Artificial intelligence requires enormous computing power for processing operations. The power provided by the processors of course, but also and especially by adapted graphics cards. And when you think GPU, you immediately think of Nvidia!
Nvidia has lifted the veil on the A100, the first GPU based on the Ampere architecture, which l’architecture contains 54 billion 7 nm transistors. This map, intended for the server market, accelerates up to 20 times (compared to previous models)the simulation of artificial intelligence and inference, deduction operations from implicit information. GPUs are connected to each other by the third generation of the Nvidia NVlink, which doubles broadband connectivity.
Power for AI calculations
If all this is a bit obscure, several Nvidia customers who already use the A100 allow us to get an idea of the capabilities capacités of this GPU. At DoorDash,the mealdelivery service, the A100 reduces the training time of models (on which AI functions are based) fonctions and accelerates the process of developing machine learning. . Indiana University will use the GPU to support scientific and medical research and advanced research in AI and data analysis.
The Technological Institute of Karlsruhe, en Germany, will be able to carry out much larger multi-scale simulations in the field of materials sciences, earth system sciences, engineering for energy and mobility research. . In short,there is no shortage of uses for such a GPU. The A100 will be integrated into the systems of several server manufacturers, including Atos, Cisco, Dell, Inspur, Lenovo, Supermicro, etc.
Nvidia also announced the DGX A100, the third generation of the manufacturer’s artificial intelligence system that offers 5 petaflops of performance in the field of AI and machine learning. . These systems carry eight Sensor Core A100s. Units are already in service, including to run models and simulations to combat COVID-19.