Parallel Computing
Center of Excellence for Geospatial Information Science (CEGIS)
Parallel Computing is a method for organizing computations into smaller pieces to be completed on multiple computer processors.
The way one chooses to employ parallel computing will vary based on workload and resources. The investigation and development of parallel computing methods in CEGIS seeks to provide support to a wide range of work across the organization and the geospatial community.
Big data
Big data typically refers to data sets that are too large to be dealt with by traditional data-related software. It can be difficult to move around, to maintain, to search, and to use effectively.
Parallel software
Software can be built to work on multiple processors in many computers.
Two common styles of parallel computing are High-Performance Computing (HPC) focusing on making one task fast, while High Throughput Computing (HTC) handles a large number of independent tasks.
Many-task Computing (MTC) is similar to HTC but emphasizes completing many varied tasks quickly.
Parallel systems
To use and generate data quickly we need computer systems that enable that functionality.
One can employ virtual machines and isolated software environments (containers) in various ways to offer flexibility for users and system administrators.
GPU's and similar hardware can provide additional computation resources for many tasks.
2025 CEGIS Annual Research Meeting
