In recent years, there has been a growing interest in the development of in vitro models to predict cellular behavior within living organisms. Mathematical models, based on differential equations and associated numerical algorithms, have been employed for this purpose. In this study, we present initial forays into the design of parallel strategies aimed at accelerating an algorithm for behavior prediction, specifically based on the Cellular Potts Model. To do this, we engage the computational power of Graphic Processing Units within the CUDA environment to optimize critical low-level kernels.This work intends to provide a comprehensive analysis of the energy performance of the proposed implementation. Tests and experiments affirm significant performance gains in terms of both processing time and substantial energy savings.
Energy performance profiling of a GPU-based CPM implementation
De Luca P.
;Galletti A.;Marcellino L.
2023-01-01
Abstract
In recent years, there has been a growing interest in the development of in vitro models to predict cellular behavior within living organisms. Mathematical models, based on differential equations and associated numerical algorithms, have been employed for this purpose. In this study, we present initial forays into the design of parallel strategies aimed at accelerating an algorithm for behavior prediction, specifically based on the Cellular Potts Model. To do this, we engage the computational power of Graphic Processing Units within the CUDA environment to optimize critical low-level kernels.This work intends to provide a comprehensive analysis of the energy performance of the proposed implementation. Tests and experiments affirm significant performance gains in terms of both processing time and substantial energy savings.I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.