Optimizing FPGA Logic Circuitry for Variable Voltage Supplies
Unlike central processing units (CPUs), field-programmable gate arrays (FPGAs) have conventionally been powered with a fixed supply voltage ( V_{\text {dd}} ). However, recent efforts have shown that adopting dynamic voltage scaling reduces FPGA power consumption significantly. In this article, we a...
Gespeichert in:
Veröffentlicht in: | IEEE transactions on very large scale integration (VLSI) systems 2020-04, Vol.28 (4), p.890-903 |
---|---|
Hauptverfasser: | , , |
Format: | Artikel |
Sprache: | eng |
Schlagworte: | |
Online-Zugang: | Volltext bestellen |
Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
Zusammenfassung: | Unlike central processing units (CPUs), field-programmable gate arrays (FPGAs) have conventionally been powered with a fixed supply voltage ( V_{\text {dd}} ). However, recent efforts have shown that adopting dynamic voltage scaling reduces FPGA power consumption significantly. In this article, we analyze the delay sensitivity of different FPGA circuit elements to supply voltage changes and determine that conventional lookup table (LUT) designs greatly impact variable {V_{\text {dd}}} operation. To build FPGAs with lower delay sensitivity to {V_{\text {dd}}} , we propose several new LUT designs, including gate boosting the LUT, decoding the slowest two inputs of the LUT, and using separate voltage islands for the FPGA LUTs and routing. Our fastest proposed design (decode-driver island) reduces the area-delay product of the FPGA logic plus routing tile compared to a conventional design by 12% and 52% at {V_{\text {dd}}} values of 0.8 V (the nominal voltage) and 0.6 V, respectively. Since our proposed FPGA tile designs are faster and have lower delay sensitivity to voltage, they offer better {\text {Energy-Delay} {{^{\mathrm{ 2}}} product ( {\text {ED} {{^{\mathrm{ 2}}} ) than that of the baseline at nominal {V_{\text {dd}}} and below. Our decode-driver-island FPGA achieves a 26% {\text {ED} {{^{\mathrm{ 2}}} reduction over the conventional design at the most efficient {\text {ED} {{^{\mathrm{ 2}}} operating point. |
---|---|
ISSN: | 1063-8210 1557-9999 |
DOI: | 10.1109/TVLSI.2019.2962501 |