The NVIDIA® Data Center GPUs give modern data centers the power to accelerate deep learning, machine learning, virtualization and high-performance computing workloads.
A broad array of accelerated workloads, from AI training and inference to supercomputing and virtual desktop infrastructure (VDI) applications, demand diverse classes of servers for optimal performance. NVIDIA GPU-Accelerated Server Platforms defines these server classes by recommending the optimal mix of GPUs, CPUs and interconnects for diverse Training (HGX-T), Inference (HGX-1), and Supercomputing (SCX) applications. A customer can choose the class that most closely matches their workload to identify the ideal server for that workload.
NVIDIA partners offer a wide array of cutting-edge servers capable of diverse AI, HPC and accelerated computing workloads. To promote the optimal server for each workload, NVIDIA has introduced GPU-Accelerated Server Platforms, which recommends ideal classes of servers for various Training (HGX-T),
Inference (HGX-I) and Supercomputing (SCX) applications. Platforms align the entire data center server ecosystem and ensure that, when a customer selects a specific server platform that matches their accelerated computing application, they’ll achieve the industry’s best performance.
Training increasingly complex models faster is key to improving productivity for data scientists and delivering AI services more quickly. Servers powered by NVIDIA® GPUs use the performance of accelerated computing to cut deep learning training time from months to hours or minutes.
Inference is where a trained neural network really goes to work. As new data points come in such as images, speech, visual and video search, inference is what gives the answers and recommendations at the heart of many AI services. A server with a single GPU can deliver 27X higher inference throughput than a single-socket CPU-only server resulting in dramatic cost savings.
NVIDIA GPUs are the engine of the modern HPC data center, delivering breakthrough performance with fewer servers resulting in faster insights and dramatically lower costs. Over 600 HPC applications in a broad range of domains are optimized for GPUs, including all 15 of the top 15 HPC applications and every major deep learning framework.
NVIDIA virtual GPU (vGPU) solutions bring the power of NVIDIA GPUs to virtual desktops, apps and workstations, accelerating graphics and compute to make virtualized workspaces accessible to creative and technical professionals working from home offices or anywhere.