Cambridge, MA – Julia Computing has been awarded funding by the US Defense Advanced Research Projects Agency (DARPA) to accelerate simulation of Analog and Mixed-Signal circuit models using state of the art machine learning and artificial intelligence techniques. Funding was awarded as part of DARPA’s Intelligent Auto-Generation and Composition of Surrogate Models (Ditto) effort.
According to DARPA, “Ditto will explore novel third-wave AI solutions through the lens of microelectronic system simulation. The effort seeks to develop an automated software framework that can take in a microelectronic system design, train effective ML surrogate models of sub-system components, and simulate these designs 1000x faster, while maintaining acceptable levels of accuracy. These capabilities should provide a significant boost to the US semiconductor industry and US competitiveness as part of DARPA’s broader Electronics Resurgence Initiative.”
“Julia’s performance and differentiable programming capabilities give us a unique advantage in creating novel tools for modeling and simulation,” says project PI and Julia Computing CTO Keno Fischer. “Using newly developed surrogate architectures, such as our Continuous Time Echo State Network (CTESN) architecture, we have already been able to demonstrate acceleration in excess of 100x by employing these techniques in multi-physics simulations and are excited to bring this technology to the electronics simulation space.”
Julia Computing is partnering with Boston-based quantum computing startup QuEra Computing to demonstrate these novel capabilities for simulations of the control electronics of QuEra’s neutral atom quantum computers. QuEra’s sophisticated designs stretch the boundaries of traditional simulation tooling, making significant acceleration in simulation performance all the more crucial. Julia Computing intends to make these capabilities available to the larger industry in the near future. Companies facing challenging Analog/Mixed-Signal modeling and simulation problems are encouraged to contact Julia Computing at firstname.lastname@example.org.
About Julia and Julia Computing
Julia is the high-performance language of choice for data science, artificial intelligence, and modeling and simulation applications. Julia solves the two language problem by combining the ease of use of Python and R with the speed of C++, while providing parallel computing capabilities out of the box. Julia has been downloaded more than 24 million times and is used by more than 10,000 companies and over 1,500 universities. The Julia co-creators are the winners of the 2019 James H. Wilkinson Prize for Numerical Software and the 2019 Sidney Fernbach Award.
Julia Computing was founded in 2015 by all the creators of Julia. The company provides scalable enterprise computing solutions through its JuliaHub platform. A recent focus area of the company has been the creation of a suite of modern ML-enhanced modeling and simulation tools, such as the Pumas framework for pharmaceutical simulation.
About QuEra Computing
QuEra is a neutral-atom based quantum computing startup located in the heart of Boston near Harvard University. The company is founded on pioneering research by world-renowned scientists Mikhail Lukin, Vladan Vuletic, and Markus Greiner at Harvard and MIT. QuEra’s mission is to build the most scalable quantum computers to date to tackle useful but classically intractable problems for commercially relevant applications in optimization, simulation, materials-science, pharmaceuticals, and more. To do so, QuEra is assembling a world-class team of scientists and engineers to bring quantum computing from promise to reality.