Limit study of energy & delay benefits of component-specific routing

Authors:
Nikil Mehta;Raphael Rubin;Andre DeHon
Affiliations:
California Institute of Technology, Pasadena, CA, USA;University of Pennsylvania, Philadelphia, PA, USA;University of Pennsylvania, Philadelphia, PA, USA
Venue:
Proceedings of the ACM/SIGDA international symposium on Field Programmable Gate Arrays
Year:
2012

Citing 20
Cited 3

Defect tolerance on the Teramac custom computer

FCCM '97 Proceedings of the 5th IEEE Symposium on FPGA-Based Custom Computing Machines
An adaptive FPGA architecture with process variation compensation and reduced leakage

Proceedings of the 43rd annual Design Automation Conference
Variation-driven device sizing for minimum energy sub-threshold circuits

Proceedings of the 2006 international symposium on Low power electronics and design
High-performance CMOS variability in the 65-nm regime and beyond

IBM Journal of Research and Development - Advanced silicon technology
Ultralow-voltage, minimum-energy CMOS

IBM Journal of Research and Development - Advanced silicon technology
Variation-aware routing for FPGAs

Proceedings of the 2007 ACM/SIGDA 15th international symposium on Field programmable gate arrays
Performance and yield enhancement of FPGAs with within-die variation using multiple configurations

Proceedings of the 2007 ACM/SIGDA 15th international symposium on Field programmable gate arrays
Parametric yield in FPGAs due to within-die delay variations: a quantitative analysis

Proceedings of the 2007 ACM/SIGDA 15th international symposium on Field programmable gate arrays
Stochastic physical synthesis considering prerouting interconnect uncertainty and process variation for FPGAs

IEEE Transactions on Very Large Scale Integration (VLSI) Systems
TuneFPGA: post-silicon tuning of dual-Vdd FPGAs

Proceedings of the 45th annual Design Automation Conference
Impact of Technology Scaling on Digital Subthreshold Circuits

ISVLSI '08 Proceedings of the 2008 IEEE Computer Society Annual Symposium on VLSI
Choose-your-own-adventure routing: lightweight load-time defect avoidance

Proceedings of the ACM/SIGDA international symposium on Field programmable gate arrays
VPR 5.0: FPGA cad and architecture exploration tools with single-driver routing, heterogeneity and process scaling

Proceedings of the ACM/SIGDA international symposium on Field programmable gate arrays
Self-Measurement of Combinatorial Circuit Delays in FPGAs

ACM Transactions on Reconfigurable Technology and Systems (TRETS)
Interests and limitations of technology scaling for subthreshold logic

IEEE Transactions on Very Large Scale Integration (VLSI) Systems
Variation-aware placement for FPGAs with multi-cycle statistical timing analysis

Proceedings of the 18th annual ACM/SIGDA international symposium on Field programmable gate arrays
FPGA design for timing yield under process variations

IEEE Transactions on Very Large Scale Integration (VLSI) Systems
A resilience roadmap: (invited paper)

Proceedings of the Conference on Design, Automation and Test in Europe
Timing-driven pathfinder pathology and remediation: quantifying and reducing delay noise in VPR-pathfinder

Proceedings of the 19th ACM/SIGDA international symposium on Field programmable gate arrays
A 90-nm Low-Power FPGA for Battery-Powered Applications

IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems

GROK-LAB: generating real on-chip knowledge for intra-cluster delays using timing extraction

Proceedings of the ACM/SIGDA international symposium on Field programmable gate arrays
Minimum energy operation for clustered island-style FPGAs

Proceedings of the ACM/SIGDA international symposium on Field programmable gate arrays
Defect tolerance in nanodevice-based programmable interconnects: utilization beyond avoidance

Proceedings of the 50th Annual Design Automation Conference

Quantified Score

Hi-index	0.02

Visualization

Abstract

As feature sizes scale toward atomic limits, parameter variation continues to increase, leading to increased margins in both delay and energy. The possibility of very slow devices on critical paths forces designers to increase transistor sizes, reduce clock speed and operate at higher voltages than desired in order to meet timing. With post-fabrication configurability, FPGAs have the opportunity to use slow devices on non-critical paths while selecting fast devices for critical paths. To understand the potential benefit we might gain from component-specific mapping, we quantify the margins associated with parameter variation in FPGAs over a wide range of predictive technologies (45nm-12nm) and gate sizes and show how these margins can be significantly reduced by delay-aware, component-specific routing. For the Toronto 20 benchmark set, we show that component-specific routing can eliminate delay margins induced by variation and reduce energy for energy minimal designs by 1.42-1.98×. We further show that these benefits increase as technology scales.