No abstract

, IBM announced the start of a five-year effort to build a massively parallel computer, to be applied to the study of biomolecular phenomena such as protein folding. The project has two main goals: to advance our understanding of the mechanisms behind protein folding via large-scale simulation, and to explore novel ideas in massively parallel machine architecture and software. This project should enable biomolecular simulations that are orders of magnitude larger than current technology permits. Major areas of investigation include: how to most effectively utilize this novel platform to meet our scientific goals, how to make such massively parallel machines more usable, and how to achieve performance targets, with reasonable cost, through novel machine architectures. This paper provides an overview of the Blue Gene project at IBM Research. It includes some of the plans that have been made, the intended goals, and the anticipated challenges regarding the scientific work, the software application, and the hardware design.

Research on Rent's rule in electrical engineering, the applied sciences, and technology has been based on the publication of a 1971 interpretation of Rent's memoranda by B. S. Landman and R. L. Russo. Because of the wide impact of Rent's work and requests from researchers, we present his original memoranda in this paper. We review the impact of Rent's work and present the memoranda in the context of IBM computer hardware development since the 1950s. Furthermore, because computer hardware components have changed significantly since the memoranda were written in 1960, a new interpretation is needed for today's ultra-large-scale integrated circuitry. On the basis of our analysis of the memoranda, one of the authors' personal knowledge of the 1401 and 1410 computers, and our experience in the design of high-performance circuitry for microprocessor chips, we have derived an historically equivalent interpretation of Rent's memoranda that is suitable for today's computer components. We describe an application of our historically equivalent interpretation to the problem of assessing on-chip interconnection requirements of control logic circuitry in the IBM POWER4e microprocessor.

No abstract

As 1999 ended, IBM announced its intention to construct a onepetaflop supercomputer. The construction of this system was based on a cellular architecture-the use of relatively small but powerful building blocks used together in sufficient quantities to construct large systems. The first step on the road to a petaflop machine (one quadrillion floating-point operations in a second) is the Blue Genet/L supercomputer. Blue Gene/L combines a low-power processor with a highly parallel architecture to achieve unparalleled computing performance per unit volume. Implementing the Blue Gene/L packaging involved trading off considerations of cost, power, cooling, signaling, electromagnetic radiation, mechanics, component selection, cabling, reliability, service strategy, risk, and schedule. This paper describes how 1,024 dual-processor compute application-specific integrated circuits (ASICs) are packaged in a scalable rack, and how racks are combined and augmented with host computers and remote storage. The Blue Gene/L interconnect, power, cooling, and control systems are described individually and as part of the synergistic whole.