While AI design tools already exist, they tend to be limited in use and scope. Traditional auxiliary circuit design tools still require many hours of manual programming and verification to develop a functional circuit.
The team claims that even for a processor as simple as the one created, it would take humans 1,000 times longer to develop.
The AI was trained by observing specific inputs and outputs of existing CPU designs, with the paper summarizing the training approach, "This is a novel approach to AI that generates a large-scale logic function with near 100% verification accuracy (e.g., > 99.999999999999999999999%, as Intel has) based only on external input-output examples, not formal programs written by humans. This approach generates a Boolean function represented by a graph structure called a Binary Speculation Diagram (BSD) with a lower bound on theoretical accuracy using a Monte Carlo-based extension, and Boolean function distance is used to overcome intractability."
The V32IA processor, dubbed "CPU-AI," was fabricated using 65-nanometer lithography and runs at 300 MHz. It is capable of successfully running Linux, SPEC CINT 2000 and Dhrystone, operating similarly to Intel's 1991 i486SX processors.
The researchers hypothesize that the processor's performance could be improved with advanced algorithms. In the paper's conclusion, the team ponders a self-evolving machine that will be able to develop its own iterative updates and improvements. They note. that AI independently discovered the von Neumann architecture by observing input and output data.
Thus, the algorithm could be tuned to focus on optimizing the fine-grained architecture.
18 countries have unveiled the first international agreement on how to protect artificial intelligence from irresponsible players. It aims to develop AI solutions that are "inherently safe".
On November 30, the professional IT community GlobalCIO hosted a large-scaled international conference "Global CIO Insights: Digital Transformation with AI". During the event, leading experts shared their practical experience in launching projects utilizing artificial intelligence (AI) and highlighted approaches that helped elevate their companies to new heights.
Voting for projects participating in the "Project of the Year" contest is open. The voting began on December 1st and will continue until January 15th inclusive. The winners will be announced on February 7th, 2024.
Online sales is one of the areas where the quality of IT tools directly affects business profitability. Kamza Nugumanov, CIO of Jusan store, tells about the experience of deploying a rapidly growing Kazakh marketplace.