A
AT HEART

Designed for HPC, Maverick-2 delivers efficient performance at any scale without the pain of porting. Move beyond the status quo and experience what intelligent acceleration can do for you.

SCROLL
meet us
at our booth
#1419

INTRODUCING THE
INTELLIGENT COMPUTE
ACCELERATOR

Maverick-2 Intelligent Compute Accelerator (ICA) intelligent software-defined architecture with real-time optimization that learns your application and accelerates just the hot spots. Experience faster results and greater efficiency—to drive your next innovation forward.

TECHNOLOGY THAT ADAPTS TO YOU

Maverick-2 surpasses the limits of traditional CPUs and GPUs thanks to a uniquely adaptable architecture that reduces application bottlenecks, freeing scientists to pursue breakthroughs without being hindered by technical hiccups. Maverick-2 seamlessly adapts to today's HPC and AI/ML workloads, free of the rigid, high-latency designs and high-power consumption of its competitors.

Embrace intelligent acceleration

NextSilicon's accelerators deliver exceptional out-of-the-box performance through the use of a revolutionary software-learning algorithm that dynamically optimizes hardware configurations at runtime, accelerating the path to discovery. Maverick-2 reduces time to science by optimizing computational performance through a combination of flexible hardware with intelligent software algorithms. Maverick-2 leverages runtime data to analyze application behavior, accelerating the most demanding code segments with unmatched efficiency.

Experience effortless porting

The Maverick-2 intelligent developer toolchain for HPC and AI does not require code changes or software stack reinvestment—freeing you from vendor lock-in. Maverick-2 natively supports popular programming languages and frameworks such as C/C++, FORTRAN, OpenMP, and Kokkos, with upcoming integrations planned for CUDA, HIP/ROCm, and leading AI frameworks. Many applications can run on Maverick-2 without modification, simplifying porting, eliminating the need for a proprietary software stack and reducing time to science by weeks, months, or even years.

At last—greener computing with outstanding performance

Maverick-2 sets a new standard for efficient computing with more than a 4x performance-per-watt advantage over traditional GPUs and more than 20x that of high-end CPUs, all while reducing the total cost of ownership by more than half. By intelligently optimizing for power efficiency in real time, Maverick-2 enables sustainable innovation, making it the ideal choice for data centers and researchers striving to meet environmental and operational goals without compromising on performance.

INNOVATIVE BY NATURE.
POWERFUL BY DESIGN.

HOST INTERFACE

PCIe Gen 5 (x16) card

PROCESS TECH

TSMC 5nm

FREQUENCY

1.5 GHz

PACKAGING TECH

2.5 D

MEMORY CAPACITY

96 GB

MEMORY TECH

HBM3E

MAX POWER

300 W

CACHE COHERENCE

128 MB

PROGRAMMABLE MODEL

Any program

HOST INTERFACE

PCIe Gen 5 (x16) OAM

PROCESS TECH

TSMC 5nm

FREQUENCY

1.5 GHz

PACKAGING TECH

2.5 D

MEMORY CAPACITY

192 GB

MEMORY TECH

HBM3E

MAX POWER

600 W

CACHE COHERENCE

256 MB

PROGRAMMABLE MODEL

Any program

INTELLIGENTLY
ACCELERATE

Built on principles of efficient performance, adaptability, and a future-proof design, Maverick-2 ICA is designed to deliver the best output across any workload. By forging a new path forward, Maverick-2 diverges from fixed CPU and GPU architectures in favor of purpose-built intelligent acceleration to power legacy, new, and future applications.

YOUR NEXT
INNOVATIONS

Maverick-2 is devilishly adaptable, ready to power your evolving HPC, AI, and other workloads.

DIVE DEEPER

STAY UP
TO SPEED

Subscribe to NextLetter for exclusive insights on our latest innovations, performance benchmarks, white papers, event highlights, and success stories. Stay in the know!