We present novel hardand software that e ciently implements communication primitives for parallel execution on workstation clusters. We provide low communication latencies, minimal protocol, zero operating system overhead, and high throughput. With this technology, it is possible to build e ective parallel systems using o -the-shelf workstations. Our goal is to develop a standard interfaceboard...

Load imbalance is a serious impediment to achieving good performance in parallel processing. Global load balancing schemes cannot adequately manage to balance parallel tasks generated from a single application. Dynamic loop scheduling methods are known to be useful in balancing parallel loops on shared-memory multiprocessor machines. However, their centralized nature causes a bottleneck even fo...

Many real world problems can be categorised under the data parallel programming paradigm. Such problems can be solved in the workstation cluster environment, which is fast becoming a viable platform for parallel computing, by allocating each node a portion of data proportional to its computational capability. In the workstation cluster environment, workstations may be recalled by their primary ...

As commercial microprocessors become increasingly popu lar in current MPP architectures high performance com mercial workstations have also received increased attention as cost e ective building blocks for large parallel processing systems The Fast User level Network FUNet project is an attempt at constructing an inexpensive workstation based parallel system capable of supporting e cient ex ecu...

Both the replicated and distributed data parallel full configuration interaction (FCI) implementations are described. The implementation of the FCI algorithm is organized in a hybrid strings-integral driven approach. Redundant communication is avoided, and the network performance is further optimized by an improved distributed data interface library. Examples show linear scalability of the dist...

One of the new research tendencies within the well-established cluster computing area is the growing interest in the use of multiple workstation clusters as a single virtual parallel machine, in much the same way as individual workstations are nowadays connected to build a single parallel cluster. In this paper we present an analysis on several aspects concerning the integration of different wo...

ParaStation is a high speed communication subsystem which enables a cluster of workstations or PCs to ooer performance comparable to a dedicated parallel machine. Each node is still usable as a regular workstation or PC. Speedups of 7.4 on a 8 node cluster have been achieved even on communication intensive programs. The ParaStation software supports a real multitasking environment and combines ...

For communication-intensive parallel applications, the max imum degree of concurrency achievable i s limited by the communication throughput made available by the network. In previous work [lo], we showed experimentally that the performance of certain parallel applications running o n a workstation network can be improved significantly if a congestion control protocol i s used t o enhance netwo...

Many interesting problems in genetic epidemiology are formulated as non-linear optimization problems wing the Gemini/AImini library of routines. Because of the wide availability of networked workstations, we investigate cost-effectively improving the performance of the Gemini/Almini library by exploiting parallelism m’th a set of workstations connected via a local-area network. Instrumentation ...

{ Network-of-Workstations technology is applied to the challenge of implementing very high performance workstations for Earth and space science applications. The Beowulf parallel workstation employs 16 PC-based processing modules integrated with multiple Ether-net networks. Large disk capacity and high disk to memory bandwidth is achieved through the use of a hard disk and controller for each p...