Multi and many-core processors have emerged as the dominant solution for processing in the whole range of computer system, from small devices to large-scale installations. Chip multi-processors, which are homogeneous,...
详细信息
ISBN:
(纸本)9781479942930
Multi and many-core processors have emerged as the dominant solution for processing in the whole range of computer system, from small devices to large-scale installations. Chip multi-processors, which are homogeneous, multi and many-core processors, offer an unprecedented amount of on-chip, shared resources and brings a unique set of challenges. Given the importance of the Last-Level Cache management techniques to achieve near-perfect isolation, we survey the state of the art and propose research directions to address the most pressing issues in modern computer systems. To better understand the various research directions in the field, we propose a classification of the presented techniques. Finally, we discuss possible research directions.
parallel file systems provide high-performance disk access by transparently striping data across multiple disks and I/O nodes. Similar to peer-to-peer systems (e.g. Freenet, Oceanstore, Chord/ CFS, Past), parallel fil...
详细信息
ISBN:
(纸本)1892512459
parallel file systems provide high-performance disk access by transparently striping data across multiple disks and I/O nodes. Similar to peer-to-peer systems (e.g. Freenet, Oceanstore, Chord/ CFS, Past), parallel file systems for clusters are employed on networked computers whose nodes are not guaranteed to be always available, due to node failures or network failure. However, different from peer-to-peer systems, cluster file systems like PVFS do not handle these failures very well. In this work, we explore how cluster file system can utilize certain peer-to-peer techniques that can handle failing nodes and thus allow for high data availability.
Are there computations whose characteristics are akin to certain unique phenomena that are witnessed in different domains of science? We are particularly interested in systems whose parameters are altered unpredictabl...
详细信息
ISBN:
(纸本)1892512416
Are there computations whose characteristics are akin to certain unique phenomena that are witnessed in different domains of science? We are particularly interested in systems whose parameters are altered unpredictably whenever one of these parameters is measured or modified. For example, is there a computational environment in which the uncertainty principle of digital signal processing and Le Chatelier's principle of chemical systems in equilibrium are manifested simultaneously? A positive answer might uncover computations that are inherently parallel in the strong sense, meaning that they are efficiently executed in parallel, but impossible to carry out sequentially.
It is known that the vector operation such as the sum-product computation is appeared as the fundamental calculation in many fields related to the signal processing and its fast computation is an important thing. One ...
详细信息
ISBN:
(纸本)1892512459
It is known that the vector operation such as the sum-product computation is appeared as the fundamental calculation in many fields related to the signal processing and its fast computation is an important thing. One of methods for the high-performance of the vector operation is the parallel computing with the multiprocessor. In our laboratory, we have developed the Loop Structured Computer(LSC) which is a data-flow multiprocessor system. The data-flow procedure provides opportunities for parallel and pipelined execution. at the level of indevidual instructions since it is constrained only by the data dependences among the instructions. In practice, however, the parallelism is obstructed by the architecture of the target machine. In this work, we measure the computation performance of the vector operation by using simulation with varying some factors arised from the architecture of LSC. Consequently we find the efficient combination of factors in the implementation of the vector operation on LSC.
This paper describes the architecture and implementation of Libra, a library for implementing efficient reliable distributedapplications. Libra is designed to provide fault-tolerance transparency and a simple, easy t...
详细信息
ISBN:
(纸本)0780335295
This paper describes the architecture and implementation of Libra, a library for implementing efficient reliable distributedapplications. Libra is designed to provide fault-tolerance transparency and a simple, easy to use high-level message passing interface so that the development of reliable distributedapplications can be significantly simplified Fault tolerance is based on distributed consistent checkpointing and rollback-recovery integrated with a user-level network communication protocol. By employing novel mechanisms, Libra minimises communication overhead for taking a consistent distributed checkpoint and catching messages in transit. With efficient implementation techniques, the prototype of Libra has been implemented on a network of Sun workstations, and supports reliable distributed computing at low run-time cost. The simplicity and efficiency of Libra make ita promising approach to construct reliable distributedapplications.
Telecommunication companies often like to perform operations such as compression, encryption, filtering, or exhaustive monitoring of data packets that pass through their networks. These operations can be very computat...
详细信息
ISBN:
(纸本)1932415262
Telecommunication companies often like to perform operations such as compression, encryption, filtering, or exhaustive monitoring of data packets that pass through their networks. These operations can be very computationally expensive and this problem is exacerbated by the fact that these operations must be done not only in real-time, but also without introducing any noticeable delay. The paper investigates the feasibility of using a processor-cluster in conjunction with load balancing techniques to distribute the computational load across the parallel processors. The paper describes experiments to determine how much CPU and disk I/O work can be performed on data packets without causing an unacceptable reduction in throughput. Our results show that increasing the CPU and I/O work performed per packet decreases the throughput, but this slowdown can be compensated by adding more processors to the parallel cluster, The experiments demonstrate that the system is quite scalable and is capable of supporting fairly high data rates.
This paper describes two different parallel architectures for a space-borne system and analyses them in terms of provided computational power. The designs are simulated based on the actual requirements of the schedule...
详细信息
ISBN:
(纸本)1932415262
This paper describes two different parallel architectures for a space-borne system and analyses them in terms of provided computational power. The designs are simulated based on the actual requirements of the scheduled algorithms to derive parameters like the number of processors, interconnection technology and memory. For a space-based computer the approach of an in-depth simulation was chosen since the variety of possible design options makes a physical implementation and comparison costly. As additional side effect parts of the testing that cannot be done on the actual prototypes, e.g. controlled radiation triggered single event upsets, can easily be performed in a simulation. Although some modules. of the architectures were modelled abstractly, the investigation has shown that design shortcomings can be eliminated at an early stage. This accelerates the overall project implementation. Moreover the simulation models can be used for system integration tests in which the compatibility to the other systems on-board of the satellite can be analysed.
In this paper, we address the design of a distributed service enabling platform for the management of next-generation residential services. The platform allows service providers and telecom operators to rapidly provid...
详细信息
ISBN:
(纸本)1892512459
In this paper, we address the design of a distributed service enabling platform for the management of next-generation residential services. The platform allows service providers and telecom operators to rapidly provide new integrated value-added services to their customers. Layer-based design ensures that he platform is independent of the particular service and the service realization technology. The platform consists of components both at the customer's side as well as at the service provider's side. The key features of the platform are: generic access session management, service session management, subscription management and billing. The different components of the platform will be explained in detail, together with the elaboration of a sample scenario.
distributed Hash Tables (DHTs) have been used in Peer-to-Peer networks to provide key lookups in typically O(log n) hops whilst requiring maintenance of only small amounts of routing state. We extend ROME, a layer whi...
详细信息
ISBN:
(纸本)1932415610
distributed Hash Tables (DHTs) have been used in Peer-to-Peer networks to provide key lookups in typically O(log n) hops whilst requiring maintenance of only small amounts of routing state. We extend ROME, a layer which runs on top of the Chord DHT to provide control over network size through monitoring of node workload and propose the use of processes to reorganise nodes and add or remove them from a pool of available machines. We show this can reduce further the hop counts in networks where available node capacity exceeds workload, without the need to modify any processes of the underlying Chord protocol.
Database queries, in particular, event-driven continuous queries, are useful for many pervasive computing applications, such as video surveillance. In order to enable these applications, we have developed a pervasive ...
详细信息
ISBN:
(纸本)0769523315
Database queries, in particular, event-driven continuous queries, are useful for many pervasive computing applications, such as video surveillance. In order to enable these applications, we have developed a pervasive query processing framework called Aorta. Unlike traditional database systems, a pervasive query processor requires systems support for managing a large number of networked, heterogeneous devices. In this paper, we present the communication, synchronization, and scheduling mechanisms in Aorta. Even though these techniques have their roots in distributed and parallel systems, we show how these techniques are customized and applied for pervasive query processing. In essence, communication between heterogeneous devices enables network data independence, synchronization on devices protects action atomicity, and scheduling works for adaptive, cost-based multi-query optimization. We have conducted empirical studies on our prototype as well as simulation studies to evaluate the system performance.
暂无评论