“Why Use GPU Accelerators?" is the second workshop in this series and was presented by Daniel Howard of CISL's Consulting Services Group on February 20th, 2022. The video recording for this session has been uploaded here. Topics covered include:
- Brief history of GPU/accelerator architecture development
- Trends in CPU and GPU performance
- Power consumption, acceleration, availability
- Flynn’s Taxonomy - SIMD vs. SMT vs. SIMT
- Comparing ease of programmability and evaluating GPU software paradigms
- Steps to begin a GPU project or refactoring initiative