Nvidia - Becoming more efficient
Last month Nvidia, one of our US holdings, rebased their latest graphics card. The chips become more powerful with each passing year, but we are getting to the limits of current materials. The focus now is shifting from making things more powerful, to being more efficient. So with the same computing power you would be able to do more.
To become more efficient, developers are turning to smart algorithms, to allow the chips to work hard where they need to and to 'slack' where they can. This is an area where AI can be used to find optimal algorithms.
Having more efficient chips, not only makes the chips more useful, it also means they use less electricity and emit less heat. Two key things when building large data centres!
This blog post breaks down a number of the new techniques being used to try to get more out of the latest Nvidia chips - NVIDIA's RTX cards are a gamble on the future of gaming
- "Again, simplifying the explanation, the supercomputer looks at ultra-high-resolution images and compares the data to a low-resolution version. It will then try and fails millions of times to find a way to make the low-resolution image look like the ultra-high resolution one. Once it succeeds, NVIDIA packages the algorithm for the game and sends it out via its GeForce Experience app for gamers to use."