@inbook{106196b146b64a4a9070bb9bfaed74fe,
title = "Targeting atmospheric simulation algorithms for large, distributed-memory, GPU-accelerated computers",
abstract = "Computing platforms are increasingly moving to accelerated architectures, and here we deal particularly with GPUs. In Norman et al. (2011), a method was developed for atmospheric simulation to improve efficiency on large, distributed-memory machines by reducing communication demand and increasing the time step. Here, we improve upon this method to further target GPU-accelerated platforms by reducing GPU memory accesses, removing a synchronization point, and clustering computations. The modified code ran more than two times faster than the original in some cases even though more computations were required, demonstrating the importance of improving memory handling on the GPU. Furthermore, we discovered that the modification also has a near 100 % hit rate in fast, on-chip L1 cache and discuss the reasons for this. Finally, we remark on further potential improvements to GPU efficiency.",
author = "Norman, {Matthew R.}",
note = "Publisher Copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 2013.",
year = "2013",
doi = "10.1007/978-3-642-16405-7_17",
language = "English",
series = "Lecture Notes in Earth System Sciences",
publisher = "Springer International Publishing",
number = "9783642164040",
pages = "271--282",
booktitle = "Lecture Notes in Earth System Sciences",
edition = "9783642164040",
}