NVIDIA sets 6 AI performance records for deep learning workloads

Computer chip manufacturer NVIDIA on Monday said it has achieved six Artificial Intelligence (AI) performance records with the release of industry’s first broad set of AI benchmarks.

Backed by Google, Intel, Baidu, NVIDIA and several more technology leaders, the new “MLPerf” benchmark suite measures a wide range of deep learning workloads, covering areas as computer vision, language translation, personalised recommendations and reinforcement learning tasks, the chip-maker said in a statement.

The “MLPerf” effort aims to build a common set of benchmarks that enables the machine learning (ML) field to measure system performance for both training and inference from mobile devices to cloud services.

The NVIDIA AI can help developers at every stage of development. There are aimed at helping data scientists, workgroups, enterprises and organisations building on-premise AI infrastructure.

NVIDIA achieved the best performance in the six “MLPerf” benchmarks that cover a variety of workloads and infrastructure scale — ranging from 16 GPUs on one node to up to 640 GPUs across 80 nodes.

“The new MLPerf benchmarks demonstrate the unmatched performance and versatility of NVIDIA’s Tensor Core GPUs,” said Ian Buck, Vice President and General Manager of Accelerated Computing at NVIDIA.

“Exceptionally affordable and available in every geography from every cloud service provider and every computer maker, our Tensor Core GPUs are helping developers around the world advance AI at every stage of development,” he added.

The software innovations and optimisations used to achieve NVIDIA’s “MLPerf” performance records are available free of charge in its latest NGC deep learning containers, said the company.

Leave a Reply

Your email address will not be published. Required fields are marked *