- author = "Jhe-Yu Liou and Muaaz Awan and Kirtus Leyba and Petr Sulc and Steven Hofmeyr and Carole-Jean Wu and Stephanie Forrest",
- title = "Evolving to find optimizations humans miss: using evolutionary computation to improve {GPU} code for bioinformatics applications",
- journal = "ACM Transactions on Evolutionary Learning and Optimization",
- year = "2024",
- volume = "4",
- number = "4",
- articleno = "21",
- month = dec,
- keywords = "genetic algorithms, genetic programming, Genetic improvement, GPU, Evolutionary programming, Bioinformatics, GEVO, ADEPT, SIMCoV, Coronavirus, oxDNA, LLVM-IR, nvidia P100 1080Ti V100, NERSC Cori Supercomputer, CUDA 11.4",
- ISSN = "2688-299X",
- publisher = "Association for Computing Machinery",
-
URL = "
https://doi.org/10.1145/3703920",
-
DOI = "
doi:10.1145/3703920",
- size = "28 pages",
-
abstract = "GPUs are used in many settings to accelerate
large-scale scientific computation, including
simulation, computational biology, and molecular
dynamics. However, optimizing codes to run efficiently
on GPUs requires developers to have both detailed
understanding of the application logic and significant
knowledge of parallel programming and GPU
architectures. This paper shows that an automated GPU
program optimization tool, GEVO, can leverage
evolutionary computation to find code edits that reduce
the runtime of three important applications, multiple
sequence alignment, agent-based simulation and
molecular dynamics codes, by 28.9%, 29%, and 17.8%
respectively.
The paper presents an in-depth analysis of the discovered optimizations, revealing that (1) several of the most important optimizations involve significant epistasis, (2) the primary sources of improvement are application-specific, and (3) many of the optimizations generalize across GPU architectures. In general, the discovered optimizations are not straightforward even for a GPU human expert, showcasing the potential of automated program optimization tools to both reduce the optimization burden for human domain experts and provide new insights for GPU experts.",
- notes = "https://dlnext.acm.org/journal/telo",
