Event traces are helpful in understanding the performance behavior of parallel applications since they allow the indepth analysis of communication and synchronization patterns. However, the absence of synchronized clo...
详细信息
Event traces are helpful in understanding the performance behavior of parallel applications since they allow the in-depth analysis of communication and synchronization patterns. However, the absence of synchronized cl...
详细信息
Event traces are helpful in understanding the performance behavior of parallel applications since they allow the in-depth analysis of communication and synchronization patterns. However, the absence of synchronized clocks on most cluster systems may render the analysis ineffective because inaccurate relative event timings may misrepresent the logical event order and lead to errors when quantifying the impact of certain behaviors or confuse the users of time-line visualization tools by showing messages flowing backward in time. In our earlier work, we have developed a scalable algorithm that eliminates inconsistent inter-process timings postmortem in traces of pure MPI applications. Since hybrid programming, the combination of MPI and OpenMP in a single application, is becoming more popular on clusters in response to rising numbers of cores per chip and widening shared-memory nodes, we present an extended version of the algorithm that in addition to message-passing event semantics also preserves and restores shared-memory event semantics.
It is already established that going forward, the roughly 2x/2yr performance improvements delivered over the last two decades will primarily come through parallelism rather than increasing clock frequencies due to ass...
详细信息
It is already established that going forward, the roughly 2x/2yr performance improvements delivered over the last two decades will primarily come through parallelism rather than increasing clock frequencies due to associated power challenges. Provided software and tools continue to scale well with core and thread count, large core counts bring serious challenges both in the memory hierarchy and interconnect bandwidth both on-die, within the package, and off package. Simulations on anticipated future workloads help isolate where specific bottlenecks are likely to occur. New technologies both in die stacking and package- to-package interconnects will be required. These solutions will bring dramatic changes in the physical layer that may well break backward compatibility. Furthermore, these potential approaches are segment specific and involve complex tradeoffs of performance, cost, and power. This presentation will explore several approaches highlighting potential solutions and bandwidth requirements driven by likely future applications.
An optimal strategy involving the corresponding model and approach to the generators start-up during power system restoration is presented. The aim of the method is to maximize the total power generation capability (M...
An optimal strategy involving the corresponding model and approach to the generators start-up during power system restoration is presented. The aim of the method is to maximize the total power generation capability (MWh) over an optimization time period whilst considering the corresponding constraints. The Data Envelopment Analysis (DEA) method is employed to get an effective assessment towards each generator (to be cranked) by the newly introduced indices derived from the objective function together with its constraints. As a result, the relative efficiency of each generator to be started can be evaluated comprehensively and objectively. On the other hand, the priority for each generator start-up can be determined as well. The proposed method, to some extent, can make the trade off between the simulation precision and the computing efforts much better. Case study based on a 12-generator modified real-sized system illustrate that the proposed strategy could provide more comprehensive and objective decision reference.
For understanding the performance differences caused by different computer architectures and optimization technologies, the paper characterizes performance of SPEC CPU2006 benchmarks both on Intel and AMD platform. Us...
详细信息
For understanding the performance differences caused by different computer architectures and optimization technologies, the paper characterizes performance of SPEC CPU2006 benchmarks both on Intel and AMD platform. Using the performance events collected by Performance Monitor Unit, we compare their performance differences and analyze the causes from the features of architectures and the optimization technologies. Our results and analysis help the programmers better understand the memory performance and branch prediction performance which are caused by architectures and guide them in the optimization. The analysis also help the processor architects better balance among the key architecture factors such as memory disambiguation and hardware prefetch when doing architecture design decision.
This paper proposes a notion, the 'ambit' of an action, that allows the degree of distribution of an action in a multiagent system to be quantified without regard to its functionality. It demonstrates the use ...
详细信息
ISBN:
(纸本)9780769528564
This paper proposes a notion, the 'ambit' of an action, that allows the degree of distribution of an action in a multiagent system to be quantified without regard to its functionality. It demonstrates the use of that notion in the design, analysis and implementation of dynamically-reconfigurable multi-agent systems. It distinguishes between the extensional (or system) view and intensional (or agent-based) view of such a system and shows how, using the notion of ambit, the step-wise derivation paradigm of Formal Methods can be used to derive the latter from the former In closing it addresses the manner in which these ideas inform studies in the ethics of systems of artificial agents.
This paper proposes a , the "ambit' of an action, that allows the degree of distribution of an action in a multiagent system to be quantified without regard to its functionality. It demonstrates the use of th...
详细信息
This paper proposes a , the "ambit' of an action, that allows the degree of distribution of an action in a multiagent system to be quantified without regard to its functionality. It demonstrates the use of that notion in the design, analysis and implementation of dynamically-reconfigurable multi-agent systems. It distinguishes between the extensional (or system) view and intensional (or agent-based) view of such a system and shows how, using the notion of ambit, the step-wise derivation paradigm of formal methods can be used to derive the latter from the former. In closing it addresses the manner in which these ideas inform studies in the ethics of systems of artificial agents.
A new field in distributed computing, called Ambient Intelligence, has emerged as a consequence of the increasing availability of wireless devices and the mobile networks they induce. Developing software for mobile ne...
详细信息
暂无评论