Nvidia announced that its new RTX 30 series mobile GPUs are twice as power efficient as the previous generation thanks to its new AI-powered Max-Q 3.0 and Dynamic Boost 2.0 technologies Nvidia also confirmed that graphics rival AMD's implementation of Smart Nvidia also confirmed that graphics rival AMD is in the process of implementing a resizable BAR technology called Smart Access Memory.

During the CES livestream, Jeff Fisher, senior vice president of Nvidia's GeForce graphics division, said that Dynamic Boost 2.0 uses AI technology to dynamically shift power between the CPU, GPU, and GPU memory at each frame

Net.

The net result is twice the power efficiency of conventional RTX 20 series mobile GPUs.

To put the new RTX 30 series and Max-Q 3.0 results in context, Fisher compared them to the GTX 10 series.

"Four years ago, a laptop with a GTX 1080 averaged 40mm thick and weighed over 9 pounds; after four years of innovation, Max-Q gen 3.0 laptops are half the size, half the weight, and up to 10 times the performance,"

Fisher stated.

Fischer also discussed the characteristics of the "AI" intervention claimed in Dynamic Boost 2.0 and whether it uses pre-baked profiles generated by a large AI network or whether all AI algorithms are locally and in real-time by the GPU. No details were given as to whether they are computed.

However, he did confirm that Nvidia supports resizable BARs within the PCI Express interconnect.

"In games, GPU memory is used for textures, tints, and geometry, which are constantly updated as the player moves through the world. Currently, only a portion of the GPU memory can be accessed by the CPU at a time, so the memory needs to be updated many times. With resizable BARs, games can access the entire GPU memory, allowing multiple updates at the same time, which improves performance," Fischer explained, not noting that AMD is ahead of the curve with its Smart Access Memory feature.

He also did not provide specific information on the performance boost provided thanks to resizable BAR support.

In any case, the new RTX 30 series Mobility GPUs appear to be a big step forward; Nvidia believes that even the $999 RTX 3060 Mobile is faster than the current RTX 2080 Super for laptops. In other words, the 3070 and 3080 promise to be absolute beasts.