Nvidia announced it will launch the processors Tesla M40 and M4 GPUs (graphic processing units), which may represent a new step in the evolution of machine-learning systems.

Both processors, Tesla M40 and M4, serve different purposes. In a deep-learning system, the M40 works on the training of the neural network. It posses 3072 cores, 7 teraflops, 5GB of GDDR5 memory and nearly 250 watts of power to function.

On the other hand, the M4 GPU is smaller than the former, focalized on hyper-scale environments, and it works with clusters of systems that manage the machine learning functionality. It comes with 4GB of GDDR5 memory, 2.2 teraflops, and a less significant number of 50 to 75 watts per hour.

TeslaM40_NVIDIA
Joining the Tesla M40 is the Tesla M4. As hinted at by its single-digit product number, the M4 is a small, low powered card. Credits: Anand Tech

The M40 and M4 GPUs will be the first ones the company will launch for web hosting and serving. They will also feature a function that allows the machine to read the emotional state of the user and detect color tones.

According to Ian Buck, Nvidia’s vice president of accelerated computing, both graphic processing units are server based, and thus they will require to be stored in the same server, also suitable for videos.

But the main focus on Nvidia’s new processors is the evolution of machine-learning developing and improvements on the field of artificial intelligence, and how this can enhance the functionality of supercomputers. Making use of a system that can hold a growing database, machines can store new information and adapt to changes, which can be useful in a large variety of fields, from intuitive operating systems to driving services.

Nvidia’s machine-learning technology (in this case Tegra X1) can be used to boost the auto-pilot feature on cars, which relies on artificial intelligence that responds to the vehicle’s trajectory through different traffic patterns that processors record as new data for future reference. It can also be used to upgrade machines in the medical field.

Concentrating on the more traditional functions of GPUs, the vice president explains “machine learning to help add information attached to videos could improve the accuracy of search results. Machine-learning processors could also power software models designed to analyze videos and images.”

Jen-Hsun Huang, the company’s CEO referred to machine deep learning systems as the grand  computational challenge of this generation.

The Tesla M40 and M4 graphic processing units will be launched in different dates. The M40 GPU is expected to be released near the end of this year, while the M4 processor will be available in the beginning of 2016.

Source: The Tech Portal