ECHELON software is the only reservoir simulator developed from inception for GPUs, and the new era of massively parallel computing.
Licensing informationSome of the key features of our reservoir simulation software.
Use ECHELON's speed and scalability to change how you work.
The demand for ultra-fast, scalable reservoir simulation software continues to press forward with higher stakes from deep-ocean drilling, the increasing complexity of unconventional reservoirs, the increased computational requirements of ensemble methodologies, and an overarching desire for a more detailed subsurface description. Massively parallel GPU hardware, modern solver algorithms, and careful implementation are combined in ECHELON software to allow scalable simulation up to billions of cells. This is all accomplished at speeds that enable the practical simulation of hundreds of ensemble realizations of large complex models, all while using far fewer hardware resources than CPU based solutions. Reservoir engineers can develop more accurate, robust and predictive models when the time required for each iteration cycle is reduced by an order of magnitude or more.
FAQ about ECHELON→Higher stakes from deep-ocean drilling, increasing complexity from unconventional reservoirs, and an overarching desire for a higher-fidelity subsurface description have led to a demand for reservoir simulators capable of modeling many millions of cells in minutes. ECHELON software easily scales to handle large models while still maintaining it's exceptional performance. Models as large as 1 billion cells have been simulated on as few as 30 nodes in 92 minutes. Higher resolution geo-models offer greater detail and obviate the cumbersome and heuristic upscaling process. They can capture finer geologic detail and allow engineers more accurate, robust and predictive models, leading to better investment decisions.
Request more info →ECHELON software's ability to simulate up to 12 million active cells on a single GPU means that large geo-scale models are divided into fewer and larger computational domains compared to modern CPU based simulators. For example our billion cell calculation split the model over 120 domains mapped to 120 GPUs. Multi-core CPU codes that have been able to run billion cell models do it using thousands of nodes and thus create tens of thousands of domains to map to individual cores. This splintering of the model into huge numbers of domains leads to inefficiencies related to inter-domain data communication. ECHELON ends up using about two orders of magnitude fewer domains than its multi-core competitors for the same calculation.
Schedule a demo →Choose one of our licensing options to fit your needs and budget.
Get answers to some of our most frequently asked questions, or get in touch.
View our FAQ