Optimization Techniques for GPU Programming
In October 2022, after working on it for more than a year, we finally published a survey paper on optimizations techniques for GPU programming. It covers 14 years of development of such optimizations, and we read and analyzed more than 450 papers for this work.
I will leave you here with the abstract and a link to access the paper.
In the past decade, Graphics Processing Units have played an important role in the field of high-performance computing and they still advance new fields such as IoT, autonomous vehicles, and exascale computing. It is therefore important to understand how to extract performance from these processors, something that is not trivial. This survey discusses various optimization techniques found in 450 papers published in the last 14 years. We analyze the optimizations from different perspectives which shows that the various optimizations are highly interrelated, explaining the need for techniques such as auto-tuning.