Issue link: https://read.uberflip.com/i/1187300
Amazon Web Services – HPC Lens AWS Well-Architected Framework Page 6 the entire time-to-solution into account, including non-compute aspects such as provisioning resources, staging data, or time spent in job queues. Scenarios HPC cases are typically complex computational problems that require parallel- processing techniques. To support the calculations, a well-architected HPC infrastructure is capable of sustained performance for the duration of the calculations. HPC is used in a wide range of areas, from Bioscience to Geoscience, Manufacturing, Electronic Design Automation, Climate Simulation, Finance, Media and Entertainment, and so on. Still, the grids or HPC clusters that support these calculations are remarkably similar to each other, with select cluster attributes optimized for the specific workload. In the cloud, the network, storage type, compute (instance) type, and even deployment method can be strategically chosen to optimize performance, cost, and usability for a particular use case or application. HPC is generally divided into two categories based on the degree of interaction between the concurrently running parallel processes. Loosely coupled HPC cases are those where the multiple or parallel processes don't strongly interact with each other in the course of the entire simulation. We refer to these loosely coupled calculations as high-throughput computing or HTC. Conversely, tightly coupled HPC cases are those where the parallel processes are simultaneously running and regularly exchanging information between each other at each iteration or step of the simulation. Tightly coupled cases are often simply referred to as HPC cases. With HTC, each parallel process is called an "iteration" of one simulation. The completion of an entire calculation or simulation often requires hundreds to millions of iterations (or more). The iterations typically occur in any order and at any speed, along the way to completion of the entire simulation. This offers flexibility on the computing infrastructure required for these simulations. Unlike with HTC, the HPC processes are "tightly coupled," meaning that information is exchanged regularly between the processes at each iteration or step of the simulation. Typically, the simulation runs on a homogenous cluster, with each process pinned to one core. The total core or processor count can range from tens, to hundreds, to thousands, and occasionally to hundreds of thousands if the infrastructure allows. The interactions of the processes during