Taipei, Taiwan, 27th May 2019 - GIGABYTE is today proud to be a launch partner of NVIDIA EGX, an accelerated computing platform that enables companies to perform low-latency AI computing at the edge. GIGABYTE’s G191-H44 server equipped with NVIDIA T4 GPUs is one the first NVIDIA EGX computing platform's partner systems to be announced worldwide.
▲ GIGABYTE G191-H44
The rapid proliferation of Internet of Things (IoT) devices is creating an explosion in the volume of data. By 2025, it is predicted that there will be over 150 billion machine sensors and other connected IoT devices streaming continuous data that will need to be processed1. AI at the edge will enable organizations to use these massive amounts of data to create smart retail, healthcare, manufacturing, transportation, and cities to provide engaging customer experiences.
1IDC White Paper sponsored by Seagate: Data Age 2025: The Digitization of the World from Edge to Core, November 2018.
To enable companies to quickly and securely deploy AI at the edge, NVIDIA has introduced the EGX platform, featuring an ecosystem of partner systems optimized for AI and machine learning workloads, and which includes GIGABYTE’s G191-H44 GPU accelerated server integrated with NVIDIA AI technologies.
One of the greatest challenges with deploying out of the edge is IT management – including edge server operating system installation, Kubernetes deployment, and device provisioning and updating. The EGX platform streamlines this entire process by providing a hardened software stack that makes production extremely turnkey for enterprises, integrating NVIDIA Edge Stack together with Red Hat’s OpenShift, the leading enterprise-grade Kubernetes orchestration platform. NVIDIA Edge Stack is an optimized software stack that includes NVIDIA drivers, a CUDA Kubernetes plug-in, a CUDA Docker container runtime, CUDA-X libraries and containerized AI frameworks and applications, including TensorRT, TensorRT Inference Server and DeepStream.
▲ NVIDIA TESLA T4 GPU CARD
GIGABYTE is an industry leader in GPU accelerated servers, delivering systems with the highest GPU density combined with excellent cooling performance, power efficiency and deployment flexibility. The G191-H44 is a 1U server that offers many advantages common to GIGABYTE’s G-Series Product Family, including an airflow optimized design, large thermal envelope and superior expansion flexibility. As an NVIDIA EGX platform partner system validated as NVIDIA NGC-Ready, the G191-H44 has been designed to accommodate 4 x NVIDIA Tesla® T4 accelerators to deliver an “on-premises AI-cloud in a box”, ideal to be deployed as an edge server or as part of an edge micro data center. The G191-H44 can also be combined with NVIDIA’s Tesla® V100 Tensor Core accelerators for a centralized data center AI computing platform.
Get started today deploying real-time AI at the edge with GIGABYTE’s G191-H44, an NVIDIA EGX platform system, which will be showcased together with other solutions for AI & cloud computing, 5G networking, software defined storage and liquid cooling in our booth at COMPUTEX 2019.
GIGABYTE @ COMPUTEX 2019
Location: Booth S0512, 4th Floor, Nangang Exhibition Center Hall 2
Date: Tuesday 28th May ~ Saturday 1st June
For more information about GIGABYTE's G191-H44 NVIDIA EGX Platform, please email us directly at server.grp [at] gigabyte.com