Topic
Spark (mathematics)
About: Spark (mathematics) is a research topic. Over the lifetime, 7304 publications have been published within this topic receiving 63322 citations.
Papers published on a yearly basis
Papers
More filters
Proceedings Article•
20 Jun 2016TL;DR: This paper conducts an in-depth analysis of challenges at single-thread, single-node multi- thread, and multi-node levels, and proposes solutions including batch processing and the FPGA-as-a-Service framework to address them.
Abstract: FPGA-enabled datacenters have shown great potential for providing performance and energy efficiency improvement. In this paper we aim to answer one key question: how can we efficiently integrate FPGAs into state-of-the-art big-data computing frameworks like Apache Spark? To provide a generalized methodology and insights for efficient integration, we conduct an in-depth analysis of challenges at single-thread, single-node multi-thread, and multi-node levels, and propose solutions including batch processing and the FPGA-as-a-Service framework to address them. With a step-by-step case study for the next-generation DNA sequencing application, we demonstrate how a straightforward integration with 1,000x slowdown can be tuned into an efficient integration with 2.6x overall system speedup and 2.4x energy efficiency improvement.
44 citations
01 Sep 1981
44 citations
01 Jan 1977
TL;DR: In this article, the effects of gap width, electrode configuration, mixture strength, spark duration, and energy distribution between the two components on the minimum ignition energy were investigated, using a quiescent propane-air mixture.
Abstract: To determine the optimum ignition condition for sparks consisting of a capacitance spark followed by a dc- (glow) or ac-discharge (1 MHz), the effects of gap width, electrode configuration, mixture strength, spark duration, and energy distribution between the two components on the minimum ignition energy were investigated, using a quiescent propane-air mixture. The condition in question is conveniently characterized by the optimum spark duration for which the minimum ignition energy is lowest and the corresponding energy value. For a dc-discharge spark, the well-defined optimum spark duration varies from about 50 to 300 μ sec and the minimum ignition energy for spark durations larger than the optimum increases in different modes, depending on the mixture strength and the quenching effect of spark electrodes. For an ac-discharge spark, the optimum condition for ignition is much the same as for a dc-discharge spark, but the minimum ignition energy and the spark duration are always proportional to each other above the optimum, and therefore the optimum spark duration is easily obtained up to about 5 msec. Flash-schlieren photographic observations of the initial behavior of the spark kernel confirmed that such differences in the mode of minimum ignition energy are related to electrostatic attraction by the negative electrode.
44 citations
TL;DR: The plan is to develop computational engine efficiency and improve rain prediction models successfully and effectively using big data and Hadoop learning, and the planned high timeliness and accuracy of real-time hurricane forecast with rain, can solve the problem.
44 citations