Efficient Computer raises $16M to solve computing’s energy problem

Brandon Lucia, Founder & CEO
March 7, 2024

Hello, world! We are excited to emerge from stealth and introduce Efficient Computer, the company that is revolutionizing energy-efficient computing. It was only about a year ago, in February 2023, when we welcomed our first non-founding employee, and today we received our first silicon back from the foundry.

An image of our first silicon chip, Monza

We are happy to announce $16M in seed financing led by Eclipse VC. This seed funding will enable us to grow our amazing team and combine our R&D focus with our go-to-market to get chips in customer’s hands. Eclipse is a perfect partner for our mission, with deep expertise in hardware and connections to key markets for our technology. They have also been amazing to work with throughout the process, and we are excited to go on this journey together.

I cannot thank the team enough for the hard work to get here. Our progress has been incredible — building a completely new technology stack, from compiler to silicon, in only a year is unheard of. It was only possible through the dedication of insanely talented individuals, who worked selflessly to constantly raise the bar and exceed our expectations. It is a testament to how well we have worked together that we simultaneously stood up a compiler, architecture, and silicon and had it all come together in the end.

A photo of the Efficient team

Why energy-efficient + general-purpose?

Nathan, Graham, Alex, and I founded this company to solve computing’s energy problem. Across all scales, computing is now limited by energy efficiency: be it battery life in IoT and mobile, or power supply and cooling in the data center. For decades, computer designers relied on Moore’s Law to improve energy efficiency automatically. But now that Moore’s Law has slowed, computer designers can no longer ignore the energy problem.

Today’s computers are horribly inefficient. The dominant “von Neumann” processor design wastes 99% of energy. This inefficiency is, unfortunately, baked deeply into their design. In von Neumann processors, programs are expressed as a sequence of simple instructions, but running programs in a simple sequence is unacceptably slow. Improving performance requires complex hardware to find instructions that can safely run in parallel.

Improving efficiency requires a fundamental rethinking of how we design computers. Others have approached this problem by restricting programs, i.e., limiting the processor to only run programs where parallelism is easy to find. These restrictions let designers simplify and specialize the hardware. While this approach improves efficiency, it gives up on general-purpose programmability, which is a huge problem. Generality is efficiency: any part of a program that runs inefficiently quickly limits energy-efficiency of the entire system. Moreover, these specialized processors ignore software, which is where the real value lies in computing.

A new approach to computer design

At Efficient, we are taking a different approach. Going back to the original research at Carnegie Mellon University with Graham and Nathan, we embraced the value of software, and have sought from the outset a general-purpose, post-von Neumann processor design that is easy to program and also extremely energy-efficient.

Our approach spans hardware and software, which is the only path to efficiency. Instead of executing a series of instructions like von Neumann designs, our architecture expresses programs as a “circuit” of instructions that shows which instructions talk to each other. This model lets us lay out the circuit spatially across an array of extremely simple processors and execute the program in parallel, with much simpler hardware (and thus less energy!) than any existing processor.

A photo of our chip layout

We call this design the Fabric processor architecture, and we have implemented it in the Monza test system on chip (SoC) pictured above. The Fabric’s compiler was designed alongside the hardware from day one, and it compiles programs written in high-level C or C++. Monza gets up to 100x better energy efficiency than the best embedded von Neumann processor and, unlike specialized hardware, it can be programmed in software using a standard, familiar flow.

Re-inventing computing for energy efficiency

I am extremely excited for the year ahead. The seed funding has enabled us to grow our team to 20 amazing employees, and we are executing full-speed-ahead towards our next tapeout and release of our software development kit later this year. New customer stories arrive by the day, showing how Efficient technology will enable smarter, longer-lasting devices from consumer IoT, to industrial IoT, civil infrastructure monitoring, and defense.

Lastly, I gladly welcome Greg Reichow, General Partner at Eclipse VC, to the Efficient Board of Directors. Greg was formerly VP of Production at Tesla, and his experience has already helped us scale our team and plan our road map for the years to come. I am thrilled to have Greg on-board to grow Efficient to dominate the world of energy-efficient computing. Go team!