Google’s Compute Optimized VMs offer the highest consistent performance per core to support real-time application performance. They’re ideal for most performance-intensive workloads. The new AMD-powered C2D instances provide the largest VM sizes within the Compute Optimized VM family. They’re best-suited for memory-bound workloads like high-performance databases, gaming, and high-performance computing (HPC) workloads, such as electronic design automation (EDA) and computational fluid dynamics (CFD). The new instances are configurable with up to 112 vCPUs (56 cores), 896 GB of memory, and 3 TB of Local SSD. C2D is available in standard, high-cpu, and high-mem, each with seven machine types for optimal memory-to-core ratio to better align with your workload. The C2D instances are just the latest example of Google embracing AMD’s EPYC processors. In the last six months, the cloud provider also introduced Milan-powered Tau VMs, which are designed for scale-out workloads, as well as its general purpose N2D instances powered by Milan. In the illustration below, Google shows how the new C2D compares against N2D with 2nd Gen EPYC (formerly code-named “Rome”) chips in compute intensive performance, media transcoding, and gaming benchmarks. The widespread adoption of AMD’s EPYC processor contributed to AMD’s strong 2021 results. The company reported earlier this month that it had record annual revenue and profitability in 2021, thanks in part to data center revenues doubling. Google’s C2D instances are available now in the following regions: us-central1 (Iowa), asia-southeast1 (Singapore), us-east1 (South Carolina), us-east4 (North Virginia), asia-east1 (Taiwan), and europe-west4 (Netherlands).
