Coping with Latency in System-on-a-Chip Design

Luca Carloni
(Professor Alberto L. Sangiovanni-Vincentelli)
Semiconductor Research Corporation

As commercial demand for system-on-a-chip (SOC)-based products grows, the effective reuse of existing intellectual property design modules (also known as IP cores) is essential to meet the challenges posed by deep-submicron (DSM) technologies and to complete a reliable design within time-to-market constraints. An IP core must be both flexible, to collaborate with other modules within different environments, and independent from the particular details of one-among-many possible implementations. The prerequisite for easy trade, reuse, and assembly of IP cores is the ability to assemble predesigned components with little or no effort. The consequent challenge is addressing the communication and synchronization issues that naturally arise while assembling predesigned components. We believe that the semiconductor industry will experience a paradigm shift from computation- to communication-bound design: The number of transistors that a signal can reach in a clock cycle--not the number that designers can integrate on a chip--will drive the design process. The strategic importance of developing a communication-based design methodology naturally follows.

An essential element of communication-based design is the encapsulation of predesigned functional modules within automatically generated interface structures. Such a strategy ensures a correct-by-construction composition of the system. Latency-insensitive design [1] and the recycling paradigm [2] are a step in this direction. High-end microprocessor designers have traditionally anticipated the challenges that ASIC designers are going to face in working with the next process generation. Latency is increasingly affecting the design of state-of-the-art microprocessors (latency, for example, drove the design of so-called drive stages in the new hyperpipelined Netburst microarchitecture of Intel's Pentium 4) and will become a shaping force for SOC architectures [3]. On the one hand, the increasing impact of latency variations will drive architectures toward modular designs with an explicit global latency mechanism. In the case of multiprocessor architectures, latency variation will lead the designers to expose computation/communication tradeoffs to the software compilers. At the same time, the focus on latency will open the way to new synthesis tools that can automatically generate the hardware interfaces responsible for implementing the appropriate synchronization and communication strategies, such as channel multiplexing, data coherency, and so on. All these considerations lead us to propose a design methodology that guarantees the robustness of the system's functionality and performance with respect to arbitrary latency variations [4].

L. P. Carloni, K. L. McMillan, and A. L. Sangiovanni-Vincentelli, "Theory of Latency-Insensitive Design," IEEE Trans. Computer-Aided Design of Integrated Circuits and Systems, Vol. 20, No. 9, September 2001.
L. P. Carloni and A. L. Sangiovanni-Vincentelli, "Performance Analysis and Optimization of Latency Insensitive Systems," Proc. Design Automation Conf., Los Angeles, CA, June 2000.
L. P. Carloni and A. L. Sangiovanni-Vincentelli, "Coping with Latency in SOC Design," IEEE Micro, special issue on systems on chip, Vol. 22, No. 5, September-October 2002.
L. P. Carloni, K. L. McMillan, A. Saldanha, and A. L. Sangiovanni-Vincentelli, "A Methodology for Correct-by-Construction Latency-Insensitive Design," ed. A. Kuehlmann et al., The Best of ICCAD--20 Years of Excellence in Computer-Aided Design, Kluwer Academic Publishers, 2003.

More information ( or

Send mail to the author : (

Edit this abstract