Amazon announced the general availability of new Amazon EC2 P5en instances. Powered by NVIDIA H200 Tensor Core GPUs and custom 4th generation Intel Xeon Scalable processors, these instances deliver superior performance for workloads like deep learning, generative AI, and high-performance computing (HPC). P5en boasts a 50% increase in memory bandwidth, up to 3200 Gbps network bandwidth with EFAv3, and up to four times higher throughput between CPU and GPU. This results in improved latency and more efficient scaling for distributed training workloads. P5en instances also offer up to 30 TB of local NVMe SSD storage and up to 25% higher Amazon EBS bandwidth. They are available in US East (Ohio), US West (Oregon), and Asia Pacific (Tokyo) AWS Regions through EC2 Capacity Blocks for ML, On Demand, and Savings Plan purchase options.