H3C Boosts Development of Heterogeneous Computing with NVIDIA – HPCwire

May 22, 2020 NVIDIA has recently announced the NVIDIA A100 Tensor Core GPU based on the NVIDIA Ampere architecture. This is NVIDIAs first elastic, multi-instance GPU that unifies data analytics, AI training, inference and HPC. The H3C UniServer servers will incorporate this brand-new NVIDIA A100 GPU to provide higher computing power for high-performance computing and AI.

Deployed for a wide range of applications including AI, data analysis and HPC, NVIDIA A100 Tensor Core GPUs help customers address computing challenges with its outstanding acceleration and versatility. Its performance in AI training and inference is significantly enhanced over the previous generation. As the engine of NVIDIA data center platform, NVIDIA A100 GPUs can be efficiently scaled up by the thousands for large-scale deployments, or each can be partitioned into seven separate GPU instances with the new multi-instance GPU technology to accelerate workloads of all sizes.

The powerful trends of cloud computing and AI are driving a tectonic shift in data center designs so that what was once a sea of CPU-only servers is now GPU-accelerated computing, said Jensen Huang, founder and CEO of NVIDIA. NVIDIA A100 GPU is a 20x AI performance leap and an end-to-end machine learning accelerator from data analytics to training to inference. For the first time, scale-up and scale-out workloads can be accelerated on one platform. NVIDIA A100 will simultaneously boost throughput and drive down the cost of data centers.

As a leader in digital solutions, H3C is always pioneering technology and product development. H3C has been intensively developing data analysis, machine learning, AI and other technologies. Deploying NVIDIA A100 GPUs in H3C UniServer servers empowers the application of GPU products in AI and helps customers to build the future of intelligence.

At Navigate 2020 launched this April, H3C announced its AI in ALL intelligence strategy. The strategy is designed to create smarter products and solutions through Smart Digital Platforms and empower customers with more intelligent businesses and operations by enabling smart applications.

With a focus on heterogeneous computing, H3C has launched GPU-scenario solutions, built the GPU server clusters based on the GPU servers for AI such as H3C UniServer R5300 G3, and launched independently-developed AI platform AIOS. These products and services will hence boost the industrial integration of AI and accelerate digital transformation for enterprises to embrace the Intelligence Era.

About H3C

H3C is an industry leader in the provision of Digital Solutions, and is committed to becoming the most trusted partner of our customers in their quest for business innovation and digital transformation. H3C offers a full portfolio of Digital Infrastructure products, spanning across compute, storage, networking, security and related domains, and provide a comprehensive one-stop digital platform that includes cloud computing, big data, artificial intelligence (AI), intelligent connectivity, 5G solutions, information security, new safety, Internet of Things (IoT) and edge computing, as well as end-to-end technical services. H3C is also the exclusive provider of HPEservers, storage and associated technical services in China.

Source: H3C

View original post here:

H3C Boosts Development of Heterogeneous Computing with NVIDIA - HPCwire