Memory hierarchies are a key component in obtaining high performance on modern microprocessors. To satisfy the ever-increasing demand on data rate access, they are also becoming increasingly complex: multilevel caches, non-blocking caches, sophisticated instructions for supporting prefetch and cache control, etc. If all of these advanced features promise to offer large performance gains, they a...

With the current popularity of cluster computing systems, it is increasingly important to understand the capabilities and potential performance of various interconnection networks. In this paper, we propose an analytical model for studying the capabilities and potential performance of interconnection networks for multi-cluster systems. The model takes into account stochastic quantities as well ...

The imminent arrival of best-effort transactional hardware has spurred new interest in the construction of nonblocking data structures, such as those that require atomic updates to k words of memory (for some small value of k). Since transactional memory itself (TM) was originally proposed as a universal construction for crafting scalable lock-free data structures, we explore the possibility of...

In this paper we study the liveness of several MUTEX solutions by representing them as processes in PAFASs, a CCS-like process algebra with a specific operator for modelling non-blocking reading behaviours. Verification is carried out using the tool FASE, exploiting a correspondence between violations of the liveness property and a special kind of cycles (called catastrophic cycles) in some tra...

Work-stealing is an efficient method to implement load balancing in fine-grained task parallelism. Typically, concurrent deques are used for this purpose. A disadvantage of many concurrent deques is that they require expensive memory fences for local deque operations. In this paper, we propose a new non-blocking work-stealing deque based on the split task queue. Our design uses a dynamic split ...

The Benes network is capable of setting its own switches dynamically which makes it a best example of a self routing network. The network is capable of realizing a rich class of permutations. In this paper there is an overview of the how routing is done in Benes network and a new algorithm is proposed for routing of the data packets in order to turn into a non-blocking network. Keywords— Blocki...

A major problem in the design of large multichip crossbar networks is the latency associated with the centralized controller used to arbitrate requests. We present a solution to reduce this latency and also provide fault-tolerance by the use of multiple controllers that can operate concurrently. This paper concentrates on crossbars that are constructed using one-sided crosspoint switches, as su...

Testing networked systems is challenging. The client or server side cannot be tested by itself. We present a solution using tool “Modbat” that generates test cases for Java’s network library java.nio, where we test both blocking and non-blocking network functions. Our test model can dynamically simulate actions in multiple worker and client threads, thanks to a carefully orchestrated design tha...

In this paper we consider workflow nets as dynamical systems governed by ordinary difference equations described by a particular class of Petri nets. Workflow nets are a formal model of business processes. Well-formed business processes correspond to sound workflow nets. Even if it seems necessary to require the soundness of workflow nets, there exist business processes with conditional behavio...

This paper proposes efficient algorithms for implementing multicast in heterogeneous workstation/PC clusters. Multicast is an important operation in many scientific and industrial applications. Its efficient implementation on distributed-memory machines plays a critical role in the performance of distributed-memory parallel computing applications. Our work distinguishs itself between others in ...