MIT Lincoln Laboratory HPECPanel-1 DRM 06/21/22 Amending Moore’s Law for Embedded Applications Panel Discussion David R. Martinez Eighth Annual Workshop on High Performance Embedded Computing 29 September 2004 This work is sponsored by the Defense Advanced Research Projects Agency under Air Force Contract F19628- 00-C-0002. Opinions, interpretations, conclusions and recommendations are those of the author and are not necessarily endorsed by the United States Government.
4
Embed
Amending Moore’s Law for Embedded Applications Panel Discussion
Amending Moore’s Law for Embedded Applications Panel Discussion. David R. Martinez Eighth Annual Workshop on High Performance Embedded Computing 29 September 2004. - PowerPoint PPT Presentation
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
This work is sponsored by the Defense Advanced Research Projects Agency under Air Force Contract F19628-00-C-0002. Opinions, interpretations, conclusions and recommendations are those of the author and are not necessarily endorsed by the United States Government.
MIT Lincoln LaboratoryHPECPanel-2DRM 04/22/23
DoD Embedded Processing Applications
Future systems need: • Higher performance with reduced
cost, size, weight, and power consumption• Adaptability, flexibility,scalability, reconfigurability• High bandwidth internal and network data communications
WarfighterTechnology
Space-BasedSensors
UCAV
Micro AirVehicles:
Visible, IR, Radar
Airborne Comm Nodes
Interceptors
Underwater Fighter
CommSystems
Unmanned Systems
Airborne Sensors:Radar, Elint, SIGINT
NavalSurface
Systems:Radar,Comm
Courtesy of P. Monticciolo
MIT Lincoln LaboratoryHPECPanel-3DRM 04/22/23
Power Density: The Fundamental Problem
Courtesy of C.Keast
MIT Lincoln LaboratoryHPECPanel-4DRM 04/22/23
Prognosis For Moore’s Law BenefitsHigher Speed? Lower Cost?
Lower Power?
PastSupply voltage (V) scales as 1/sCapacitance (C) scales as 1/sEnergy per op scales as CV2 1/ s3
Voltage scaling from 5V to 1V accounts for 25X reduction in power, just by itself
Future IssuesOnly 2x voltage scaling planned (1V now to ~0.5V in 2016) Scaling energy per op is critical to long endurance battery powered systems and to supercomputers (getting power in and heat out)