DGX 1 is the world's first deep learning super computer in a box announced and developed by the NVIDIA. Data scientists and Artificial Intelligence (AI) researchers requires ACCCURACY, SIMPLICITY and SPEED FOR DEEP LEARNING SUCCESS.Faster training and faster iteration
gives an eventual solution for faster innovations and faster time to market.
The DGX 1 uses the pascal architecture which was recently showed in car super computer. The DGX 1 is developed with 8 tesla GP100 GRAPHIC PROCESSING UNIT (GPU) each with 8 gigabytes of memory. On the other hand it also consists of 512 GB of RAM and four 1.92 tera bytes of hard disks.
The machine comes pre-loaded with an array of tools for developers namely NVIDIA CUDA, a deep neural network(DNN) library that helps to create and design networks. On the other side, Cuda includes an array of standard DNN frameworks, namely Caffe, Theano and Torch. NVIDIA offers full support for the system through the cloud which also includes software updates and manages the systems.
The machine comes pre-loaded with an array of tools for developers namely NVIDIA CUDA, a deep neural network(DNN) library that helps to create and design networks. On the other side, Cuda includes an array of standard DNN frameworks, namely Caffe, Theano and Torch. NVIDIA offers full support for the system through the cloud which also includes software updates and manages the systems.
Deep Neural
Networks allow computers to emulate the human mind in order to recognize things
we might think as simple, such as determining a cat from a dog. In recent
years, DNNs have found multiple uses, from writing your emails, beating Chinese Go masters and even putting you on
the fast-track to being the worlds next Eminem.
Here is the video about super computer: