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. Their task was to use the GPU to accelerate CoMD: a code for molecular dynamics simulations, which scientists use to study the interactions between molecules. Kyle put his mentor hat on for Team MUSIC (for MUScl for Ion Collision), which consisted of members from BNL and Stony Brook University. Their application is used to simulate the evolution of the quark-gluon plasma produced at Brookhaven’s Relativistic Heavy Ion Collider (RHIC).
Sanhu and José participated as members of Team AccSequencer from University of Delaware. They worked on creating a high-level abstraction for BarraCUDA: an open-source code for an existing next-generation-sequencing tool for aligning thousands of DNA sequences. Since it was originally written in CUDA, it cannot run on any non-NVIDIA architecture. Porting this code to OpenACC allows users to run it on a variety of hardware, including multi-core CPUs (Intel, AMD, and IBM), AMD GPUs, and NVIDIA GPUs. This sequencer has far-reaching impact in the area of bioinformatics research including drug targeting technology, cancer research, congenital disease and others applications.
For more information, check out the article: https://www.bnl.gov/newsroom/news.php?a=212273