The book focuses on the cost/area, performance and power consumption differences between Field-Programmable Gate Arrays (FPGAs) and Application Specific Integrated Circuits (ASICs). These differences are referred to as the gap between FPGAs and ASICs and knowledge of this gap is fundamental for people who design FPGAs, who use FPGAs, or who are considering their use. This book reviews and examines the gap in two ways. The first portion of the book focuses on measurements of the silicon area, performance, and power consumption gap. This is done by comparing designs implemented on a commercial FPGA and using an ASIC methodology. Through this comparison, various trends are noted to elucidate some of the design choices that can narrow the gap. The latter half of the book focuses on the trade-offs that can be made in the creation of a FPGA to narrow the gap selectively. This is useful because silicon area, performance and power consumption are not equally important to all users of FPGAs. The book describes the approach used to investigate these trade-offs and it includes a detailed description of the transistor sizing tool developed to assist in this investigation. The scope of the trade-offs is then examined and the effect of these trade-offs on the FPGA to ASIC gap is considered. The idea of making cost and performance trade-offs has been considered in past works but this book explores the use of transistor-sizing to enable these trade-offs.
Cited By
- Tang X, Giacomin E, Cadareanu P, Gore G and Gaillardon P A RRAM-based FPGA for energy-efficient edge computing Proceedings of the 23rd Conference on Design, Automation and Test in Europe, (144a-144f)
- Farooq U, Mehrez H and Bhatti M (2018). Inter-FPGA interconnect topologies exploration for multi-FPGA systems, Design Automation for Embedded Systems, 22:1-2, (117-140), Online publication date: 1-Jun-2018.
- Mazumdar B, Ali S and Sinanoglu O (2016). A Compact Implementation of Salsa20 and Its Power Analysis Vulnerabilities, ACM Transactions on Design Automation of Electronic Systems, 22:1, (1-26), Online publication date: 28-Dec-2016.
- Gaillardon P, Tang X, Sandrini J, Thammasack M, Omam S, Sacchetto D, Leblebici Y and De Micheli G A ultra-low-power FPGA based on monolithically integrated RRAMs Proceedings of the 2015 Design, Automation & Test in Europe Conference & Exhibition, (1203-1208)
- Benkrid K and Clayton T (2012). Digital Hardware Design Teaching, ACM Transactions on Computing Education (TOCE), 12:4, (1-20), Online publication date: 1-Nov-2012.
Recommendations
Measuring the Gap Between FPGAs and ASICs
This paper presents experimental measurements of the differences between a 90-nm CMOS field programmable gate array (FPGA) and 90-nm CMOS standard-cell application-specific integrated circuits (ASICs) in terms of logic density, circuit speed, and power ...
Efficient AES implementations on ASICs and FPGAs
AES'04: Proceedings of the 4th international conference on Advanced Encryption StandardIn this article, we present two AES hardware architectures: one for ASICs and one for FPGAs. Both architectures utilize the similarities of encryption and decryption to provide a high throughput using only a relatively small area. The presented ...
(When) will FPGAs kill ASICs? (panel session)
DAC '01: Proceedings of the 38th annual Design Automation ConferenceThere was a time - in the dim historical past - when foundries actually made ASICs with only 5000 to 50,000 logic gates. But FPGAs and CPLDs conquered those markets and pushed ASIC silicon toward opportunities with more logic, volume, and speed. Today'...