Pressroom

British computing company Signaloid has joined CERN openlab, the public-private partnership through which CERN evaluates emerging information technologies for scientific computing. As part of the collaboration, CERN and Signaloid will evaluate Signaloid's distribution-extended compute hardware (UxHw®) technology within the CERN openlab Heterogeneous Architectures Testbed, which explores new processor technologies for future scientific computing infrastructures. The collaboration comes as research organisations worldwide are increasingly adopting heterogeneous computing architectures that combine CPUs, GPUs and specialised accelerators to tackle demanding workloads more efficiently. As the High-Luminosity Large Hadron Collider (HiLumi LHC) approaches, CERN is evaluating a range of emerging computing technologies that could help address its rapidly growing computational requirements. “Heterogeneous architectures are becoming essential for the HiLumi LHC and CERN openlab is pioneering a model for evaluating next-generation computing technologies such as Signaloid's distribution-extended compute hardware technology. The upcoming deployment of Signaloid’s hardware and software stack at CERN openlab illustrates the kind of architectural innovation openlab was created to evaluate.” says Maria Girone, CTO CERN openlab. Preparing for the High-Luminosity LHC The Large Hadron Collider (LHC) is the world's largest particle accelerator. By colliding protons at nearly the speed of light, CERN’s scientists investigate the fundamental building blocks of matter and seek answers to some of the biggest questions in physics. Much of this research depends on Monte Carlo simulation, which allows physicists to compare experimental measurements with millions of simulated particle collisions. Generating these simulations requires repeatedly calculating the same physical processes using different random inputs, making Monte Carlo event generation one of the most computationally-demanding workloads in particle physics. When the HiLumi LHC begins operation later this decade, the number of recorded collisions will increase dramatically. While this promises unprecedented scientific opportunities, it will also place enormous pressure on CERN's computing infrastructure, with projected computing demand expected to outpace available resources. UxHw: Beyond the Capabilities of Classical Computers, Available in Production Today Rather than replacing conventional processors, Signaloid's UxHw® technology is designed to extend heterogeneous computing systems with native support computation directly on digital representations of continuous probability distributions. With this capability, instead of repeatedly executing the same kernel millions of times with different random inputs (so-called sampling), software running on UxHw can perform calculations directly on probability distributions, in a single execution pass, while requiring minimal changes to existing software. In benchmarking against today's high-performance server platforms, UxHw has demonstrated speed-ups of up to 2,000× for representative workloads ranging from high-energy physics, to regulatory risk modeling for banks, to simulations used in chip design, to robotics. Additional efficiency gains are expected from Signaloid's recently custom ASIC implementations, the first of which taped out in May 2026 using a low-power TSMC fabrication process. Evaluating a New Computing Architecture As part of the CERN openlab Heterogeneous Architectures Testbed, CERN and Signaloid will evaluate a representative Monte Carlo event generation workflow based on the Pepper framework for proton-proton collisions producing multiple gluons. The project will assess computational performance, numerical accuracy, and integration effort, helping determine where distribution-extended computing technologies like UxHw can complement existing CPU- and GPU-based scientific computing infrastructure. The joint project is designed to identify where distribution-extended computing adds value within the Monte Carlo event generation pipeline and what practical considerations are involved in integrating the technology into existing high-energy physics software. "The future of high-performance computing will not be defined by a single processor architecture, but by heterogeneous systems that combine specialised hardware for different classes of computation," said Prof. Phillip Stanley-Marbell, Founder and CEO of Signaloid. "We're excited that CERN openlab is evaluating UxHw alongside other emerging computing technologies. Experimental particle physics represents one of the most demanding and exciting environments in which to demonstrate its potential." Dr. Stefan Roiser, Senior Computing Engineer at CERN, says “The largest share of LHC computing resources is spent simulating particle collisions. We will explore Signaloid's technology in Monte Carlo event generation, the first step in the simulation chain expected to see substantial cost increases during CERN's upcoming High Luminosity data-taking period. Because event generation relies heavily on multi-dimensional distributions, Signaloid's UxHw technology has strong potential to accelerate this software, helping to meet the forecasted computing budgets during HiLumi LHC, starting in 2030.” The collaboration reflects a broader trend across high-performance computing. Around the world, governments and research organisations are investing in heterogeneous computing systems capable of combining multiple processor architectures for increasingly complex scientific and AI workloads, including the UK's planned £750 million AI Research Resource (AIRR) heterogeneous supercomputer.

British compute hardware company Signaloid has joined the Open Chiplet Alliance (OCA) and announced plans to make its UxHw® compute acceleration technology available as chiplets within the OCA ecosystem. The UxHw technology targets AI and simulation workloads that rely on stochastic methods, including quantitative finance, reinforcement learning, engineering simulations, and world models. The announcement follows Signaloid’s recent tapeout of a UxHw ASIC for robotics and physical AI in an ultra-low-power TSMC process. “The Open Chiplet Atlas (OCA) increases innovation in chip design by defining an open architecture for multi-vendor chiplet interoperability. In doing so, it enables new Systems-in-Package (SiPs) with reduced non-recurring engineering (NRE) costs and a vastly expedited time-to-market,” says Wei-han Lien, Chief CPU Architect and Senior Fellow of Tenstorrent. “We are thrilled to welcome Signaloid to the OCA ecosystem. Their unique, innovative accelerator for stochastic workloads adds a highly specialized capability that enriches our expanding suite of chiplets.” A Different Kind of AI Accelerator Chiplet Signaloid’s UxHw technology delivers orders-of-magnitude speedups for workloads common in robotics, machine learning, quantitative finance, and engineering simulations. These workloads often rely on iterative algorithms with randomized variations, including Monte Carlo methods, importance sampling, and particle filters, to evaluate large numbers of possible scenarios in searching for a solution. Unlike conventional CPUs and GPUs, which handle such computations through repeated execution across many compute cores, Signaloid’s UxHw dynamically restructures computations to process information about probable outcomes directly and more efficiently. In competitive benchmarking against contemporary high-end server processors, UxHw has demonstrated speedups of multiple orders of magnitude while often reducing energy consumption by up to 1000×. What the Chiplet Will Enable Signaloid’s existing binary-translation-based cloud instances, FPGA implementations, and ASIC realizations of UxHw already provide multiple orders-of-magnitude speedups over conventional approaches for stochastic workloads. By bringing UxHw to the OCA ecosystem as a chiplet, Signaloid aims to enable tighter integration with next-generation heterogeneous AI accelerators. The UxHw technology and its implementation are covered by a growing portfolio of more than 90 intellectual property filings across the US, China, Taiwan, Japan, and the EU.

Cambridge, UK, 14th September 2026 — British technology company Signaloid today announced the appointment of three distinguished industry veterans to its advisory board and senior leadership roles, to strengthen the commercialization momentum behind its technology: Dr. Han Lee, former Global Head of Quantitative Strategies and Automated Trading for the Fixed Income Division at Morgan Stanley, Dr. Nachiketh Potlapally, former Architect at Oracle Cloud Infrastructure, and Christian Roth, former Senior Director Enterprise Sales, Intel. Bringing deep expertise in quantitative finance and cloud infrastructure, the appointments build on Signaloid’s commercial traction momentum in Europe, Japan, and the United States. Dr. Lee, prior to his executive role at Morgan Stanley, served as Global Head of Quantitative Analytics at RBS and holds a Ph.D. in Theoretical Physics from the University of Cambridge. He is a co-founder of RLxPartners Ltd, and serves as an advisor to the Head of the Department of Physics at the University of Oxford. Dr. Potlapally holds a Ph.D. in Computer Science from Princeton University. He previously worked at Intel on the architectural security of high-performance processors and servers, was a security architect  at Amazon Web Services (AWS) Oracle Cloud Infrastructure (OCI). As an early member at both AWS and OCI teams, he worked on building secure cloud infrastructure from ground-up.  Mr. Roth, who is joining Signaloid as Chief Commercialization Officer, joins Signaloid from over two decades at Intel where he served in various leadership positions in Sales including Senior Director Enterprise Sales and Global Key Account Director. In addition he served as the Director of Product Marketing in EMEA for Data Center, Business Clients, Storage and Networking Platforms. He is an Insead Alumnus (IEP), holds an MBA from the Carlsson School of Management/University of Minnesota, USA and a Global EMBA from the Executive Academy of the WU Vienna, Austria (Wirtschaftsuniversität Wien).    Signaloid’s UxHw Technology: From Server-Based Quantitative Finance to Edge Robotics and Physical AI Many mission-critical applications ranging from financial risk modeling and energy safety analysis to chip design, robotics, and AI , rely on stochastic methods such as Kalman filters, particle filters, importance sampling, and Monte Carlo simulations. These methods are particularly important in modern AI and machine learning (ML), powering applications ranging from reinforcement learning and probabilistic programming to localization and decision-making in physical AI systems. Traditional CPUs and GPUs typically execute such workloads through repeated calculations across thousands of cores, often requiring substantial compute resources, runtime, and energy. Signaloid’s distribution-enhanced compute hardware (UxHw®) takes a different approach to running stochastic workloads. Instead of relying on large numbers of repeated calculations, UxHw restructures computations, using binary translation optionally augmented with hardware acceleration, to work directly on probability distributions. This enables results that can otherwise require billions of operations on conventional hardware. Deployed on existing hardware, UxHw can deliver performance improvements of several orders of magnitude, in some cases on the order of 1,000x, without requiring software rewrites, at the same time reducing energy consumption by similar orders of magnitude. On AWS r7iz compute instances, UxHw has demonstrated substantial performance gains across quantitative finance workloads, including up to 430x acceleration for Value at Risk (VaR) calculations using geometric Brownian motion and up to 580x acceleration for computations involving Heath–Jarrow–Morton models (typically calibrated to a grid of swaption prices). In robotics and physical AI, UxHw has delivered more than 37x speedups for particle filter algorithms on embedded microcontroller units (MCUs). Additional gains are possible when UxHw is combined with Signaloid’s recently announced UxHw C0-ASIC. What the new advisors bring to Signaloid: Buyer-Side Experience from Quantitative Finance and Enterprise Clouds The appointment of the new advisors will help Signaloid build on its recent momentum with the availability of its UxHw toolchain for deployment on both cloud-based and on-premises Amazon Web Services (AWS) instances for quantitative finance, engineering simulation, and high-energy physics simulations, as well as new distributions channels for its edge hardware modules (with distribution contracts in place with Mouser Inc. and DigiKey Inc., two of the world's largest semiconductor device distributors).  In this context, newly-appointed advisory board chair, Dr. Han Lee, former Global Head of Quantitative Strategies and Automated Trading at Morgan Stanley, says “It is not often that you find a new computing technology that already solves commercially-important challenges today, and which also has the potential to be the basis for the future of computation. Signaloid have not only invented a new class of computing platform, but have also gone all the way to engineering it into a production-ready cloud compute platform that has received the major security certifications demanded by enterprise users. As a physicist, I find it impressive to see their technology being applied already in deployments from Boeing, to Bosch, to CERN, and at the same time achieving order-of-magnitude speedups over high-end server processors on quantitative finance workloads. I am delighted to join Signaloid as an advisor.”

British computing technology company Signaloid today announced the release of the Signaloid Compute Engine Amazon Machine Image (AMI) via AWS Marketplace. The release enables organizations to deploy Signaloid’s distribution-extended compute hardware (UxHw®) technology within their Amazon Virtual Private Clouds (VPCs). The AMI provides access to UxHw, which delivers orders-of-magnitude performance improvements on x86_64 and ARM (AArch64) AWS Elastic Compute Cloud (EC2) instances. Without requiring software rewrites, UxHw enables existing applications to compute directly on probability distributions, automating algorithms such as Monte Carlo methods in finance and physics, importance sampling in reinforcement learning, and particle filters in physical AI and robotics. The technology works through binary translation and optimization at the LLVM intermediate representation (LLVM IR) level, with optional hardware acceleration via FPGAs and Signaloid’s C0-ASIC that was recently taped-out in an ultra-low-power TSMC process. Examples of performance achieved with the AMI include 430-fold speedup for Value at Risk (using geometric Brownian motion) and up to 580-fold speedup for Heath-Jarrow-Morton swaptions pricing. For organizations who currently use AWS infrastructure and want to benefit from UxHw combined with the familiarity of AWS tools, the AMI permits rapid deployment to EC2/On-Premises compute instances to benefit from UxHw. Organizations also have the option to deploy applications to Signaloid’s managed compute infrastructure, which has ISO/IEC 27001:2022 certification and SOC 2 Type II attestation. The Signaloid Compute Engine AMI is available through the AWS Marketplace.