Cambricon

Nvidia is one of the giants of artificial intelligence, but the competition is tightening more and more and resting on your laurels can mean the loss of leadership when you least expect it. Cambricon Technologies claims it has a Cambricon-1A chip that is capable of standing up to the all-powerful Tesla V100.

Cambricon-1A wants to end Nvidia's supremacy in AI

Cambricon Technologies has developed the new Cambricon-1A chip focused on artificial intelligence. It is a silicon that is capable of reaching 166.4 TOPS of power when making simple calculations of 8-bit integers, enough for the needs of artificial intelligence. Best of all, it does so with a power consumption of just 110W. As for the Nvidia Tesla V100, it is capable of offering a power of 120 TFLOPS in 8-bit decimal operations. In addition to this, the Cambricon-1A is capable of yielding 83.2 TFLOPS in medium precision operations, a significant advantage over the 30 TFLOPs that Nvidia's proposal achieves.

We recommend reading our post on SK Hynix will be the partner of Nvidia to supply the GDDR6 memories

This Cambricon-1A processor is manufactured by TSMC using 16nm lithography and achieves a maximum clock frequency of 1.3GHz. The core is accompanied by 16-32 GB of DDR4 memory at a frequency of 1600 MHz, much cheaper to produce than the HBM2 memory used by the Nvidia Tesla V100, something that will directly affect the final sale price.

The Cambricon-1A goes on the market in a PCI Express card format with a turbine heatsink, the company already has development kits compatible with Caffee, TensorFlow and MXNet, the most common development languages ​​for artificial intelligence applications. This Cambricon-1A promises to be Nvidia's biggest rival in the AI ​​arena.

Anandtech font