GPU-Accelerated Web Services

Millions of people now share photos, video, and music or spoken words on the web daily. GPU powered micro services can process this data quickly to deliver great visual experiences and intelligent capabilities based on deep learning.

Image Compute Engine (ICE)

We interact with our digital lives through an increasingly diverse set of devices from watches to various kinds of phones and tablets to laptops and desktops. Regardless of how we connect, as consumers of digital information we expect to have an experience that is beautiful, smooth and responsive on whatever screen we happen to be using. Satisfying these expectations with low-latency is a challenge for both web sites and mobile applications. The NVIDIA Image Compute Engine (ICE) delivers the power of GPU-accelerated image processing to cloud-based web and mobile services. Learn how ICE makes on-demand image resizing feasible for rich visual services.


The NVIDIA GPU REST Engine (GRE) is a critical component for developers building low-latency web services. GRE includes a multi-threaded HTTP server that presents a RESTful web service and schedules requests efficiently across multiple NVIDIA GPUs. The overall response time depends on how much processing you need to do, but GRE itself adds very little overhead and can process null-requests in as little as 10 microseconds.