Cadence’s computational software heritage enables customers to turn electronic design concepts into reality across a variety of end markets, including hyperscale computing, mobile, and 5G communications. We have successfully run our verification and library characterization products on the AWS Graviton2-based R6g memory optimized instances, delivering compelling price-performance benefits. The new Graviton2-based X2g instances have a much larger memory footprint, which will allow for more efficient runs and enable even more memory-intensive EDA workloads.

SmugMug operates two very large online photo platforms, SmugMug and Flickr, enabling more than 100 million members to safely store, search, share, and sell tens of billions of photos. Last year we were able to transition our caching servers to r6gd.8xlarge instances with a simple recompile and are enjoying a 33% price benefit and improved latency. The large memory footprint of the new X2gd instances allows us to consolidate our caching on instances that closely match our workload, lowering our cost per instance and cost per GB of RAM by an additional 28%.

Synopsys’ customers are increasingly leveraging cloud for scaling and accelerating applications across our portfolio for system-on-chip (SoC) design processes, including verification, library characterization, analog, and digital design implementation flows. Our anchor products, such as Synopsys’ VCS functional verification solution, are optimized to use advances in hardware performance and memory introduced in AWS’s Graviton2-based X2gd instances, enabling our customers to accelerate SoC verification and design.

At Annapurna Labs, we have been running almost all of our chip simulations and verification up till now on Graviton2-based R6g instances. With the new X2gd instances, we are able to double the number of full chip and cluster level simulations for same instance size, allowing us to do twice the output while reduce costs at the same time.

Technology has become ubiquitous in all industries, driving the need for more compute products in less time while simultaneously using fewer resources to keep costs low. The design, verification, and implementation of silicon IP are the most critical phases between idea and a finished product produced in volume, and we have measured a performance uplift of 45% on EDA workloads when running on Arm-based Graviton2-powered X2gd cloud instances compared to previous generation X1 instances.