Amazon EC2 Elastic GPUs allow you to easily attach low-cost graphics acceleration to current generation EC2 instances. With Elastic GPUs, you choose the GPU resources that are sized for your workload, so you can accelerate the graphics performance of your applications for a fraction of the cost of stand-alone graphics instances. Elastic GPUs are ideal If you need a small amount of GPU for graphics acceleration, or have applications that could benefit from some GPU, but also require high amounts of compute, memory, or storage.
Elastic GPUs make it easy to attach graphics acceleration to existing Amazon EC2 instance types in much the same way as attaching Amazon EBS volumes. With Amazon EC2 Elastic GPUs, you can configure the right amount of graphics acceleration to your particular workload without being constrained by fixed hardware configurations and limited GPU selection. Amazon EC2 Elastic GPUs plan to support OpenGL and offer up to 8GB of GPU memory, making them ideally suited for any workload that needs a small amount of additional GPU such as virtual desktops, gaming, industrial design, or HPC visualization.
Workstation-Class Graphics Performance
Elastic GPUs are capable of running a variety of graphics workloads, such as 3D modeling and rendering, with similar workstation performance compared to direct-attached GPUs.
Optimized Performance and Cost
Elastic GPUs come in multiple frame buffer sizes up to 8GB, allowing you to achieve the optimal graphics performance for your workload for the lowest possible cost.
Elastic GPUs plan to support Open Graphics Library (OpenGL), a cross-language, cross-platform API for rendering 2D and 3D vector graphics, with a roadmap for certification of additional APIs.
|If you have…||For applications such as…||Consider using|
|An application with high compute, storage or memory needs that still could benefit from additional GPU||Virtual desktops, gaming, industrial design, HPC visualization or 3D modeling and rendering,and 3D Application Streaming.||Elastic GPUs for fractional GPUs and G2 Instances for full GPUs|
|A general-purpose compute applications that requires a GPU||Machine learning, high performance databases, computational fluid dynamics, computational finance, seismic analysis, molecular modeling, and genomics.||Amazon EC2 P2 Instances|
AWS now offers a Graphics Certification Program for software vendors and developers to help make sure that their applications take full advantage of Elastic GPUs and our other GPU-based offerings. To accelerate availability of the applications being certified, the program is supported with AWS credits and co-marketing funds for qualifying applications.