Browse Proceedings

Clusters of industry-standard multiprocessors are emerging as a competitive alternative for large-scale parallel computing. However, these systems have several disadvantages over large-scale multiprocessors, including complex thread scheduling and ...

This paper describes our experiences in building and deploying Windows NT^* based high-end workstation compute farms within the Intel engineering community. An overview of Intel's compute requirements is presented, along with the solution developed to ...

In this paper, we describe an approach to build high-performance, commercial distributed object systems over system area networks (SANs) with user-level networking. The specific platforms we use in this study are the Virtual Interface Architecture (VIA) ...

This paper shares an innovative technology that we developed while migrating Intel CAD design environment from UNIX to Microsoft Windows NT operating system. The UNIX to Windows NT migration is a complex and challenging task because the chip design ...

In this paper we present our experiences developing two distributed computing applications on NT. In both examples a legacy application is ported from Unix to NT and is then further developed to be a distributed application within the NT environment. We ...

This paper describes our experiences in porting the VMMC user-level communication architecture from Linux to Windows NT. The original Linux implementation required no operating system changes and was done entirely using device drivers and user-level ...

We have built a 16-way, ccNUMA multiprocessor prototype to study the feasibility of building large scale servers out of Standard High Volume (SHV) components. Using a cache-coherent interconnect, our prototype combines four 4-processor SMPs built using ...

Sandia National Laboratories (U.S. Department of Energy) and Compaq Computer Corporation built a 72-node Windows NT cluster, which Sandia utilizes for production work contracted by the U.S. government. Recently, Sandia and Compaq's Tandem Division ...

We present the design and results of Millennium Sort, a distributed sorting application built using three layers of technology: extensible River System primitives, the Virtual Interface Architecture (VIA) and the Distributed Component Object Model (DCOM)...

This paper presents an implementation of scheduling abstractions originally developed for the Rialto real-time operating system within a research version of Windows NT called Rialto/NT. These abstractions, CPU Reservations and Time Constraints, as ...

For a variety of reasons, Microsoft Windows NT is increasingly being considered as a platform for deployment of real-time systems. In order to meet the stringent latency requirements of hard real-time systems, it is necessary to augment the capabilities ...

We present a concurrent framework for Win32 programming based on Concurrent ML, a concurrent language with higher-order functions, static typing, lightweight threads and synchronous communication channels. The key points of the framework are the move ...

This paper presents FIFS, a framework that facilitates file system research under Windows NT. FIFS addresses the high cost of file system development under Windows NT by providing a simple user-mode development environment. The environment is a Common ...

Innovative systems research hinges on the ability to easily instrument and extend existing operating system and application functionality. With access to appropriate source code, it is often trivial to insert new instrumentation or extensions by ...

With the introduction of Windows NT, Terminal Server Edition (TSE), Microsoft finally brings to Windows the "thin-client" computing model the X Window System has offered Unix for a decade. TSE's two most salient features are the provision of multi-user ...

This paper presents the design, implementation, and performance of the Harvard Array of Clustered Computers (HACC), a cluster-based design for scalable, cost-effective web servers. HACC is designed for locality enhancement. Requests that arrive at the ...

Application startup latency has become a performance problem for both desktop applications and web applications. In this paper, we show that much of the latency experienced during application startup can be avoided by more efficiently packing ...