Jane C. Blake,
Managing Editor

Designs that capitalize on Digital's 64-bit Alpha RISC processors or that enhance the performance of scientific applications are the subjects of papers in this issue. Featured topics include the well-received AlphaServer multiprocessing systems, the DEC OSF/1 symmetric multiprocessing operating system, a high-performance math library, and a preprocessor program developed by Kuck & Associates, Inc.

To develop a price/performance leader for the server market, designers of the AlphaServer 2100 and 2000 multiprocessing systems had to make decisions that were at once creative, pragmatic, and timely. Fidelma Hayes, an engineering manager for the Server Group, presents an overview of these high-performance servers that incorporate Alpha RISC technology and PC-style I/O subsystems, and support three operating systems -- Microsoft's Windows NT, DEC OSF/1, and OpenVMS. Because of the engineering team's persistent focus on performance, cost, and time-to-market, all these goals for the AlphaServer systems were surpassed.

Introducing two PC buses in the AlphaServer multiprocessing system was an important factor in market success and an interesting engineering challenge. Andy Russo discusses the benefits of a dual-level I/O structure which contains both the widely used EISA bus and the newer high-performance PCI bus that connects to a 128-bit multiprocessing system bus. He describes several innovative techniques that promote efficiency in the hierarchical bus structure, the advantages offered by the selection of bus bridges (one custom ASIC and one standard chip set), and the I/O interrupt scheme that combines familiar technology with custom support logic.

The next paper presents the significant software work done to ensure high performance and reliability as CPUs are added to the 2100 and 2000 multiprocessing systems. Jeff Denham, Paula Long, and Jim Woodward first review the foundations of DEC OSF/1 version 3.0, Digital's implementation of UNIX for the AlphaServer multiprocessing systems. They then examine issues that arise when moving an operating system from a uniprocessor to a shared-memory SMP platform, in particular, the design team's efforts in lock-based synchronization and algorithm modifications aimed at parallelism within the operating system kernel.

The total impact of 64-bit RISC systems and operating system support for shared memory SMP platforms is demonstrated by meeting the demands of scientific and technical applications. A tool for accelerating application performance on all Alpha systems is the DXML Extended Math Library. Chandrika Kamath, Roy Ho, and Dwight Manley briefly discuss the role of mathematical libraries and then present an overview of DXML components, which include both public domain BLAS and LAPACK libraries and Digital proprietary software. Using example routines, they explain optimization techniques that effectively exploit the memory hierarchy and provide substantial performance improvements.

Another tool for optimizing scientific application performance is KAP, a preprocessor to parallelize DEC Fortran and DEC C programs. As authors Bob Kuhn, Bruce Leasure, and Sanjiv Shah from Kuck & Associates describe it, the KAP product is a superoptimizer, performing optimizations at the source code level that go beyond those performed by the compilers. Their paper reviews adaptations to KAP for SMP systems and the key design aspects, such as data dependence analysis and the selection of loops to parallelize from among many in a program.

The editors thank Andrei Shishov, Mid-range AlphaServers Program Manager, for his help in developing this issue of the Journal.