Ultra-elastic cgras for irregular loop specialization

C Torng, P Pan, Y Ou, C Tan… - 2021 IEEE International …, 2021‏ - ieeexplore.ieee.org
Reconfigurable accelerator fabrics, including coarse-grain reconfigurable arrays (CGRAs),
have experienced a resurgence in interest because they allow fast-paced software algorithm …

A fast algorithm for ICP-based 3D shape biometrics

P Yan, KW Bowyer - Computer Vision and Image Understanding, 2007‏ - Elsevier
In a biometrics scenario, gallery images are enrolled into the database ahead of the
matching step, which gives us the opportunity to build related data structures before the …

Low power HEVC software decoder for mobile devices

E Raffin, E Nogues, W Hamidouche, S Tomperi… - Journal of Real-Time …, 2016‏ - Springer
In the context of mobile handheld devices, energy consumption is a primary concern and the
process of video decoding is often among the most resource-intensive applications. Recent …

Synchoricity and NOCs could make billion gate custom hardware centric SOCs affordable

A Hemani, SMAH Jafri, S Masoumian - Proceedings of the Eleventh …, 2017‏ - dl.acm.org
In this paper, we present a novel synchoros VLSI design scheme that discretizes space
uniformly. Synchoros derives from the Greek word chóros for space. We propose raising the …

Power-aware computing systems on FPGAs: a survey

G Akgün, M Ali, D Göhringer - 2021 31st International …, 2021‏ - ieeexplore.ieee.org
A major concern with battery-operated devices is power-awareness and its appropriate
computing. The power dissipation of such systems is usually considered a hardware …

Energy efficiency and performance management of parallel dataflow applications

S Holmbacka, E Nogues, M Pelcat… - Proceedings of the …, 2014‏ - ieeexplore.ieee.org
Parallelizing software is a popular way of achieving high energy efficiency since parallel
applications can be mapped on many cores and the clock frequency can be lowered. Perfect …

Mocha: Morphable locality and compression aware architecture for convolutional neural networks

SMAH Jafri, A Hemani, K Paul… - 2017 IEEE International …, 2017‏ - ieeexplore.ieee.org
Today, machine learning based on neural networks has become mainstream, in many
application domains. A small subset of machine learning algorithms, called Convolutional …

Power-aware HEVC decoding with tunable image quality

E Nogues, S Holmbacka, M Pelcat… - 2014 IEEE workshop …, 2014‏ - ieeexplore.ieee.org
A high pressure is put on mobile devices to support increasingly advanced applications
requiring more processing capabilities. Among those, the emerging High Efficiency Video …

Silago-cog: Coarse-grained grid-based design for near tape-out power estimation accuracy at high level

SMAH Jafri, N Farahini… - 2017 IEEE computer …, 2017‏ - ieeexplore.ieee.org
It is well known that ASICs have orders of magnitude higher power efficiency than general
propose processors. However, due to the high engineering and manufacturing cost only …

RiBoSOM: Rapid bacterial genome identification using self-organizing map implemented on the synchoros SiLago platform

Y Yang, D Stathis, P Sharma, K Paul… - Proceedings of the 18th …, 2018‏ - dl.acm.org
Artificial Neural Networks have been applied to many traditional machine learning
applications in image and speech processing. More recently, ANNs have caught attention of …