Cloud architecture - Using Ellexus Breeze for EDA Workload Migration to AWS

Cloud architecture

While the lift and shift approach can get you started on AWS quickly, making small changes to workflows allows you to advantage of native AWS services, resulting in cost reduction and getting results quicker. In this case, the workflow is straightforward and Breeze identifies which scripts need to be updated when migrating to AWS.

We have chosen an Amazon EC2 z1d instance. z1d instances deliver high single thread performance due to a custom Intel Xeon Scalable processor with a sustained all-core frequency of up to 4.0 GHz—the fastest of any cloud instance at this time. The z1d provides both high compute performance and a large amount of memory, which is ideal for EDA workflows. Additionally, the z1d instance has an Amazon EC2 instance store, which are local NVMe SSD drives local to the instance. The z1d instance fulfills our CPU and storage requirements, and we can adjust the configuration later to optimize for cost and performance.

The project and workflow have been packaged and stored in Amazon S3. This is a cost-effective way of storing large amounts of project data. When migrating this EDA tool to AWS, a new workflow was configured that pulls the project data from Amazon S3 and then runs the workflow using a local instance store.