A unified framework for over-clocking linear projections on FPGAs under PVT variation
RP Duarte, CS Bouganis - … , ARC 2014, Vilamoura, Portugal, April 14-16 …, 2014 - Springer
Linear Projection is a widely used algorithm often implemented with high throughput
requisites. This work presents a novel methodology to optimise Linear Projection designs …
requisites. This work presents a novel methodology to optimise Linear Projection designs …
Fault-tolerant architecture for on-board dual-core synthetic-aperture radar imaging
In this research work, an on-board dual-core embedded architecture was developed for SAR
imaging systems, implementing a reduced-precision redundancy fault-tolerance …
imaging systems, implementing a reduced-precision redundancy fault-tolerance …
Arc 2014 over-clocking KLT designs on FPGAs under process, voltage, and temperature variation
RP Duarte, CS Bouganis - ACM Transactions on Reconfigurable …, 2015 - dl.acm.org
Karhunen-Loeve Transformation is a widely used algorithm in signal processing that often
implemented with high-throughput requisites. This work presents a novel methodology to …
implemented with high-throughput requisites. This work presents a novel methodology to …
Leveraging PVT-Margins in Design Space Exploration for FPGA-based CNN Accelerators
The performance of an FPGA based CNN accelerator is determined by both parallelism and
frequency, however, most prior works optimize the parallelism in the RTL design and resolve …
frequency, however, most prior works optimize the parallelism in the RTL design and resolve …
Over-clocking of linear projection designs through device specific optimisations
RP Duarte, CS Bouganis - 2014 IEEE International Parallel & …, 2014 - ieeexplore.ieee.org
Frequently, applications such as image and video processing rely on implementations of the
Linear Projection algorithm with high throughput and low latency requirements. This work …
Linear Projection algorithm with high throughput and low latency requirements. This work …
Making data center computations fast, but not so furious
We propose an aggressive computational sprinting variant for data center environments.
While most of previous work on computational sprinting focuses on maximizing the sprinting …
While most of previous work on computational sprinting focuses on maximizing the sprinting …
Variation-Aware Optimisation for Reconfigurable Cyber-Physical Systems
RP Duarte, CS Bouganis - … Innovation for Cyber-Physical Systems: 7th IFIP …, 2016 - Springer
Abstract Cyber-Physical Systems are present in many industries such as aerospace,
automotive, health-care and transportation, and over time they have become critical and …
automotive, health-care and transportation, and over time they have become critical and …
[PDF][PDF] On-The-Fly Fault-Tolerant Floating-Point Arithmetic
RP Duarte - Conference on, Aug, 2012 - academia.edu
On-the-Fly ROM-based Redundancy can detect and correct errors by using low-latency
redundant Look-Up Tables stored in ROM. Thus far, determining only fixed-point arithmetic …
redundant Look-Up Tables stored in ROM. Thus far, determining only fixed-point arithmetic …