Graham R. Hellestrand
CEO & President
Vast Systems Technology Corp.
 
Graham R. Hellestrand (M) is President, CEO, and a founder of Vast Systems Technology Corp., Sunnyvale, CA, which specializes in tools for making and marketing real-time, embedded silicon systems. VaST has offices and distributors in USA, Japan, Europe, Korea and Australia, and numbers three of the top five semiconductor vendors in the world as clients.

He was a full Professor of Computer Science and Electrical Engineering at the University of New South Wales, Sydney, Australia 1989-1997. During 1997-98 he served as Vice President for Asia-Pacific for the IEEE Circuits and Systems Society, and was a member of its Board of Governors from 1994 to 1998. He was Chairman of the International Steering Committee of the Asia-Pacific Conference on Circuits and Systems 1997-1998 and was General Chair of the inaugural meeting of this bi-annual conference series held in Sydney in 1992. He has published in excess of 100 refereed conference and journal papers.
 

The talk topic is:

The Bloody Revolution in Systems Engineering
 


Abstract

 
The process of engineering real-time, embedded systems on a chip, apart from transforming the way the world operates, will transform relationships among the hardware, software, and mechanical designers who make the revolutionary products such as 3G cell phones, PDAs, automotive electronics, games, and telecommunications equipment.

The engineering of real-time, embedded systems is not a quiet backwater but a tumult political and economic realignment and foment. And like any revolution-in-progress it is the harbinger of great and unpredictable change bringing with it huge opportunities hand-in-hand with equally impressive threats. The 30 years of hardware dominance in silicon electronic engineering is being torn apart by the recognition that the complexity of modern systems is determined by its multifunctionality, adaptability and flexibility - attributes that, in an economic sense, are best realized in software.

The genesis of this revolution has been the stunning success of the silicon engineers, which ironically has carried with it the seeds of its own diminishment, at least for the half-turn of the next political-technological cycle. As silicon technology marches through 0.18 µm minimum feature sizes to 0.15 µm to 0.13 µm in the next couple of years, and then to sub 0.10 µm, the number of transistors on a chip will approach, then exceed, 1000 million. The majority of these transistors will be consumed as on-chip memory devices. Memory is most useful in programmed devices, and with processors executing several billion instructions per second when implemented in 0.1 µm silicon technology, programmed devices, such as embedded processors, will progressively phase out many special purpose hardware devices.

The trials and tribulations of the industry are evident as hardware, software, and systems engineering are merged to develop the next generation of SoCs. Traditional bottom-up methodologies that have served the semiconductor industry in the past cannot support the development of future generations of complex devices, even though they may be physically realizable. Systems engineering methodologies must be adapted and used to successfully design, model, verify, and integrate hardware, software, and mechanical systems prior to fabrication. Real-time, embedded silicon systems engineering tools to support the specification, design, modeling, and verification of complex hardware-software systems will enable the design of these sophisticated devices.
 
 

Last update: September 7, 2000