NVIDIA announced that Facebook will power its next-generation computing system. Facebook will use Tesla based accelerated platform. It will drive a broad range of machine learning applications.
Real-time speech translation, Autonomous robots, Detection of human emotions through facial analysis are the machine learning applications. But it takes a large amount of computing performance to train the sophisticated deep neural networks that power these new applications.
Neural networks are the part of AI system. To understand complex neural network, even the fastest computer will take days or weeks. But Nvidia Tesla based GPU will do this 10-20 times faster than the Fastest Computer.
Facebook is the first company to adopt NVIDIA Tesla M40 GPU accelerators. These accelerators will play a key role in the new “Big Sur” Computing platform. This computing platform designed especially for neural network training. Deep learning play an important role in neural network training. It is enabled by big data and powerful GPUs.
Facebook’s Big Sur Computing platform is optimized for Machine Learning. It delivers maximum performance for machine learning workloads. It also includes the training of large neural networks across multiple Tesla GPUs. The addition of Tesla M40 GPUs will help Facebook make new advancements in machine learning research. It enable teams across its organization to use deep neural networks in a variety of products and services.
Nvidia Tesla M40 Accelerator consist of 3072 CUDA cores. It is having 12 GB of Video memory and memory bandwidth is 288 GB/s. The single precision floating point performance is 7 Tera Flops.
First Open Sourced AI Computing Architecture
“Big Sur” represents the first time a computing system specifically designed for machine learning and artificial intelligence (AI) research will be released as an open source solution. Committed to doing its AI work in the open and sharing its findings with the community, Facebook intends to work with its partners to open source Big Sur specifications via the Open Compute Project. This unique approach will make it easier for AI researchers worldwide to share and improve techniques, enabling future innovation in machine learning by harnessing the power of GPU accelerated computing.
Advances in Machine Learning Powered by NVIDIA Deep Learning SDK
Software kit for machine learning is NVIDIA’s Deep Learning SDK. It a suite of powerful tools and libraries that give data scientists and researchers the building blocks for training and deploying deep neural nets.
It includes DIGITS, NVIDIA’s Deep Learning GPU Training System. This lets data scientists and researchers quickly design the best deep neural network based on their data using real-time network behavior visualization. All without requiring them to write any code.