SYCL Support for Continental-Scale Ecological Observations: Scalable and Portable Blending of Massive Image Mosaics
The National Ecology Observatory Network (NEON) is a continental-scale facility which gathers hundreds of terabytes of long-term open-access ecological data to study changes in US ecosystems. Most of this data comes from Airborne Observation Platforms (AOPs) and it is processed and shared with the scientific community through OpenViSUS, developed by the University of Utah and deployed by VISOAR LLC.
Some data analysis components of this infrastructure, such as the color blending algorithm, were originally designed for proprietary GPUs, NEON needed a solution to work across diverse hardware and cloud resources. The adoption of SYCL, Intel MKL and the DPC++ Compatibility Tool provided scalability and portability while significantly reducing development efforts.
Speaker(s)
Steve Petruzza - Utah State University/Assistant Professor
Dr. Steve Petruzza is an Assistant Professor at Utah State University and a Research Associate at the Scientific Computing and Imaging Institute of the University of Utah. His research spans the area of in high performance computing and large scale scientific visualization with focus on efficient and portable workflows for parallel and distributed data analysis and visualization.
