Uttarakhand, India

来源：

20TH INTERNATIONAL WORKSHOP ON ADVANCED COMPUTING AND ANALYSIS TECHNIQUES IN PHYSICS RESEARCH | 2023年 / 2438卷

关键词：

D O I：

10.1088/1742-6596/2438/1/012013

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

We report the latest development in ROOT/TMVA, a new tool that takes trained ONNX deep learning models and emits C++ code that can be easily included and invoked for fast inference of the model, with minimal dependency. An introduction to SOFIE (System for Optimized Fast Inference code Emit) is presented, with examples of interface and generated code. We discuss the latest expanded support of a variety of neural network operators, including convolutional and recurrent layers, as well as the integration with RDataFrame. We demonstrate the latest performance of this framework with a set of benchmarks.

引用

页数：5

共 50 条

[1] Fast Inference for Machine Learning in ROOT/TMVA
Albertsson, Kim
An, Sitong
Moneta, Lorenzo
Wunsch, Stefan
Zampieri, Luca
[J]. 24TH INTERNATIONAL CONFERENCE ON COMPUTING IN HIGH ENERGY AND NUCLEAR PHYSICS (CHEP 2019), 2020, 245
[2] C plus plus EDSL for parallel code generation
Berenyi, Daniel
[J]. PROCEEDINGS 2015 8TH ROMANIA TIER 2 FEDERATION GRID, CLOUD & HIGH PERFORMANCE COMPUTING IN SCIENCE (RO-LCG), 2015,
[3] Fast analysis of source code in C and C plus
Savitskii, V. O.
Sidorov, D. V.
[J]. PROGRAMMING AND COMPUTER SOFTWARE, 2013, 39 (01) : 49 - 55
[4] A Code Generation Toolkit for C plus plus Web Services Development
Ji, Xiangye
Han, Jun
Zhao, Yongwang
[J]. 2013 THIRD INTERNATIONAL CONFERENCE ON INTELLIGENT SYSTEM DESIGN AND ENGINEERING APPLICATIONS (ISDEA), 2013, : 17 - 21
[5] Generation of C plus plus Code from Isabelle/HOL Specification
Jiang, Dongchen
Xu, Bo
[J]. INTERNATIONAL JOURNAL OF SOFTWARE ENGINEERING AND KNOWLEDGE ENGINEERING, 2022, 32 (07) : 1043 - 1069
[6] Detection of Memory Leaks in C/C plus plus Code via Machine Learning
Andrzejak, Artur
Eichler, Felix
Ghanavati, Mohammadreza
[J]. 2017 IEEE 28TH INTERNATIONAL SYMPOSIUM ON SOFTWARE RELIABILITY ENGINEERING WORKSHOPS (ISSREW 2017), 2017, : 252 - 258
[7] Vulnerability Detection in C/C plus plus Source Code With Graph Representation Learning
Wu, Yuelong
Lu, Jintian
Zhang, Yunyi
Jin, Shuyuan
[J]. 2021 IEEE 11TH ANNUAL COMPUTING AND COMMUNICATION WORKSHOP AND CONFERENCE (CCWC), 2021, : 1519 - 1524
[8] Bridging Excel and C/C plus plus Code
Punuru, Janardhana R.
Knopf, F. Carl
[J]. COMPUTER APPLICATIONS IN ENGINEERING EDUCATION, 2008, 16 (04) : 289 - 304
[9] Generation of Reversible C plus plus Code for Optimistic Parallel Discrete Event Simulation
Schordan, Markus
Oppelstrup, Tomas
Jefferson, David
Barnes, Peter D., Jr.
[J]. NEW GENERATION COMPUTING, 2018, 36 (03) : 257 - 280
[10] Analysis and Code Model Extraction for C/C plus plus Source Code
Wagner, Christian
Margaria, Tiziana
Pagendarm, Hans-Georg
[J]. 2009 14TH IEEE INTERNATIONAL CONFERENCE ON ENGINEERING OF COMPLEX COMPUTER SYSTEMS (ICECCS), 2009, : 110 - +

← 1 2 3 4 5 →