Evaluation of Emerging Energy-Efficient Heterogeneous Computing Platforms for Biomolecular and Cellular Simulation Workloads

Abstract

Many of the continuing scientific advances achieved through computational biology are predicated on the availability of ongoing increases in computational power required for detailed simulation and analysis of cellular processes on biologically-relevant timescales. A critical challenge facing the development of future exascale supercomputer systems is the development of new computing hardware and associated scientific applications that dramatically improve upon the energy efficiency of existing solutions, while providing increased simulation, analysis, and visualization performance. Mobile computing platforms have recently become powerful enough to support interactive molecular visualization tasks that were previously only possible on laptops and workstations, creating future opportunities for their convenient use for meetings, remote collaboration, and as head mounted displays for immersive stereoscopic viewing. We describe early experiences adapting several biomolecular simulation and analysis applications for emerging heterogeneous computing platforms that combine power-efficient system-on-chip multi-core CPUs with high-performance massively parallel GPUs. We present low-cost power monitoring instrumentation that provides sufficient temporal resolution to evaluate the power consumption of individual CPU algorithms and GPU kernels. We compare the performance and energy efficiency of scientific applications running on emerging platforms with results obtained on traditional platforms, identify hardware and algorithmic performance bottlenecks that affect the usability of these platforms, and describe avenues for improving both the hardware and applications in pursuit of the needs of molecular modeling tasks on mobile devices and future exascale computers.

Immersive Molecular Visualization with Omnidirectional Stereoscopic Ray Tracing and Remote Rendering

“…We have outlined opportunities for future work that could positively impact our approach. An exciting opportunity for future development lies in multiuser collaborative visualization, and support for mobile phone-based HMDs as self-contained clients [54]. We feel our approach is general and that it could be used by many other domains within science and engineering.…”

Recent Advances in Coarse-Grained Models for Biomolecules and Their Applications

“…Therefore, simulation of an inherently large biological system at a biologically relevant time scale has very high computational cost. To address this issue, nowadays graphics processing unit (GPU)-enabled simulations are being run at less cost in terms of time [23]. For instance, the DHFR system consisting of 23,558 atoms when simulated over a single NVIDIA GTX-TITAN GPU card achieved a maximum speed of 110.65 ns/day [24].…”

Adanmış ve Gömülü GPU Sistemlerinin Kapsamlı Performans Karşılaştırması

“…After the release of Jetson TX1, the second generation of Jetson cards, it also gained popularity among researchers. [11] uses both Jetson TK1 and Jetson TX1 for comparing the performance and energyefficiency of five different heterogeneous computing platforms for bio-molecular and cellular simulation workloads. [12] evaluates the effectiveness of Jetson TX1 in real-time computer vision workloads.…”