With current trends toward deeper pipelined, superscalar processors and the high frequency of branch instructions, accurate branch prediction becomes increasingly important. This paper introduces an innovative hybrid ...
详细信息
ISBN:
(纸本)1892512459
With current trends toward deeper pipelined, superscalar processors and the high frequency of branch instructions, accurate branch prediction becomes increasingly important. This paper introduces an innovative hybrid branch prediction method that applies a four-class dynamic classifier. It employs various prediction methods for branch instructions of different classes. The simulation results indicate that this new method provides an improvement of accuracy over the published branch prediction methods. In addition, the Four-class Dynamic Branch Predictor performs specifically well when hardware resources are limited.
distributed storage systems comprise a large number of commodity hardware distributed across several data centers. Even in the presence of failures (permanent failures) the system should provide reliable storage. Whil...
详细信息
ISBN:
(纸本)9780769543284
distributed storage systems comprise a large number of commodity hardware distributed across several data centers. Even in the presence of failures (permanent failures) the system should provide reliable storage. While replication has advantages because of its simplicity there exist coding techniques that provide adaptable reliability properties with an optimal redundancy ratio at the same time e.g. MDS (maximum distance separable) erasure codes. The coding and distribution scheme influences the prospective storage reliability. In this paper we present reliability models for erasure coding and replication techniques especially for their application in wide-area storage systems. Furthermore we utilize these models to quantify the reliability properties of concrete data storage scenarios.
On-Line Analytical processingtechniques are used for data analysis and decision support systems. The multidimensionality of the underlying data is well represented by multidimensional databases. For data mining in kn...
详细信息
ISBN:
(纸本)0818684038
On-Line Analytical processingtechniques are used for data analysis and decision support systems. The multidimensionality of the underlying data is well represented by multidimensional databases. For data mining in knowledge discovery, OLAP calculations can be effectively used. For these, high performance parallel systems are required to provide interactive analysis. Precomputed aggregate calculations in a Data Cube can provide efficient query processing for OLAP applications. In this article, we present parallel data cube construction on distributed-memory, parallel computers from a relational database. Data Cube is used for data mining of associations using Attribute Focusing. Results are presented for these on the IBM-SP2, which show that our algorithms and techniques are scalable to a large number of processors, providing a high performance platform for such applications.
With the advent in WAN of delay sensitive technical applications, such as remote control, signal propagation delay becomes a major problem. The extent of the problem is analysed by lower bounding the delay in relation...
详细信息
ISBN:
(纸本)1932415262
With the advent in WAN of delay sensitive technical applications, such as remote control, signal propagation delay becomes a major problem. The extent of the problem is analysed by lower bounding the delay in relation to different transmission media. Requirements for reliability and bandwidth are considered. The consequences of this bounding for communication network planning and provisioning are discussed in relation to mitigating the effects of signal propagation delay as a barrier to the penetration of control applications into WAN.
Large-scale workflows are becoming increasingly important in both the scientific research and business domains. Science and commerce have both experienced an explosion in the sheer amount of data that must be analyzed...
详细信息
ISBN:
(纸本)9781932415605
Large-scale workflows are becoming increasingly important in both the scientific research and business domains. Science and commerce have both experienced an explosion in the sheer amount of data that must be analyzed. An important tool for analyzing these huge data sets is a compute "cluster" of hundreds or thousands of machines. However, debugging and tuning clusters requires specialized tools. Current cluster performance tools are more oriented towards tightly coupled parallelapplications. We describe how the NetLogger Toolkit methodology is more appropriate for this class of cluster computing, and describe our new automatic workflow anomaly detection component. We also describe how this methodology is being used in the Nearby Supernova Factory (SNfactory) project at Lawrence Berkeley National Laboratory.
Cloud computing has transformed the means of computing in recent years with several benefits over traditional systems, like scalability and high availability. However, there are still some opportunities, especially in...
详细信息
ISBN:
(纸本)9781728116440
Cloud computing has transformed the means of computing in recent years with several benefits over traditional systems, like scalability and high availability. However, there are still some opportunities, especially in the area of resource provisioning and scaling [13]. Since workload may fluctuate a lot in certain environments, over-provisioning is a common practice to avoid abrupt Quality of Service (QoS) drops that may result in Service Level Agreement (SLA) violations, but at the price of an increase in provisioning costs and energy consumption. Workload prediction is one of the strategies by which efficiency and operational cost of a cloud can be improved [13]. Knowing demand in advance allows the previous allocation of sufficient resources to maintain QoS and avoid SLA violations [1]. This paper presents the advantages and disadvantages of three workload prediction techniques when applied in the context of cloud computing. Our preliminary results compare ARIMA, MLP, and GRU under different cloud configurations to help administrators choose the more appropriate and efficient predictive model for their specific problem.
processing and analyzing large volumes of data plays an increasingly important role in many domains of scientific research. We are developing a compiler that processes data intensive applications written in a dialect ...
详细信息
ISBN:
(纸本)0769513638
processing and analyzing large volumes of data plays an increasingly important role in many domains of scientific research. We are developing a compiler that processes data intensive applications written in a dialect of Java and compiles them for efficient execution on distributed memory parallel machines. In this paper, we focus on the problem of generating correct and efficient communication for data intensive applications. We present static analysis techniques for 1) extracting a global reduction function from a data parallel loop, and 2) determining if a subscript function is monotonic. We also present a runtime technique for reducing the volume of communication during the global reduction phase. We have experimented with two data intensive applications to evaluate the efficacy of our techniques. Our results show that 1) our techniques for extracting global reduction functions and establishing monotonicity of subscript functions can successfully handle these applications, 2) significant reduction in communication volume and execution times is achieved through our runtime analysis technique, 3) runtime communication analysis is critical for achieving speedups on parallel configurations.
Current increases in the logic density of silicon circuits have made feasible the integration of multiple parallel compression engines (along with their own dedicated memory) onto a single chip. This paper presents a ...
详细信息
ISBN:
(纸本)1892512416
Current increases in the logic density of silicon circuits have made feasible the integration of multiple parallel compression engines (along with their own dedicated memory) onto a single chip. This paper presents a range of alternative routing strategies for data compression, which are investigated in order to understand tradeoffs between compression, latency and throughput. The performance of the compressors is tested using a variety of realistic datasets. For parallel compression it is clear that careful consideration must be given to the routing of the input and output stream.
We have evaluated a number of techniques for obtaining distributed high performance arithmetic for large integers. Two main ideas are presented: a technique for handling carry propagation in parallel additions and a t...
详细信息
ISBN:
(纸本)0769516807
We have evaluated a number of techniques for obtaining distributed high performance arithmetic for large integers. Two main ideas are presented: a technique for handling carry propagation in parallel additions and a technique for distributing not only the processing but also the storage of very large integers onto a number of computers. These ideas have been compared to state-of-the-art arithmetic libraries. We have done performance evaluations on a Linux cluster with 32 computers and an SMP with eight processors. The performance of addition was improved by a factor 13, and that the method where the storage of an integer is distributed was superior to the approaches where only processing is distributed. The multiplication performance was improved by a factor of 7.
Pervasive Grid Computing Platforms include centralized computing nodes (e.g. parallel servers) as well as decentralized and mobile devices. Pervasive Grid applications include data-and computing-intensive components w...
详细信息
ISBN:
(纸本)9780769539393
Pervasive Grid Computing Platforms include centralized computing nodes (e.g. parallel servers) as well as decentralized and mobile devices. Pervasive Grid applications include data-and computing-intensive components which can be mapped also onto decentralized and mobile nodes. The effective and practical success of this mapping resides also in deriving proper configurations of applications which consider the limited memory capabilities of those resources. In this paper we target this issue by showing how we can study and configure the memory requirements of an Emergency Management application. We present our solutions by using the ASSISTANT programming model for Pervasive Grid applications.
暂无评论