Artificial Intelligence systems, particularly those involving machine learning and deep learning, require an enormous amount of energy due to the computational intensity of the tasks they perform. These processes require powerful hardware, which in turn consumes a lot of electricity. Microsoft is even considering powering its data centers with nuclear energy to help address the problem.
As AI technology continues to advance and its use becomes widespread, the energy consumption associated with it is expected to increase, raising concerns about its environmental impact. Andrew Sloss, an experienced engineer who recently finished his 25-year tenure at Arm as a senior principal research engineer, has taken on a new role at new UK startup Vaire Computing to tackle this problem from a different angle.
Vaire, which has joined incubator organization Silicon Catalyst UK to help drive its plans, has the ambitious goal of tackling “reversible computing”, which could lead to the development of logic circuits that consume almost no power.
Physics-aware architectures
In his role at Arm, Sloss focused on future technology and Vaire's work seems to be the perfect next step for him. Speaking about the move on his LinkedIn, Sloss says: “As we all know, the semiconductor industry is under increasing pressure, especially as we move towards the physical limits of Moore's Law (EoML), i.e. a silicon atom is ~2 Angstroms in size, increased thermal problems, etc., i.e. “You can't change the laws of physics.” Therefore, it forces us to go back to the decisions we made in the past and rethink them. “We have new and future pressures that affect scalability in computing and power constraints (e.g., ML, LLM, and DL).”
He goes on to explain that Vaire Computing “wants to rewrite George Boole's Laws of Thought and von Neumann Architecture by creating Physics Aware Architectures (with behavioral support for existing software). It all comes down to making logic aware of physics (from the transistors up). This concept is not the standard 1-2-3 game. Physics gives us a huge amount of tricks that we haven't used in the architectural space.”
This suggests that Vaire could be exploring a similar avenue to Normal Computing, a company made up of former members of the Google Brain Team and X Engineers who built generative AI production systems for Alphabet.
