P.J. Garcia’s research while affiliated with University of Castilla-La Mancha and other places

One of the objectives of the decade for High-Performance Computing systems is to reach the exascale level of computing power before 2018, hence this will require strong efforts in their design. In that sense, High-speed low-latency interconnection networks are essential elements for exascale HPC systems. Indeed, the performance of the whole system depends on that of the interconnection network. In order to develop and test new techniques, suited to exascale HPC systems, software-based networks simulators are commonly used. As developing a network simulator from scratch is a difficult task, several platforms help the developers, OMNeT++ being one of the most popular. In this paper, we propose a new generic network simulator, exploiting the features of the OMNeT++ framework. The proposed tool is the first step to model HPC high-performance interconnection networks of exascale HPC systems: the message switching layer, routing and arbitration algorithms and buffer organizations have been modeled according to the current and expected characteristics of these systems. In addition, the tool has been designed so that it is possible to simulate networks of large size. Simulation results, validated against real systems, show the accuracy of the model.

The Interconnection networks are essential elements in current computing systems. For this reason, achieving the best network performance, even in congestion situations, has been a primary goal in recent years. In that sense, there exist several techniques focused on eliminating the main negative effect of congestion: the Head of Line (HOL) blocking. One of the most successful HOL blocking elimination techniques is RECN, which can be applied in source routing networks. FBICM follows the same approach as RECN, but it has been developed for distributed deterministic routing networks. Although FBICM effectively eliminates HOL blocking, it requires too much resources to be implemented. In this paper we present a new FBICM version, based on a new organization of switch memory resources, that significantly reduces the required silicon area, complexity and cost. Moreover, we present new results about FBICM, in network topologies not yet analyzed. From the experiment results we can conclude that a far less complex and feasible FBICM implementation can be achieved by using the proposed improvements, while not losing efficiency.

Congestion has been an open issue in lossless interconnection networks for the last twenty years. In this environment, as packets can not be dropped, congestion may lead to a dramatic degradation of network performance. Although congestion was traditionally avoided by overdimensioning the network, this solution is no longer valid due to cost and power consumption concerns, that tend to reduce the size of the network in current systems. The restriction on network size makes the system working closer to the network saturation point, thus increasing congestion probability. Therefore, an effective congestion management mechanism is essential in order to avoid network performance degradation. However, except the recently proposed RECN mechanism, none of the congestion management strategies proposed in the literature had been able to achieve, at the same time, the required efficiency and scalability levels demanded by emerging systems. In this paper we analyze the difficulties in han-dling congestion on lossless interconnection networks, identifying the key points for the design of an efficient and scalable congestion management technique. We also describe how these ideas have been implemented in the RECN design. Moreover, we also show that RECN is fully compatible with the Advanced Switching standard, allowing efficient and scalable congestion management in real systems.

Interconnection networks are a key element in a wide variety of systems: massive parallel processors, local and system area networks, clusters of PCs and workstations, and Internet Protocol routers. They are essential to high performance in the form of high-bandwidth communications, with low latency, "quality of service" (guaranteed service levels), efficient switching, and flexibility of network topology, as embodied in Myrinet, InfiniBand, Quadrics, Advanced Switching, and similar interconnects. But, despite all the advances that modem interconnects offer, congestion is a growing problem as "lossless" interconnection networksrdquo those that do not allow data packets to be discarded" come to the fore.

Compared to the overdimensioned designs of the past, current interconnection networks operate closer to the point of saturation and run a higher risk of congestion. Among proposed strategies for congestion management, only the regional explicit congestion notification (RECN) mechanism achieves both the required efficiency and the scalability that emerging systems demand

We present a parallel algorithm for lossless compression. The algorithm is based on the 3D wavelet transform (3-D WT). The system under study consists of a parallel implementation of a wavelet compression software running on a cluster of eight nodes linked by a high performance local area network, Myrinet. The parallel implementation is based on the standard message passing interface (MPI). We have used three implementations of the MPI standard: MPI-BIP, MPICH, and LAM. Experimental results are reported based on these three implementations. We provide performance results of this parallel system for the compression video sequences. Some bugs in the efficiency for TCP implementation are reported and resolved for this system

The Network File System (NFS) is an open standard that implements a client/server architecture enabling file sharing over heterogeneous computer systems from PCs to mainframes. NFS is currently being upgraded to better meet the performance and reliability requirements of a large variety of applications, ranging from database queries in a LAN cluster to multimedia applications via the Internet. The main objective of our work is to analyze the performance of NFS as the file system support for parallel image processing applications. We undertake the performance study of NFS over a parallel-processing platform used to accelerate the compression process of digital video. The experimental platform consists of eight nodes connected by a high-speed network (Myrinet). We use NFS to allow a set of processors to gain access to the uncompressed video sequences stored in the NFS-based file server. We have carried out a first set of experiments to evaluate the performance of NFS in terms of I/O response time. Our first results have shown the existence of communication bottlenecks and scalability problems in the system. We have identified some critical system parameters and analyzed their impact over the overall system response time. In a second set of experiments, we explored the performance of the system by changing the cluster topology

In this paper we have carried out an experimental study of the I/O latency of a distributed file system over a parallel multimedia platform. Our experimental platform uses NFS (Network File System) to support an application characterized by its high processing and storage requirements. We evaluate the overall system by varying several NFS parameters as well as the underlying network topology and data access patterns. We have also examined the relevance of two other important file management access mechanisms: caching and prefetching. Our experimental results have allowed us to identify the major system parameters affecting the performance of NFS. We then propose the use of a predictive data access mechanisms. Under this mechanism, the file server should detect the similarities among the most recent I/O requests incoming from a set of cooperating clients. Once having identified the access pattern, the file server will be able to multicast the required data even before receiving explicit I/O data requests from the clients. Under this predictive mechanism, the system performance should improve as the number of explicit I/O requests directed to the file server decreases