Poster Type: Research Posters
Author: Tavin Mistry (Queen's University Canada), Tobias Salamon (Queen's University Canada), Matthew Tindale (Queen's University Canada), Ian Karlin (Queen's University Belfast)
Abstract: The high performance computing (HPC) industry is moving past an era in which each new generation of devices provided uniform performance improvements across all workloads. In this work, we profile a diverse suite of applications across multiple generations of NVIDIA HPC GPUs to evaluate how architectural design decisions translate into real-world application performance, in terms of speedup and energy efficiency. The suite of applications was hand-picked to represent the modern HPC landscape; it covers scientific computing, AI inference, AI training, and targeted microbenchmarks. GPU-level performance counters, execution time, power, and energy measurements were collected and analyzed to identify which architectural improvements provide the greatest benefit, which are less impactful, and what workload characteristics determine their effectiveness. Relative to the increase in transistor count, the data exhibits significant performance gains among Tensor Core bound applications, expected gains in memory-bound applications and below-expected gains in vector throughput-bound applications.
Best Poster Finalist (BP): no
Poster: PDF
Poster Summary: PDF