--> High-Performance Reservoir Simulations on Modern CPU-GPU Computational Platforms

2018 AAPG International Conference and Exhibition

Datapages, Inc.Print this page

High-Performance Reservoir Simulations on Modern CPU-GPU Computational Platforms

Abstract

Objective and Scope: For modern day reservoir simulators, it is essential to provide realistic physical description of reservoirs, fluids and hydrocarbon extraction technology and guarantee excellent performance and parallel scalability. In the past, the advances in simulation performance were largely limited by memory throughput of CPU based computer systems. Recently, new generation of graphical processing units (GPU) became available for general purpose computing with the support of double precision floating point operations, necessary for dynamic reservoir simulations. The graphic cards currently available on the market have 1000s of computational cores that can be efficiently utilized for simulations. To the best of our knowledge, the hybrid approach proposed in this paper has not been applied in the reservoir simulators before, despite it seems to provide the optimal solution from the price/performance point of view. In this paper, for the first time, we present results of running full physics reservoir simulator on CPU+GPU platform and discuss implications of this new technology on the existing reservoir simulation workflows. Methods, Procedures, Process: We discuss challenges and developed solutions for running reservoir simulations using modern CPU+GPU hardware architecture. We propose a methodology to distribute the workload between different parts efficiently. The approach is tested on several data sets typical for Russian fields on various computational platforms, such as personal computers and clusters with and without GPU’s involved. Results, Observations, Conclusions: The technology proposed in this paper demonstrates multifold speed up for models with large number of active grid blocks. The speed up due to GPU utilization can in some cases reach as high as 3-4 times compared to the traditional GPU-based approach. Taking into account the recent progress in the GPU development, this factor is expected to grow in the near future, and the hybrid CPU+GPU based approach allows to utilize the great potential of the hardware evolution. The results, advances and potential bottlenecks combined with analysis of the performance and the ‘value for money’ of the modern hardware solutions are discussed in this work.