PC Sampling

Analyzing GPU-accelerated Applications Using HPCToolkit

Using HPCToolkit to Measure and Analyze the Performance of GPU-accelerated Applications Tutorial, Mar-Apr 2021

GPA: A GPU Performance Advisor Based on Instruction Sampling

Presented our CGO'21 work.

GPA

GPA is a performance advisor for NVIDIA GPUs that suggests potential code optimization opportunities at a hierarchy of levels, including individual lines, loops, and functions. GPA uses data flow analysis to approximately attribute measured instruction stalls to their root causes and uses information about a program's structure and the GPU to match inefficiency patterns with suggestions for optimization. GPA estimates each optimization's speedup based on a PC sampling-based performance model.

Tools for Top-down Performance Analysis of GPU-Accelerated Applications

Presented our ICS'20 work.