Maverick-2 Delivers Unmatched Performance with Intelligent Software-Defined Hardware
NextSilicon, a pioneer in high-performance computing (HPC) innovation, today announced its emergence from stealth with the launch of Maverick-2, the industry’s first Intelligent Compute Accelerator (ICA). Maverick-2 represents a revolutionary shift in computing by introducing intelligent software-defined hardware acceleration that delivers real-time adaptability and unmatched performance. This breakthrough technology is designed to deliver superior performance and efficiency for HPC, AI, and vector database applications.
In addition to unveiling Maverick-2, NextSilicon showcases its robust financial positioning with $303 million in funding from prominent investors such as Aleph, Amiti, Liberty Technology VC, Playground Global, Standard Investments, StepStone, and Third Point Ventures. This strong financial backing, combined with groundbreaking innovation, positions NextSilicon to reshape the future of high-performance computing with its revolutionary Intelligent Compute Accelerator (ICA) architecture.
“Sandia National Laboratories is already using new Maverick-2 accelerators in anticipation of our deployment later this year of our new integrated system – named Spectra – which will be delivered in 2025,” said James H. Laros III, Distinguished Member of technical staff and Vanguard program lead. “Our partnership with NextSilicon, which began over four years ago, has been an outstanding example of how the NNSA laboratories can work with industry partners to mature novel emerging technologies. NextSilicon’s continued focus on HPC made them a prime candidate for the Vanguard program.”
Maverick-2 redefines accelerator architectures, moving beyond the limitations of traditional fixed GPU designs which are based upon the eight-decade old Von Neumann architecture. It uses advanced telemetry and NextSilicon’s patented algorithms to dynamically tailor acceleration in real-time to the unique needs of an application. This adaptability can enable organizations to achieve over 4x the performance-per-watt of traditional GPUs and more than 20x that of high-end CPUs, while reducing operational costs by more than half.
The Maverick-2 ICA is designed to focus on the critical codes and workflows that run the majority of the time in HPC and AI environments. Its self-optimizing architecture delivers immediate, scalable performance improvements. This is achieved by creating software-defined processor cores tailored to the performance needs of each application and then executed on the accelerator hardware. As your application runs, telemetry data is fed to NextSilicon’s intelligent algorithms, to continuously self-optimize performance, power consumption, and utilization in real-time. The result is efficient performance at scale for the most demanding HPC applications, while consuming 50-80% less power than traditional GPUs.
“Traditional CPU and GPU architectures are often constrained by high-latency pipelines and limited scalability,” said Steve Conway, Senior Analyst at Intersect360 Research. “There is a clear need for reduced energy waste and unnecessary computations within HPC and AI infrastructures. NextSilicon addresses these important issues with Maverick-2, a novel architecture purpose-built for the unique demands of HPC and AI. Maverick-2 is designed to break down barriers to adoption and migration from legacy architectures.”
Alternative accelerators have tried for years to challenge the dominance of traditional GPUs and CPUs, but they often struggled in overcoming the complexities of application porting and vendor-specific frameworks which create lock-in. NextSilicon’s Maverick-2 ICA is the first to break through these barriers with a powerful, user-friendly software suite. It natively supports popular languages like C/C++, FORTRAN, OpenMP, and Kokkos, allowing many applications to run on Maverick-2 without modification. This software compatibility and ease of use saves months in development effort, enabling faster time-to-science and insight. NextSilicon is dedicated to providing comprehensive support for customer applications, with upcoming integrations planned for CUDA, HIP/ROCm, and leading AI frameworks.
Maverick-2 not only addresses today’s HPC commercial and research computing challenges, but also incorporates NextSilicon’s unique intellectual property to tackle evolving and future workloads. Its intelligent and flexible architecture is designed to be easily adapted to new use cases for converged HPC-AI workloads, vector database applications, breakthroughs in AI models, and emerging agentic and generative AI applications.
“We are excited to support the launch of the Maverick-2 Intelligent Compute Accelerator and its potential to drive new levels of performance and efficiency in the HPC market,” said Phil Pokorny, CTO of Penguin Solutions. “At Penguin, we are adept at turning cutting-edge ideas into outcomes—faster, and at any scale, enabling our customers to tackle the most demanding workloads. Maverick-2’s intelligent, software-defined approach complements the wide array of technologies we provide, offering organizations a powerful option to optimize their infrastructure and achieve breakthrough results in HPC and AI. As complexity in applications grows, innovations like Maverick-2 open new possibilities for our customers to accelerate scientific and commercial advancements.”
“I am thrilled to announce the launch of the Maverick-2 Intelligent Compute Accelerator, a groundbreaking innovation in computing,” said Elad Raz, Founder and CEO of NextSilicon. “Maverick-2 represents a first-of-its-kind solution that seamlessly combines advanced software and hardware to optimize the most complex scientific codes running on the world’s largest high-performance computing systems. As we face the growing demand for faster, more efficient applications, Maverick-2 unlocks possibilities previously deemed impossible. I want to express my deepest gratitude to our customers and employees for their unwavering support and commitment. We are excited about the incredible advancements that lie ahead.”
The Maverick-2 ICA is now shipping to dozens of customers, with volume shipments beginning in early 2025 to fulfill a strong backlog. NextSilicon supports a variety of organizations, ranging from the US Department of Energy, to leading academic research institutions, as well as commercial customers in financial services, energy, manufacturing, and life sciences verticals. Early adopter programs for new customers are now available through partners Penguin Solutions and Dell Technologies.
To learn more, visit us at booth #1419 during the SC24 Supercomputing Conference, held from November 17-22, 2024, at the Georgia World Congress Center in Atlanta, Georgia.
Explore AITechPark for the latest advancements in AI, IOT, Cybersecurity, AITech News, and insightful updates from industry experts!
