检索结果-内蒙古大学图书馆

30th International Conference on Architectural Support for programming languages and Operating Systems-ASPLOS

作者： Wang, Yujie Zhu, Shenhan Fu, Fangcheng Miao, Xupeng Zhang, Jie Zhu, Juan Hong, Fan Li, Yong Bin Cui Peking Univ Beijing Peoples R China Purdue Univ W Lafayette IN USA Alibaba Grp Beijing Peoples R China

ISBN: (纸本)9798400710797

Recent foundation models are capable of handling multiple tasks and multiple data modalities with the unified base model structure and several specialized model components. However, efficient training of such multi-task (MT) multimodal (MM) models poses significant system challenges due to the sophisticated model architecture and the heterogeneous workloads of different tasks and modalities. In this paper, we propose Spindle, a brand new training system tailored for resource-efficient and high-performance training of MT MM models via wavefront scheduling. The key idea of Spindle is to decompose the model execution into waves and address the joint optimization problem sequentially, including both heterogeneity-aware workload parallelization and dependency-driven execution scheduling. We build our system and evaluate it on various MT MM models. Experiments demonstrate the superior performance and efficiency of Spindle, with speedup ratio up to 71% compared to state-of-the-art training systems.

关键词： Multi-Task Large models distributed Training Workload Heterogeneity

来源：评论

学校读者我要写书评

暂无评论

Evaluating HLS4ML For Converting a CNN Model Into High Level Synthesis 5

Evaluating HLS4ML For Converting a CNN Model Into High Level...

引用

5th International Conference on Advanced Research in computing, ICARC 2025

作者： Jariri, Noura Chaman, Mohammed Majdoubi, Rania Hadjoudja, Abdelkader Faculty of Science Ibn Tofail University Electronic Systems Information Processing Mechanics and Energy Laboratory Kenitra Morocco

ISBN: (纸本)9798331530983

Deep learning models, although high-performing, often require hardware acceleration to be effectively deployed on Field Programmable Gate Arrays (FPGAs). This paper investigates the use of the hls4ml framework to convert a Convolutional Neural Network (CNN) model into High Level Synthesis (HLS). hls4ml is a Python tool that translates neural networks into FPGA-compatible firmware for high-performance inference with reduced latency and power usage. It employs High-Level Synthesis (HLS) techniques to translate high-level programming languages like C++ or Python into hardware description languages, such as VHDL or Verilog. We evaluate the model's performance in terms of accuracy and demonstrate the effectiveness of converting a deep learning model, specifically a CNN, for hardware implementation. The results highlight the potential of hls4ml facilitating embedded artificial intelligence applications, offering an efficient and scalable solution for deploying deep learning models on resource-constrained platforms. © 2025 IEEE.

关键词： C++ (programming language)

来源：评论

学校读者我要写书评

暂无评论

Compiling distributed System models with PGo 2023

Compiling Distributed System Models with PGo

引用

28th ACM International Conference on Architectural Support for programming languages and Operating Systems (ASPLOS)

作者： Hackett, Finn Hosseini, Shayan Costa, Renato Do, Matthew Beschastnikh, Ivan Univ British Columbia Vancouver BC Canada

ISBN: (纸本)9781450399166

distributed systems are difficult to design and implement correctly. In response, both research and industry are exploring applications of formal methods to distributed systems. A key challenge in this domain is the missing link between the formal design of a system and its implementation. Today, practitioners bridge this link through manual effort. We present a language called Modular PlusCal (MPCal) that extends PlusCal by cleanly separating the model of a system from a model of its environment. We then present a compiler tool-chain called PGo that automatically translates MPCal models to TLA(+) for model checking, and that also compiles MPCal models to runnable Go code. PGo provides system designers with a new ability to model and check their designs, and then re-use their modeling efforts to mechanically extract runnable implementations of their designs. Our evaluation shows that the PGo approach works for complex models: we model check, compile, and evaluate the performance of MPCal systems based on Raft, CRDTs, and primary-backup. Compared to previous work, PGo requires less time to develop a checked model and derive a fully working implementation. With PGo we created a formally checked Raft model and its corresponding implementation in under 1 person-month, which is 3x less time than Ivy. Our evaluation shows that a PGo-based Raft KV store with three nodes has 41% higher throughput than a Raft KV store based on Ivy, the highest performing verified Raft-based KV store from related work. A PGo-based CRDT set has a latency within 2x of a CRDT set implementation from SoundCloud called Roshi.

关键词： Formal methods distributed systems Compilers PlusCal TLA(+)

来源：评论

学校读者我要写书评

暂无评论

programming distributed Collective Processes for Dynamic Ensembles and Collective Tasks 25th

Programming Distributed Collective Processes for Dynamic Ens...

引用

25th International Conference on Coordination models and Language (COORDINATION)

作者： Audrito, Giorgio Casadei, Roberto Damiani, Ferruccio Torta, Gianluca Viroli, Mirko Univ Torino Turin Italy Univ Bologna Cesena Italy

ISBN: (纸本)9783031353604;9783031353611

Recent trends like the Internet of Things (IoT) suggest a vision of dense and multi-scale deployments of computing devices in nearly all kinds of environments. A prominent engineering challenge revolves around programming the collective adaptive behaviour of such computational ecosystems. This requires abstractions able to capture concepts like ensembles (dynamic groups of cooperating devices) and collective tasks (joint activities carried out by ensembles). In this work, we consider collections of devices interacting with neighbours and that execute in nearly-synchronised sense-compute-interact rounds, where the computation is given by a single control program. To support programming whole computational collectives, we propose the abstraction of a distributed collective process (DCP), which can be used to define at once the ensemble formation logic and its collective task. We implement the abstraction in the eXchange Calculus (XC), a core language based on neighbouring values (maps from neighbours to values) where state management and interaction is handled through a single primitive, exchange. Then, we discuss the features of the abstraction, its suitability for different kinds of distributed computing applications, and provide a proof-of-concept implementation of a wave-like process propagation.

关键词： collective computing collective processes ensembles formation control

来源：评论

学校读者我要写书评

暂无评论

Etudes for Parallel Programmers 33

Etudes for Parallel Programmers

引用

33rd Euromicro International Conference on Parallel, distributed, and Network-Based Processing, PDP 2025

作者： Marzolla, Moreno Center for Inter-Department Industrial Research ICT Bologna Italy

ISBN: (数字)9798331524937

ISBN: (纸本)9798331524937

Mini-applications are widely used in parallel computing for testing and benchmarking purposes. However, many existing mini-applications are not suitable for teaching, since they require advanced knowledge of algebra, numerical analysis or physics to be fully understood, which might be beyond the reach of beginners. In this paper we describe a set of programming assignments, called parallel etudes, that have been used in the last years for teaching High Performance computing at the undergraduate level. These applications are self-contained, self-documenting, and short. They are drawn from more familiar domains such as 3D rendering, simulation, image processing and simple physics models, to be more accessible to students without a strong mathematical background. The mini-applications target shared-memory, distributed-memory and GPU programming. The analysis of the students' feedback and final grades provides indirect support for the effectiveness of the etudes. © 2025 IEEE.

关键词： Parallel programming

来源：评论

学校读者我要写书评

暂无评论

HPC master design: experience from Pisa 33

HPC master design: experience from Pisa

引用

33rd Euromicro International Conference on Parallel, distributed, and Network-Based Processing, PDP 2025

作者： Danelutto, Marco Univ. of Pisa Dept. of Computer Science Italy

ISBN: (纸本)9798331524937

HPC is a widely used term, often referred to the applications, architectures and programming models and tools targeting highly parallel machines such as those of the *** lists. Recent advances in computing hardware resources require application of HPC techniques when using much smaller machines. Indeed, proper parallel programming tools and applications are needed also to exploit parallel hardware resources in personal computers (laptops, desktops, servers). This paper outlines key challenges in designing master's degree programs in HPC and shares lessons learned from various experiences in developing and implementing such programs in Italy and Europe. © 2025 IEEE.

关键词： Parallel programming

来源：评论

学校读者我要写书评

暂无评论

Maude Specification of Nets-Within-Nets: A Formal Model of Adaptable distributed Systems 23

Maude Specification of Nets-Within-Nets: A Formal Model of A...

引用

38th Annual ACM Symposium on Applied computing (ACM SAC)

作者： Capra, Lorenzo Koehler-Bussmeier, Michael Univ Milan Dipartimento Informat Milan Italy Univ Appl Sci Hamburg Germany

ISBN: (纸本)9781450395175

Adaptable distributed systems gain growing attention to raising service quality at low costs. Managing adaptation calls for suitable models through the entire life cycle. A challenging point is system structural reconfiguration, which has led to specialized formal models. We aim to bridge the gap with daily programming languages by defining a Maude abstract machine for "Nets-within-Nets".

关键词： Adaptive Systems Petri Nets Maude Nets-within-Nets

来源：评论

学校读者我要写书评

暂无评论

Using a Large Language Model as a Building Block to Generate UsableValidation and Verification Suite for OpenMP 25

Using a Large Language Model as a Building Block to Generate...

引用

8th International Conference on High Performance computing in Asia-Pacific Region, HPC Asia 2025

作者： Pophale, Swaroop Elwasif, Wael Bernholdt, David E. Oak Ridge National Laboratory Oak Ridge United States

ISBN: (纸本)9798400713354

In the HPC area, both hardware and software move quickly. Often new hardware is developed and deployed, the corresponding software stack, including compilers and other tools, are under active development while leading edge software developers are working to port and tune their applications, all at the same time. While the software ecosystem is in flux, one of the key challenges for users is obtaining insight into the state of implementation of key features in the programming languages and models their applications are using - whether they have been implemented, and whether the implementation conforms to the specification, especially for newly implemented features (less tested by widespread use). OpenMP is one of the most prominent shared memory programming models used for on-node programming in HPC. With the shift towards accelerators (such as GPUs and FPGAs) and heterogeneous programming OpenMP features are getting more complex. It is natural to ask whether generative AI approaches, and large language models (LLMs) in particular, can help in producing validation and verification test suites to allow users better and faster insights into the availability and correctness of OpenMP features of interest. In this work, we explore the use of ChatGPT-4 to generate a suite of tests for OpenMP features. We have chosen a set of directives and clauses, a total of 78 combinations, which first appeared in OpenMP 3.0 (released in May 2008) but are also relevant for accelerators. We prompted ChatGPT to generate tests in the C and Fortran languages, for both host (CPU) and device (accelerator). On the Summit super-computer using the GNU implementation, we found that, of the 78 generated tests 67 C tests and 43 Fortran tests compiled successfully and fewer than those executed to completion. On further analysis we show that not all generated tests are valid. We document the process, results, and provide detailed analysis regarding the quality of tests generated. With the aim of prov

关键词： FORTRAN (programming language)

来源：评论

学校读者我要写书评

暂无评论

Reward Augmentation in Reinforcement Learning for Testing distributed Systems

引用

proceedings OF THE ACM ON programming languages-PACMPL 2024年第OOPSLA2期8卷 1928-1954页

作者： Borgarelli, Andrea Enea, Constantin Majumdar, Rupak Nagendra, Srinidhi MPI SWS Kaiserslautern Germany Inst Polytech Paris LIX Ecole Polytech CNRS Palaiseau France Univ Paris Cite IRIF CNRS Paris France Chennai Math Inst Chennai India

Bugs in popular distributed protocol implementations have been the source of many downtimes in popular internet services. We describe a randomized testing approach for distributed protocol implementations based on reinforcement learning. Since the natural reward structure is very sparse, the key to successful exploration in reinforcement learning is reward augmentation. We show two different techniques that build on one another. First, we provide a decaying exploration bonus based on the discovery of new states-the reward decays as the same state is visited multiple times. The exploration bonus captures the intuition from coverage-guided fuzzing of prioritizing new coverage points;in contrast to other schemes, we show that taking the maximum of the bonus and the Q-value leads to more effective exploration. Second, we provide waypoints to the algorithm as a sequence of predicates that capture interesting semantic scenarios. Waypoints exploit designer insight about the protocol and guide the exploration to "interesting" parts of the state space. Our reward structure ensures that new episodes can reliably get to deep interesting states even without execution caching. We have implemented our algorithm in Go. Our evaluation on three large benchmarks (RedisRaft, Etcd, and RSL) shows that our algorithm can significantly outperform baseline approaches in terms of coverage and bug finding.

关键词： CCS Concepts Software and its engineering Software testing and debugging Theory of computation Reinforcement learning computing methodologies distributed algorithms

来源：评论

学校读者我要写书评

暂无评论

AquaLang: A Dataflow programming Language 18

AquaLang: A Dataflow Programming Language

引用

18th International Conference on distributed and Event-Based Systems (DEBS)

作者： Segeljakt, Klas Haridi, Seif Carbone, Paris KTH Royal Inst Technol Stockholm Sweden RISE Res Inst Sweden Stockholm Sweden

ISBN: (纸本)9798400704437

Dataflow systems are widely used today for building and running continuous data-intensive applications. However, the unavoidable semantic gap between the host languages of dataflow system libraries and the dataflow model creates programmability limitations that hinder performance, safety, and ease of use. We propose AquaLang, a new language designed for dataflow systems. Programs in AquaLang blend strongly typed relational and functional syntax and are verified using an effect system that prevents undefined behaviour that can occur when introducing user-defined logic that violates dataflow semantics. Unverified external code is also feasible in AquaLang through the novel use of sandboxing. Furthermore, on top of standard dataflow optimisations employed by current systems, AquaLang's ability to analyze algebraic properties of user-defined functions further unlocks the potential of deeper dataflow program re-writing. In our evaluation, we measure up to one order of magnitude speedup for Nexmark queries against hand-written Flink programs attributed to pushdown and window incrementalisation techniques.

关键词： programming languages Dataflow Systems Data Streams

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：