Our research

We conduct research in the areas of developing and applying parallel programming models on large scale applications, exploring heterogeneous computing platforms and investigating Deep Learning techniques on different hardware.

Exploring language features for high-level programming models to port scientific legacy applications such as molecular dynamics, NGS and nuclear reactor codes on highly parallel large scale systems

Exploring parallelization of irregular algorithms, specifically MIT sFFT, on different platforms

Building validation & verification suites to validate the implementations of programming models OpenACC 2.5 and OpenMP 4.5 and onwards

Developing accelerator benchmark suite to stress test hardware, in collaboration with Standard Performance Evaluation Corporation High Performance Group (SPEC HPG)

Exploring varieties of hardware architecture and its suitability to port Exascale Computing Project (ECP) CANcer Distributed Learning Environment (CANDLE) benchmark pilot case studies

News

Arnov Sinha interns with Numeca International

on October 5, 2017

CRPL member Arnov Sinha joins Numeca International as an intern to port Computational Fluid Dynamics code to large scale supercomputers using high-level directive-based programming model, OpenACC. Arnov’s defended his Master’s thesis on’“High Performance Sparse Fast Fourier Transform using OpenACC.”

Continue reading

Kshitij Srivastava moves to ORNL to work on Deep Learning and Cancer Research

on October 5, 2017

CRPL member Kshitij Srivastava leaves for Oak Ridge National Laboratory to work on cancer data and deploy deep learning strategies on large scale supercomputers. Kshitij Srivastava graduated with his Masters degrees from Electrical & Computer Engineering (Spring 2017). He can be reached on LinkedIn or on Twitter“

Continue reading

Robbie, Kyle, Sanhu, and Jose Travel to Brookhaven National Laboratory for GPU Hackathon

on September 6, 2017

On June 5-9, 2017, CRPL’s Robert Searles, Kyle Friedline, Sanhu Li, and José Monsalve Díaz traveled to Brookhaven National Laboratory (BNL) to participate in the GPU Hackathon hosted there. BNL hosted this event in conjunction with NVIDIA, The Portland Group (PGI), and Oak Ridge National Laboratory (ORNL). Robbie and Kyle acted as mentors for their teams, providing insight using their extensive GPU programming experience. Robbie served as the mentor for Team Uduh: a combination of members from University of Delaware and University of Houston.

Continue reading

CRPL Lab members - Sanhu Li & Arnov Sinha present their research @ GTC'17

on August 22, 2017

Our two teams presented at GTC 2017. Sanhu Li, Sunita Chandrasekaran “S7341: Using OpenACC for NGS Techniques to create a portable and easy-to-use code base” May 9, 15:00-15:25, Room 210C slides Arnov Sinha, Sunita Chandrasekran “S7478: Using OpenACC to Parallelize Irregular Algorithms on GPUs”, May 10, 15:30 - 15:55, Marriott BallRoom 3 slides

Continue reading