ACM-IEEE CS Eckert-Mauchly Award
United States – 2013
CITATION

For pioneering contributions to the architecture of shared-memory multiprocessors.

Press Release

Fellow
United States – 2010
CITATION

For contributions to parallel processor and memory system design.

ABOUT JAMES GOODMAN

James R. Goodman is the 2013 ACM-IEEE Eckert-Mauchly recipient, recognized for contributions to the hardware/software interface of computer architecture.  His innovations led to the development of hybrid approaches to high-performance computer memory systems that can achieve nearly the performance of hardware but with the flexibility of software.  Goodman spent much of his career at the University of Wisconsin-Madison, where he and his students extensively researched computer memory systems. He is currently a computer science professor at the University of Auckland, New Zealand.  The Eckert-Mauchly award is known as the computer architecture community’s most prestigious award.  Goodman will receive the award at the International Symposium on Computer Architecture (ISCA 2013), June 26, in Tel Aviv, Israel.

In his seminal 1983 paper, Using Cache Memory to Reduce Processor-memory Traffic, Goodman was the first to describe came to be known as snooping cache coherence protocols for maintaining the consistency of stored data in multiprocessing environments.  The paper also identified the cache’s importance in conserving memory bandwidth.  This work is reflected in virtually every computer built and sold today, reflecting the broad influence of his innovations.

Goodman was the principal co-inventor of hardware queue-based locks, which allow programs with busy-wait synchronization, also known as spinning, to scale to very large multiprocessors.  Spinning is a technique in which a process repeatedly checks to see if a condition is true.  He also introduced critical section speculation, which helped launch the resurgence of transactional memory as a parallel programming and synchronization method. Transactional memory is used for controlling access to shared memory in concurrent computing, a computational processes that may be executed in parallel.  Architectures based on this work have recently begun to appear in products, including the flagship microprocessors from Intel Corp.

Goodman co-authored A Programmer's View of Computer Architecture, a highly acclaimed book on computer architecture, with Karen Miller, and Structural Computer Architecture with Andrew Tanenbaum. A principal supervisor of 10 Ph.D. students, several of which have received prominent recognition as academics and practitioners, Goodman is a Fellow of IEEE and ACM.

A graduate of the University of California, Berkeley with a Ph.D. degree, he worked for Intel Corp. while earning his degree.  He then joined the faculty at the University of Wisconsin – Madison and spent several academic years on sabbatical at AT&T Bell Laboratories, the Advanced Computer Research Laboratory in Lyon, France, and Intel Corp. before going to the University of Auckland.