NVIDIA Fuses HPC and AI into Unified Computing Architecture with Launch of HGX-2

At GTC Taiwan today NVIDIA introduced HGX-2, a unified computing platform for both artificial intelligence and high performance computing.

According to NVIDIA, the HGX-2 cloud server platform provides unique flexibility to support the future of computing, enabling high-precision calculations using FP64 and FP32 for scientific computing and simulations, while also providing FP16 and Int8 for AI training and inference. The result is a level of versatility that meets the requirements of the growing number of applications that combine HPC with AI, according to the company.

HGX-2 is a part of the larger family of NVIDIA GPU-Accelerated Server Platforms, an ecosystem of qualified server classes addressing a broad array of AI, HPC, and accelerated computing workloads.

Supported by major server manufacturers, the platforms align with the data center server ecosystem by offering a mix of GPUs, CPUs, and interconnects for diverse training (HGX-T2), inference (HGX-I2) and supercomputing (SCX) applications. Customers are able to choose a specific server platform to match their accelerated computing workload mix and achieve best-in-class performance.

CPU scaling has slowed while computing demand is “skyrocketing,” said Jensen Huang, founder and chief executive officer of NVIDIA. The HGX-2 with Tensor Core GPUs gives the industry a computing platform that fuses HPC and AI “to solve the world’s grand challenges,” he added.

HGX-2 has achieved record AI training speeds of 15,500 images per second on the ResNet-50 training benchmark, and can replace up to 300 CPU-only servers. According to NVIDIA, the HGX-2  incorporates features such as the NVIDIA NVSwitch interconnect fabric, which seamlessly links 16 NVIDIA Tesla V100 Tensor Core GPUs to work as a single GPU delivering two petaflops of AI performance. The first system built using HGX-2 was the recently announced NVIDIA DGX-2.

A number of leading computer makers today shared plans to bring to market systems based on the NVIDIA HGX-2 platform

Four server makers—Lenovo, QCT, Supermicro, and Wiwynn—have announced plans to bring their own HGX-2-based systems to market later this year.

Additionally, four original design manufacturers (ODMs)—Foxconn, Inventec, Quanta, and Wistron—are designing HGX-2-based systems, also expected later this year, for use in large cloud data centers.

More information is available at