AWS has developed leading cloud computing services which are tailor-made for demanding HPC workloads. By selecting the right combination of cloud-based compute and storage resources, customers can meet the demands of the most challenging HPC applications. AWS provides an elastic and scalable cloud infrastructure, powerful orchestration tools and advanced services to make it easy to quickly deploy and operate a sophisticated cloud based HPC system.
With Amazon EC2, you can choose from a broad range of compute instances allowing you to match the optimal instance with your particular workload’s characteristics. You can then combine this with high performance storage and networking options built specifically for HPC workloads. This means engineers, researchers, and HPC system owners can innovate beyond the limitations of on-premises HPC infrastructure, enabling scale out applications to run without limits. Workloads from many different fields of science and industry run on AWS, including HPC applications such as genomics, computational chemistry, financial risk modelling, computer aided engineering, weather prediction, and seismic imaging, as well as emerging technologies such as quantum computing and machine and artificial intelligence/ deep learning workloads.
AWS can provide a greater ROI and lower Total Cost of Ownership (TCO) when compared to operating a fixed infrastructure acquired through a capital purchase. You can easily size your HPC to meet changing demands without having to operate a fixed infrastructure sized for a workload peak. As an example, a spike in compute demands at the end of the working day, as found with investment banking risk workloads
Read this whitepaper to learn what makes AWS the best place to run HPC industry specific workloads across verticals such as financial services, life sciences, autonomous vehicles, oil and gas, electronic design automation and manufacturing.