C5d instances are optimized for compute-intensive workloads that need low-latency, high-speed local NVMe storage delivering cost-effective high performance at a low price per compute ratio. These instances are ideal for high-performance computing (HPC), machine learning, deep inference, distributed analytics, batch processing, and much more. With the new larger 24xlarge and metal sizes, C5d instances now offer 33% more vCPU and memory and 2x more local-NVMe storage unlocking more performance for those compute intensive workloads.
Furthermore, the new C5d bare metal option provides your applications with direct access to the processor and memory resources of the underlying server. Bare metal instances are ideal for workloads that require access to the hardware feature set (such as Intel® VT-x), for applications that need to run in non-virtualized environments for licensing or support requirements, or for customers who wish to use their own hypervisor.
c5d.12xlarge, c5d.24xlarge, and c5d.metal instances are available today in the following AWS regions: US East (Northern Virginia, Ohio), US West (Oregon, Northern California), Asia Pacific (Tokyo, Sydney, Singapore, Seoul), Europe (Ireland, Frankfurt, London, Stockholm), South America (Sao Paulo), Canada (Central), and AWS GovCloud (US-West). C5d instances are now available in 8 sizes, with 2, 4, 8, 16, 36, 48, 72, and 96 vCPUs and are purchasable as On-Demand, Reserved, Spot, and as Dedicated Instances.