Tuning GPU applications is a very challenging task as any source-code optimization can sensibly impact performance, power, and energy consumption of the GPU device. Such an impact also depends on the GPU on which the application is run. This paper presents a suite of microbenchmarks that provides the actual characteristics of specific GPU device components (e.g., arithmetic instruction units, memories, etc.) in terms of throughput, power, and energy consumption. It shows how the suite can be combined to standard profiler information to efficiently drive the application tuning by considering the three design constraints (power, performance, energy consumption) and the characteristics of the target GPU device.
|Titolo:||Power-aware Performance Tuning of GPU Applications Through Microbenchmarking|
|Data di pubblicazione:||2017|
|Appare nelle tipologie:||04.01 Contributo in atti di convegno|