GLTraceSim

Our new graphics tracing and replay framework allows us to explore system-level effects on heterogeneous CPU+GPU memory systems. By efficiently generating GPU memory access traces for modern graphics applications, GLTraceSim replays them through a high-level cache model, or a detailed simulator (Gem5 extension) to explore effects in bandwidth, cache misses, scheduling and performance. GLTraceSim is built upon publicly-available tools.

GitHub

Publications

• [3] Germán Ceballos, Andreas Sembrant, Trevor E. Carlson, David Black-Schaffer. Behind The Scenes: Memory Analysis of Graphical Workloads on Tile-based GPUs. ISPASS 2018

• [2] Germán Ceballos, Andreas Sembrant, Trevor E. Carlson, David Black-Schaffer. Analyzing Graphical Workloads on Task-Based GPUs. IISWC 2017

• [1] Andreas Sembrant, Trevor E. Carlson, Erik Hagersten, David Black-Schaffer. A Graphics Tracing Framework for Exploring CPU+GPU Memory Systems. IISWC 2017