NEU Computer Architecture Research Group


Fanny Nina-Paravecino

Currently, I'm a PhD Candidate and Research Assistant in Computer Engineering at Northeastern University. I am part of Northeastern University Research Group (NUCAR) under supervision of Dr. David Kaeli. I received a B.S. in System and Informatics Engineering from University of San Antonio Abad of Cusco in PerĂº in 2008. Later, in 2011, I received M.Sc. in Computer Engineering from University of Puerto Rico at Mayaguez.

My undergrad thesis was focused on OpenGL as a tool to develop virtual 3D environment to build Industrial Robots. Later, my master research was focused on image processing algorithms to analyze hyper-spectral imagery. Currently, my main interest focuses on high performance optimization, with emphasis on parallel architectures such as GPGPU.

In recent years, I have been working on parallel implementation of image segmentations algorithms such as: connected component labeling, spectral clustering, level set and graph partitioning on Kepler Architectures using CUDA framework, leveraging the latest advances features (e.g. Hyper-Q, dynamic parallelism). Image segmentation plays an important role in many different applications. My current efforts target homeland security application. Specifically, luggage scanning at airports. On the computer architecture side, my research explores the feasibility of auto-tuning process for different applications over different GPGPU architectures. One of the main contributions is to exploit the concurrent kernel execution.