Introducing Amazon EC2 P3dn Instances, Our Most Powerful GPU Instance Yet

Today, we are announcing that Amazon EC2 P3dn.24xlarge GPU instances, the latest addition to the P3 instance family are generally available. With up to 4x the network bandwidth of P3.16xlarge instances, P3dn.24xlarge instances are optimized for distributed machine learning and HPC applications. These new instances provide up to 100 Gbps of networking throughput, 96 custom Intel®Xeon® Scalable (Skylake) vCPUs, 8 NVIDIA® V100 Tensor Core GPUs with 32 GB of memory each, 300 GB/s NVLINK GPU interconnect, and 1.8 TB of local NVMe-based SSD storage.

The faster networking, new processors with additional vCPUs, doubling of GPU memory, and fast local instance storage enable developers to not only optimize performance on a single instance but also significantly lower the time to train their ML models or run more HPC simulations by scaling out their jobs across several instances (e.g., 16, 32 or 64 instances).

AWS is the first cloud provider to deliver 100 Gbps of networking throughput which helps remove data transfer bottlenecks and optimizes the utilization of GPUs to deliver maximum instance performance. In addition, the doubling of GPU memory from 16 GB to 32 GB per GPU provides the flexibility to train more advanced and larger machine learning models as well as process larger batches of data such as 4k images for image classification and object detection systems.

Below is a comparison of how P3dn.24xlarge instances compare to existing P3 instances.

P3dn.24xlarge instances are available in the US East (N. Virginia) and US West (Oregon) AWS regions as On-Demand, Reserved, or Spot Instances. To learn more about P3 instances and how they are being used by customers such as Airbnb, Salesforce, and Western Digital, visit the P3 page.