Arm’s former unofficial tech futurologist joins obscure startup that wants to solve AI’s sustainability problem — by developing computers that consume almost no power
Artificial Intelligence systems, particularly those involving machine learning and deep learning, require a huge amount of energy, due to the computational intensity of the tasks they perform. These processes require powerful hardware, which in turn consume 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 usage becomes more widespread, the energy consumption associated with it is expected to increase, raising concerns about its environmental impact. Andrew Sloss, a seasoned engineer who recently ended 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 joined the incubator organization, Silicon Catalyst UK, to help drive its plans forward, has the ambitious aim 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. Talking 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, thermal issues increasing, etc., i.e., “Ye cannae change the laws of physics.” Hence, it forces us to go back to the decisions we made in the past and re-think them. We have new and upcoming pressures that hit scalability in computation and power limitations (e.g., ML, LLMs, and DL).”
He goes on to explain that Vaire Computing “wants to rewrite George Boole’s Laws of Thought and the von Neumann Architecture by creating Physics-aware Architectures (with behavioral support for existing software). It comes down to making the logic aware of the physics (from transistors upwards). This concept is not the standard 1-2-3 play. Physics gives us a huge bag of tricks we haven’t used in the architecture space.”
This suggests that Vaire might be exploring an avenue similar to Normal Computing, a firm staffed by former members of the Google Brain Team and X Engineers who built generative AI production systems for Alphabet.
More from TechRadar Pro
Artificial Intelligence systems, particularly those involving machine learning and deep learning, require a huge amount of energy, due to the computational intensity of the tasks they perform. These processes require powerful hardware, which in turn consume a lot of electricity. Microsoft is even considering powering its data centers with nuclear…
