Presentation
SIGN IN TO VIEW THIS PRESENTATION Sign In
Scalable Tuning of (OpenMP) GPU Applications via Kernel Record and Replay
DescriptionHPC is a heterogeneous world in which host and device code are interleaved throughout the application. Given the significant performance advantage of accelerators, device code execution time is becoming the new bottleneck. Tuning the accelerated parts is consequently highly desirable but often impractical due to the large overall application runtime which includes unrelated host parts.
We propose a Record-Replay (RR) mechanism to facilitate auto-tuning of large (OpenMP) offload applications. RR dissects the application, effectively isolating GPU kernels into independent executables. These comparatively small code-lets are amenable to various forms of post-processing, including elaborate auto-tuning. By eliminating the resource requirements and application dependencies, massively parallel and distributed auto-tuning becomes feasible.
Using RR, we run scalable Bayesian Optimization to determine optimal kernel launch parameters. LULESH showcases an end-to-end speedup of up to 1.53x, while RR enables 102x faster tuning compared to existing approaches using the entire application.
We propose a Record-Replay (RR) mechanism to facilitate auto-tuning of large (OpenMP) offload applications. RR dissects the application, effectively isolating GPU kernels into independent executables. These comparatively small code-lets are amenable to various forms of post-processing, including elaborate auto-tuning. By eliminating the resource requirements and application dependencies, massively parallel and distributed auto-tuning becomes feasible.
Using RR, we run scalable Bayesian Optimization to determine optimal kernel launch parameters. LULESH showcases an end-to-end speedup of up to 1.53x, while RR enables 102x faster tuning compared to existing approaches using the entire application.
Event Type
Paper
TimeTuesday, 14 November 20233:30pm - 4pm MST
Location401-402
Accelerators
Distributed Computing
Middleware and System Software
Performance Measurement, Modeling, and Tools
Post-Moore Computing
TP
Best Paper Finalist
