the proceedings contain 53 papers. the special focus in this conference is on Software, applications and Tools. the topics include: Solving of the alignment and scheduling problems;accuracy and stability of spatial dy...
ISBN:
(纸本)3540406735
the proceedings contain 53 papers. the special focus in this conference is on Software, applications and Tools. the topics include: Solving of the alignment and scheduling problems;accuracy and stability of spatial dynamics simulation by cellular automata evolution;resource similarities in Petri net models of distributed systems;authentication primitives for protocol specifications;an extensible coloured Petri net model of a transport protocol for packet switched networks;parallelcomputing for globally optimal decision making;parallelization of alternating direction implicit methods for three-dimensional domains;an approach to assessment of heterogeneous parallel algorithms;a hierarchy of conditions for asynchronous interactive consistency;associative parallel algorithms for dynamic edge update of minimum spanning trees;the renaming problem as an introduction to structures for wait-free computing;graph partitioning in scientific simulations;process algebraic model of superscalar processor programs for instruction level timing analysis;a polymorphic type system for bulk synchronous parallel ml;towards an efficient functional implementation of the NAS benchmark ft;a fast pipelined parallel ray casting algorithm using advanced space leaping method;formal modeling for a real-time scheduler and schedulability analysis;global system image for cluster computing;asynchronous timed multimedia environments based on the coordination paradigm;component-based development of dynamic workflow systems using the coordination paradigm;an efficient marshaling framework for distributed systems;deciding optimal information dispersal for parallelcomputing with failures and communication-efficient parallel Gaussian elimination.
Centralized parallel packet switch algorithm and distributed parallel packet switch algorithm are two typical scheduling algorithms for parallel packet switch. this paper analyzes the two algorithms in detail, address...
详细信息
ISBN:
(纸本)9780769527369
Centralized parallel packet switch algorithm and distributed parallel packet switch algorithm are two typical scheduling algorithms for parallel packet switch. this paper analyzes the two algorithms in detail, addresses several key problems in their implementation and finally presents several available methods and suggestions to make the parallel packet switch more practical.
In the paper, we propose a generic parallelcomputing model for the distributed computing platforms. this model is built on the top of the popular CORBA middleware in order to ensure easy distribution of the software ...
详细信息
ISBN:
(纸本)9780769527369
In the paper, we propose a generic parallelcomputing model for the distributed computing platforms. this model is built on the top of the popular CORBA middleware in order to ensure easy distribution of the software components along the participating computers. We use the concept of factory objects in the model to create slave objects dynamically to fulflll the master/slave parallelcomputing paradigm. the speedup of the experiment programs using our proposed model is measured and compared withthe corresponding A PI implementation. the experiment results show that our model is not only a feasible model for designing parallel programs with CORBA but also an efficient way in comparison to the MPI implementation.
One important way of solving 110 bottleneck is to develop parallel file system. Research showed that the strided file access pattern in scientific applications combined with current file system methods to perform thes...
详细信息
ISBN:
(纸本)9780769527369
One important way of solving 110 bottleneck is to develop parallel file system. Research showed that the strided file access pattern in scientific applications combined with current file system methods to perform these accesses lead to unacceptable performance for large data access. To enhance performance of discontiguous data access, we have created a new high performance 110 method: the user-defined file view and combining 110 requests (UFCR). We have implemented our ideas on WPFS. Experimentation results showed that our method can substantially enhance the performance of scientific applications.
We describe a tool that implements a set of services to manipulate and store data from a radar network in a transparent way to end users. A major requirement of this system is data availability and reliability. Conseq...
详细信息
ISBN:
(纸本)9780769527369
We describe a tool that implements a set of services to manipulate and store data from a radar network in a transparent way to end users. A major requirement of this system is data availability and reliability. Consequently, we have implemented a redundancy schema based on the Information Dispersal Algorithm (IDA). Preliminary results show that the IDA based replication provides better reliability and less storage spending than traditional replication.
A fault-tolerant conference key distribution scheme based on mechanism of identity-based cryptography and (t,n) threshold secret sharing is proposed in this paper. this scheme is much different to traditional ones, it...
详细信息
ISBN:
(纸本)9780769527369
A fault-tolerant conference key distribution scheme based on mechanism of identity-based cryptography and (t,n) threshold secret sharing is proposed in this paper. this scheme is much different to traditional ones, its secret shadows are not brought from the sponsor of conference, but from each server's private key signature. By getting together these n secret shadows, the sponsor can construct polynomial. Any of conferees invited by the sponsor can request these secret shadows from t of these n servers, and then restitute conference key by them. In all courses of conference key distribution and reconstruction, every member's identity can be easily validated, so it can be prevented from all kinds of cheat.
the knapsack problem is a famous NP-complete problem. It is very important in the research on cryptosystem and number theory. After its proposed parallel algorithms are analyzed deeply, a new parallel algorithm by sam...
详细信息
ISBN:
(纸本)9780769527369
the knapsack problem is a famous NP-complete problem. It is very important in the research on cryptosystem and number theory. After its proposed parallel algorithms are analyzed deeply, a new parallel algorithm by sampling is proposed based on MIMD supercomputers in the paper . then performance analysis and comparisons are illuminated Finally the experimental results of the knapsack instances randomly generated on IBM P690 supercomputer are given. the results show: the parallel efficiency can be over 60% when solving the larger scale knapsack instances (n >= 40). thus it is proved that the proposed parallel algorithm for the knapsack problem is feasible and efficient on MIMD scalable supercomputers.
Multi-core processors can easily provide benefits for multithreaded workloads, but many applications written for uniprocessors cannot automatically benefit from chip multiprocessors (CMP) designs. this paper presents ...
详细信息
ISBN:
(纸本)9780769527369
Multi-core processors can easily provide benefits for multithreaded workloads, but many applications written for uniprocessors cannot automatically benefit from chip multiprocessors (CMP) designs. this paper presents a reverse compilation framework, which translates existing binary code without source code to the Static Single Assignment (SSA) form, and then the internal SSA form is applied by the compilation phase to generate the Speculative parallelthreading (SPT) code. A profiler is applied to optimize the code dynamically during execution. the evaluation results show that these existing binary codes without source codes execute on CMP with performance improved, due to taking advantage of the speculative parallelthreading support provided by the processor.
the problem is that the parallel scheduling strategies are minimally supported in distributed environments. the well-known Coffman-Graham algorithm is highly effective but applied only for the sample case when all tas...
详细信息
ISBN:
(纸本)9780769527369
the problem is that the parallel scheduling strategies are minimally supported in distributed environments. the well-known Coffman-Graham algorithm is highly effective but applied only for the sample case when all tasks have the same execution time and not applied for the distributed systems. In this paper, an expanding task graph and an expanding Coffman-Graham algorithm, which orients to the distributed systems and can be applied for the case when the tasks have the different execution time, are proposed Like the well-known Coffman-Graham algorithm, the ECG algorithm is proved to be an efficient scheduling algorithm for the distributed systems, through presenting and deducting one theorem and two corollaries.
暂无评论