检索结果-内蒙古大学图书馆

ACM Conference on Special Interest Group on Data Communication (SIGCOMM)

作者： Gao, Kai Gu, Chen Xiang, Qiao Yang, Yang Richard Bi, Jun Tsinghua Univ Beijing Peoples R China Tongji Univ Shanghai Peoples R China Yale Univ New Haven CT 06520 USA

ISBN: (纸本)9781450341936

Handling state dependencies is a major challenge in modern SDN programming, but existing frameworks do not provide sufficient abstractions nor tools to address this challenge. In this paper, we propose a novel, high-level programming abstraction and implement the Function Automation SysTem (FAST). With the two key features, i.e., automated state dependency tracking and efficient re-execution scheduling, we demonstrate that FAST substantially simplifies state-dependent SDN programming and boosts the performance.

关键词： SDN programming abstraction State dependency

来源：评论

学校读者我要写书评

暂无评论

QCCP: a taskflow programming model for emerging computing scenario

引用

EPJ QUANTUM TECHNOLOGY 2025年第1期12卷 23-23页

作者： Du, Qiming Xu, Jinchen Zhu, Yu Lian, Hang Xiong, Qibing Zheng, Danyang Liu, Yi Tu, Zheng Shan, Zheng Informat Engn Univ 62 Sci Ave Zhengzhou 450000 Henan Peoples R China

As the demand for computing power continues to rise, it is difficult for a single type of computing device or architecture to satisfy the current situation. Diversity and heterogeneity are becoming more and more popular. Seamlessly integrating the realms of high performance computing and quantum computing, and harnessing their collective potential, has emerged as a consensus approach to effectively address the pressing need for increased computing power. In the emerging computing scenario, various different types of computing devices have super-heterogeneous characteristics, and there are significant differences in computational principles, programming models, parallelism, etc. Effectively harnessing these disparate resources and achieving a unified programming paradigm have become urgent imperatives. To address the above problems, this paper introduces QCCP, a taskflow programming model that enables efficient collaborative computing between classical computers and quantum computers. QCCP establishes a unified programming abstraction, shields the super-heterogeneous characteristics of the underlying network and hardware, and supports flexible scheduling for different computational backends. The experimental results indicate that QCCP can support the processing of hybrid classical-quantum applications with diverse program structures. In particular, QCCP reveals its immense potential and superiority in tackling real-world challenges, specifically in the realm of quantum circuit cutting and reconstruction.

关键词： Super-heterogeneous programming abstraction programming paradigm Classical-quantum collaborative computation

来源：评论

学校读者我要写书评

暂无评论

Challenges and Opportunities to Enable Large-Scale Computing via Heterogeneous Chiplets 24

Challenges and Opportunities to Enable Large-Scale Computing...

引用

29th Asia and South Pacific Design Automation Conference (ASP-DAC)

作者： Yang, Zhuoping Ji, Shixin Chen, Xingzhen Zhuang, Jinming Zhang, Weifeng Jani, Dharmesh Zhou, Peipei Univ Pittsburgh Pittsburgh PA USA Lightelligence Boston MA USA Meta Menlo Pk CA USA

ISBN: (纸本)9798350393545

Fast-evolving artificial intelligence (AI) algorithms such as large language models have been driving the ever-increasing computing demands in today's data centers. Heterogeneous computing with domain-specific architectures (DSAs) brings many opportunities when scaling up and scaling out the computing system. In particular, heterogeneous chiplet architecture is favored to keep scaling up and scaling out the system as well as to reduce the design complexity and the cost stemming from the traditional monolithic chip design. However, how to interconnect computing resources and orchestrate heterogeneous chiplets is the key to success. In this paper, we first discuss the diversity and evolving demands of different AI workloads. We discuss how chiplet brings better cost efficiency and shorter time to market. Then we discuss the challenges in establishing chiplet interface standards, packaging, and security issues. We further discuss the software programming challenges in chiplet systems.

关键词： Chiplet interconnect advanced packaging security programming abstraction heterogeneous computing large language model (LLM) generative AI

来源：评论

学校读者我要写书评

暂无评论

ThrustHetero: A Framework to Simplify Heterogeneous Computing Platform programming using Design abstraction 19

ThrustHetero: A Framework to Simplify Heterogeneous Computin...

引用

12th Innovations in Software Engineering Conference (ISEC)

作者： George, Ajai V. Manoj, Sankar Sarkar, Santonu BITS Pilani KK Birla Goa Campus Sancoale Goa India

ISBN: (纸本)9781450362153

Heterogeneous compute architectures like Multi-Core CPUs, CUDA GPUs, and Intel Xeon Phis have become prevalent over the years. While heterogeneity makes architecture specific features available to the programmer, it also makes application development difficult, as one needs to plan for optimal usage of architectural features, suitable partitioning of the workload, communication and data transfer among the participating devices. A suitable design abstraction that hides such variabilities of the underlying devices and at the same time exploits their computing capabilities, can improve developer productivity. In this work, we present "ThrustHetero", a lightweight framework based on NVIDIA's Thrust, that provides an abstraction over several devices such as GPUs, Xeon Phis and multicore, yet allows developers to easily leverage the full compute capability of these devices. We also demonstrate a novel method for workload distribution in two stages - micro-benchmarking during framework installations to find good proportions and then using this information during application execution. We consider four classes of applications based on how they would perform on various computing architectures on the basis of the amount of branching present in the application. We show that the framework produces a good workload distribution proportions for each class of application and also show that the framework is scalable and portable. Further, we compare the performance and ease of development when using the framework with the native versions of various benchmarks and obtain favorable results.

关键词： programming abstraction Design Simplicity High Performance Computing Thrust Heterogeneous Computing CUDA

来源：评论

学校读者我要写书评

暂无评论

The state of the art of macroprogramming in IoT: An update

引用

JOURNAL OF INTERNET SERVICES AND APPLICATIONS 2022年第1期13卷 54-65页

作者： Sene Jr, Iwens G. Santana, Thalia S. Bulcao-Neto, Renato F. Porter, Barry F. Univ Fed Goias Goiania Brazil Univ Lancaster Lancaster England

Macroprogramming's primary goal is to increase developers' productivity by providing high-level specifications of applications' behaviour at the system level. Macroprogramming may be a viable solution for developing complex IoT applications, such as those manipulating high data volume and heterogeneity. This paper updates a recent work identifying and analysing primary research on macroprogramming in IoT through a systematic literature mapping (SLM). We extended the search strategy scope by conducting an automatic search over five new databases and also performed the snowballing technique. As a result, besides the 38 studies group found in previous SLM, nine new papers were classified as relevant and rigorously analysed, totalising forty-seven studies. In comparison to previous work, results still point out the recurrence of abstractions in the network infrastructure, highlighting the use of frameworks in one-third of the applications and contributing with an overview of macroprogramming by researchers in different knowledge areas.

关键词： Internet of Things Wireless Sensor Network Systematic Mapping Adaptation programming abstraction

来源：评论

学校读者我要写书评

暂无评论

ClickINC: In-network Computing as a Service in Heterogeneous Programmable Data-center Networks 23

ClickINC: In-network Computing as a Service in Heterogeneous...

引用

ACM SIGCOMM Conference (SIGCOMM)

作者： Xu, Wenquan Zhang, Zijian Feng, Yong Song, Haoyu Chen, Zhikang Wu, Wenfei Liu, Guyue Zhang, Yinchao Liu, Shuxin Tian, Zerui Liu, Bin Tsinghua Univ Beijing Peoples R China Futurewei Santa Clara CA USA Peking Univ Beijing Peoples R China New York Univ Shanghai Shanghai Peoples R China

ISBN: (纸本)9798400702365

In-Network Computing (INC) has found many applications for performance boosts or cost reduction. However, given heterogeneous devices, diverse applications, and multi-path network typologies, it is cumbersome and error-prone for application developers to effectively utilize the available network resources and gain predictable benefits without impeding normal network functions. Previous work is oriented to network operators more than application developers. We develop ClickINC to streamline the INC programming and deployment using a unified and automated workflow. ClickINC provides INC developers a modular programming abstractions, without concerning to the states of the devices and the network topology. We describe the ClickINC framework, model, language, workflow, and corresponding algorithms. Experiments on both an emulator and a prototype system demonstrate its feasibility and benefits.

关键词： In-Network Computing Programmable networks programming abstraction Program compilation Program placement

来源：评论

学校读者我要写书评

暂无评论

Jupiter: a modern federated learning platform for regional medical care

引用

Science China(Information Sciences) 2021年第10期64卷 152-165页

作者： Ju XING Jiadong TIAN Zexun JIANG Jiali CHENG Hao YIN Department of Automation Tsinghua University School of Cyberspace Security Beijing University of Posts and Telecommunications Department of Computer Science and Technology Tsinghua University College of Engineering Northeastern University

With the emergence of AI technologies, intrinsic value of data is released and takes tremendous effects on numerous industries. In the context of regional medical care, data sharing and cooperating is in high demand, which can bring both financial and societal benefits. At present, however, medical data are locked inside medical facilities owing to legal risks and economic considerations. How to bring AI technologies into full play under this circumstance is a big challenge. In this paper, we propose Jupiter, an easy-to-use,secure, and high-performance platform for federated machine learning. Jupiter constructs a secure and highperformance aggregator cluster with SGX to efficiently aggregate the encrypted model parameters. Jupiter employs a stateful design to cooperate with medical facilities in regional medical systems with a fixed network connection. By providing an innovative programming abstraction, Jupiter makes model development more friendly to developers. The experiments show that with a low memory footprint, the throughput of a single node on an ordinary PC can reach 300 MB/s(with slice size fixed to 64 KB), and the aggregation primitive we built can process 11 k aggregations per second.

关键词： federated learning programming abstraction SGX high-performance

来源：评论

学校读者我要写书评

暂无评论

Automatic Generation of Network Function Accelerators Using Component-Based Synthesis

Automatic Generation of Network Function Accelerators Using ...

引用

Symposium on SDN Research (SOSR)

作者： Pereira, Francisco Matos, Goncalo Sadok, Hugo Kim, Daehyeok Martins, Ruben Sherry, Justine Ramos, Fernando M., V Pedrosa, Luis Univ Lisbon Inst Super Tecn INESC ID Lisbon Portugal Carnegie Mellon Univ Pittsburgh PA 15213 USA Microsoft Redmond WA USA

ISBN: (纸本)9781450398923

Designing networked systems that take best advantage of heterogeneous dataplanes - e.g., dividing packet processing across both a PISA switch and an x86 CPU - can improve performance, efficiency, and resource consumption. However, programming for multiple hardware targets remains challenging because developers must learn platform-specific languages and skills. While some 'write-once, run-anywhere' compilers exist, they are unable to consider a range of implementation options to tune the NF to meet performance objectives. In this short paper, we explore preliminary ideas towards a compiler that explores a large search space of different mappings of functionality to hardware. This exploration can be tuned for a programmer-specified objective, such as minimizing memory consumption or maximizing network throughput. Our initial prototype, SYNAPSE, is based on a methodology called component-based synthesis and supports deployments across x86 and Tofino platforms. Relative to a baseline compiler which only generates one deployment decision, SYNAPSE uncovers thousands of deployment options - including a deployment which reduces the amount of controller traffic by an order of magnitude, and another deployment which halves memory usage.

关键词： In-network compute Network function virtualization programming abstraction

来源：评论

学校读者我要写书评

暂无评论

Jupiter: A Modern Federated Learning Platform for Regional Medical Care

Jupiter: A Modern Federated Learning Platform for Regional M...

引用

IEEE International Conference on Joint Cloud Computing (JCC)

作者： Xing, Ju Jiang, Zexun Yin, Hao Tsinghua Univ Beijing Peoples R China

ISBN: (纸本)9781728169811

In this paper we propose Jupiter, an easy-to-use, secure and high-performance federated learning platform for regional medical care. Jupiter provides innovative programming abstractions to make data tunning more efficient as well as high-performance infrastructures to accelerate secure aggregations of parameters. Jupiter employs a stateful design with a bunch of optimizations and leverages popular techniques like SDN, DPDK and Intel SGX. The experiments show that with a low memory footprint, the throughput of single aggregator can reach 300MB/sec(with slice size fixed to 64KB), and the aggregation primitive we built can process 11k aggregations per second.

关键词： federated learning programming abstraction performance Intel SGX

来源：评论

学校读者我要写书评

暂无评论

A Software Stack for Composable Cloud Robotics System 20th

A Software Stack for Composable Cloud Robotics System

引用

20th International Conference on Algorithms and Architectures for Parallel Processing (ICA3PP)

作者： Xu, Yuan Zhang, Tianwei Wang, Sa Bao, Yungang Chinese Acad Sci State Key Lab Comp Architecture ICT Beijing Peoples R China Univ Chinese Acad Sci Beijing Peoples R China Nanyang Technol Univ Singapore Singapore

ISBN: (纸本)9783030602390;9783030602383

Modern cloud robotic applications face new challenges in managing today's highly distributed and heterogeneous environment. For example, the application programmers must make numerous systematical decisions between the local robot and the cloud server, such as computation deployment, data sharing and function integration. In this paper, we propose RobotCenter, a composable cloud robotics operating system for developing and deploying robotics applications. RobotCenter provides three key functionalities: runtime management, data management and programming abstraction. With these functionalities, RobotCenter enables application programmers to easily develop powerful and diverse robotics applications. Meanwhile, it can efficiently execute these applications with high performance and low energy consumption. We implement a prototype of the design above and use an example of AGV/UAV cooperative transport application to illustrate the feasibility of RobotCenter. In the experiment, we reduce the total energy consumption and mission completion time up to 41.2% and 51.5%, respectively.

关键词： Cloud robotics Runtime management Data management programming abstraction Composable system

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：