Hardware that adapts to you

Introducing the first production dataflow accelerator powered by NextSilicon's Intelligent Compute Architecture™. Hardware that adapts to software in real-time—delivering breakthrough performance without code rewrites or vendor lock-in.

See the architecture. See the benchmarks. See the future.

Watch now

Redefining efficient performance at scale

Maverick-2 Intelligent Compute Architecture (ICA) represents a revolutionary shift in computing with the unveiling of the 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.

Discover Maverick-2

Move beyond the pain of porting

Maverick-2 ICA pioneers a new era in HPC computing for developers. Paired with a user-friendly and powerful developer toolchain that natively supports popular languages, such as C/C++, FORTRAN, OpenMP, and Kokkos, Maverick-2 eliminates the need for domain-specific languages and the burdensome application porting effort they create. With Maverick-2 you can avoid extensive code rewrites, and accelerate your innovation while bypassing the time-consuming porting process. This software compatibility and ease of use saves months in development effort, enabling faster time-to-science and insights. NextSilicon is dedicated to providing comprehensive support for customer applications, with upcoming integrations planned for CUDA, HIP/ROCm, and leading AI frameworks.

About Maverick-2

The future of acceleration is intelligent

Maverick-2 is redefining the future of high-performance computing with Intelligent Compute Architecture (ICA), a new approach that moves beyond the status quo of traditional CPU and GPU acceleration by combining intelligent software-defined hardware with real-time optimization. Maverick-2 ICA can dynamically adapt and reconfigure its hardware to the specific needs of your HPC and AI workloads to provide efficient, workload-specific performance with the flexibility to adapt to any future demands.

Learn more

ACCELERATING SANDIA'S VANGUARD PROGRAM

In 2023, Sandia National Laboratories, leading a tri-lab consortium with Lawrence Livermore National Laboratory (LLNL) and Los Alamos National Laboratory (LANL), announced their partnership with NextSilicon Inc. to deliver the next Advanced Architecture Prototype System (AAPS). NextSilicon's system was embedded into Sandia's Vanguard program and was tasked with identifying and evaluating emerging pre-tested technologies, to determine their viability in supporting the National Nuclear Security Administration's (NNSA) Advanced Simulation and Computing (ASC) program. Learn more about NextSilicon and Sandia's partnership.

THE LEADING
RISC-V CORE

NextSilicon proudly presents its first server-class RISC-V CPU core - Arbel. Designed from the ground up on TSMC technology, Arbel is built to deliver unprecedented throughput for today's data-center workloads and beyond.

Learn more

ADAPTABLE TO EVOLVING WORKLOADS

Unlock the full potential in your industry and secure your competitive edge. Maverick-2 ICA target workloads include a wide variety of massively parallel HPC and AI applications.