Compute Optimized

Compute optimized instance type is suitable for computing-intensive applications that utilize processors. This instance can be used for batch processing workloads, media transcoding, high-performance web servers, high-performance computing (HPC), scientific modeling, dedicated game servers and ad server engines, machine learning inference, and other computing-intensive applications.

Applicable type: c2a

c2a

c2a instance is powered by the 3rd generation AMD EPYC 7003 series processors and are designed for computing-intensive workloads.

Hardware specifications

Up to 3.6GHz 3rd generation AMD EPYC processor (AMD EPYC 7643)
Up to 25Gbps network bandwidth
Instance sizes supporting up to 96 vCPUs and 192GiB memory
A 2:1 Memory to vCPU ratio across all sizes
Support for AMD instruction sets (AVX, AVX2)

Details

Instance size	vCPU	Memory (GiB)	Network bandwidth (Gbps)
`c2a.large`	2	4	Up to 10
`c2a.xlarge`	4	8	Up to 10
`c2a.2xlarge`	8	16	Up to 10
`c2a.4xlarge`	16	32	Up to 10
`c2a.8xlarge`	32	64	Up to 10
`c2a.12xlarge`	48	96	12.5
`c2a.16xlarge`	64	128	12.5
`c2a.24xlarge`	96	192	25

NUMA topology

Non-Uniform Memory Access (NUMA) architecture allows each CPU to access its own allocated memory (local memory). Using NUMA architecture can enable high scalability as it allows multiple processors to share memory.

c2a instance has the following NUMA topology depending on the instance size.