Active Messages: A Mechanism for Integrated Communication and Computation

Eicken, Thorsten von; Culler, David; Goldstein, Seth Copen; Schauser, Klaus E.

doi:10.1109/isca.1992.753322

Cited by 581 publications

(386 citation statements)

References 10 publications

Supporting

Mentioning

381

Contrasting

Unclassified

Order By: Relevance

“…However, the user is still faced with the burden of low-level programming and optimization decisions. There has been some work done on developing programming abstractions [15,19,24,25,34,41] for sensor networks; however, these abstractions provide only minimal programming support. Finally, authors in [4] propose an interesting novel approach of expressing computations as "task graphs," but the approach has limited applicability.…”

Section: A Related Workmentioning

confidence: 99%

Deductive Framework for Programming Sensor Networks

Gupta

Zhu

2009

2009 IEEE 25th International Conference on Data Engineering

View full text Add to dashboard Cite

Abstract-Developing powerful paradigms for programming sensor networks is critical to realize the full potential of sensor networks as collaborative data processing engines. In this article, we motivate and develop a deductive framework for programming sensor networks, extending the prior vision of viewing sensor network as a distributed database. The deductive programming approach is declarative, very expressive, and amenable to automatic optimizations. Such a framework allows users to program sensor network applications at a high-level without worrying about the low-level tedious details. Our system translates a given deductive program to efficient distributed code that runs on individual nodes. To facilitate the above translation, we develop techniques for distributed and asynchronous evaluation of deductive programs in sensor networks. Our techniques generalize to recursive programs without negations, arbitrary nonrecursive programs with negations, and in general to arbitrary "locally non-recursive" programs with function symbols. We present performance results on TOSSIM, a network simulator, and a small network testbed.

show abstract

Section: A Related Workmentioning

confidence: 99%

Deductive Framework for Programming Sensor Networks

Gupta

Zhu

2009

2009 IEEE 25th International Conference on Data Engineering

View full text Add to dashboard Cite

show abstract

“…In the case of a remote fork, the stub handler uses indirect active messages [24] to return data and control to the parent's message handler, which in turn has responsibility for integrating the data into the parent frame and indicating to the parent that its child has returned.…”

Section: Stacklet Stubsmentioning

confidence: 99%

Enabling Primitives for Compiling Parallel Languages

Goldstein

Schauser

Culler

1996

Languages, Compilers and Run-Time Systems for Scalable Computers

View full text Add to dashboard Cite

This paper presents three novel language implementation primitives-lazy threads, stacklets, and synchronizers-and shows how they combine to provide a parallel call at nearly the efficiency of a sequential call. The central idea is to transform parallel calls into parallel-ready sequential calls. Excess parallelism degrades into sequential calls with the attendant efficient stack management and direct transfer of control and data, unless a call truly needs to execute in parallel, in which case it gets its own thread of control. We show how these techniques can be applied to distribute work efficiently on multiprocessors.

show abstract

“…In order to circumvent these problems, a group of user-level communication protocols has been proposed. Examples of user-level communication protocol are U-Net [1], Fast Message [2], Active Message [3] and GAMMA [4]. The Virtual Interface Architecture (VIA) [5] has emerged to standardize these different user-level communication protocols.…”

Section: Introductionmentioning

confidence: 99%

Implementation and Performance Evaluation of M-VIA on AceNIC Gigabit Ethernet Card

Yoon

Chung

Liu

et al. 2003

Euro-Par 2003 Parallel Processing

View full text Add to dashboard Cite

Abstract. This paper describes the implementation and performance of M-VIA on the AceNIC Gigabit Ethernet card. The AceNIC adapter has several notable hardware features for high-speed communication, such as jumbo frames and interrupt coalescing. The M-VIA performance characteristics were measured and evaluated based on these hardware features. Our results show that latency and bandwidth improvement can be obtained when the M-VIA data segmentation size is properly adjusted to utilize the AceNIC's jumbo frame feature. The M-VIA data segmentation size of 4,096 bytes with MTU size of 4,138 bytes showed the best performance. However, larger MTU sizes did not necessarily result in better performance due to extra segmentation and DMA setup overhead. In addition, the cost of M-VIA interrupt handling can be reduced with AceNIC's hardware interrupt coalescing. When the parameters for the hardware interrupt coalescing were properly adjusted, the latency of interrupt handling was reduced by up to 170 µs.

show abstract

Active Messages: A Mechanism for Integrated Communication and Computation

Cited by 581 publications

References 10 publications

Deductive Framework for Programming Sensor Networks

Deductive Framework for Programming Sensor Networks

Enabling Primitives for Compiling Parallel Languages

Implementation and Performance Evaluation of M-VIA on AceNIC Gigabit Ethernet Card

Contact Info

Product

Resources

About