BlueRock Introduces New AI Infrastructure Architecture for Secure-Shared Execution with AMD DMA Isolation

Key Terms

microhypervisor technical

A microhypervisor is a very small, focused piece of software that creates and manages isolated virtual machines on a computer, doing only the essential tasks needed to run and separate workloads. For investors, it matters because the smaller codebase reduces security risks and resource use—like a minimalist building manager who tightly controls access to each apartment—potentially lowering costs, improving reliability, and enabling safer deployment of services and devices.

dma remapping technical

Direct Memory Access (DMA) remapping is a hardware feature that controls and redirects how peripheral devices read and write a computer’s main memory without using the CPU. Think of it as assigning safe lanes and checkpoints to visitors in a building so only authorized devices can reach certain rooms; that prevents accidental data collisions and blocks malicious access. For investors, DMA remapping matters because it affects a product’s security, performance, and compatibility — key factors in demand, regulatory risk, and competitive positioning for companies in chips, servers, and embedded systems.

iommu technical

An IOMMU (Input‑Output Memory Management Unit) is a hardware feature that acts like a traffic controller between peripheral devices (like network cards or storage controllers) and a computer’s memory, translating and isolating their memory access. For investors, it matters because IOMMUs improve system security, stability and virtualization performance in servers and devices—traits that can affect a chipmaker’s product competitiveness, customer adoption and total cost of ownership.

virtual machine technical

A virtual machine is a software-created computer that runs inside a physical computer, letting one machine behave like several independent ones. For investors, virtual machines matter because they let companies scale computing power, isolate services for security, and lower hardware costs—similar to renting separate apartments inside one building rather than buying multiple houses—affecting capital spending, operating efficiency, and risk exposure.

trusted computing base technical

The trusted computing base is the set of hardware, software and controls that must work correctly to keep a computer system secure and honest—think of it as the lock, key and frame that together prevent someone from breaking into a safe. For investors, a small, well-audited trusted computing base reduces the risk that critical systems or data can be tampered with, lowering the chance of operational failures, data breaches or regulatory problems that can hurt a company’s value.

gplv2 technical

A software license that requires anyone who distributes a program to also share its source code and let others use, modify, and redistribute those changes under the same terms. For investors, this matters because it can limit a company’s ability to lock up software as a proprietary asset, affect competitive advantage, create obligations for compliance and disclosure, and influence legal or commercial risk—like a rule that if you share a family recipe, you must also share any improvements you make.

See more from StockTitan in Google Search and AI answers. Adds StockTitan as a preferred source · opens Google

Add on Google Not now

Open source NOVA addresses growing AI infrastructure challenges driven by continuous, active workloads requiring a new approach to execution, isolation, and scalability.

SAN MATEO, Calif.--(BUSINESS WIRE)-- BlueRock today announced the latest open-source release of its NOVA Microhypervisor, which introduces advanced DMA remapping support for AMD (NASDAQ: AMD) platforms with IOMMU hardware virtualization capabilities.

As AI infrastructure faces sustained concurrency, growing execution complexity, and increasing economic pressure, NOVA strengthens hardware-level isolation across workloads, devices, and memory in shared execution environments.

AI systems are rapidly shifting from experimental workloads into continuously running production infrastructure, and the economics of operating them are becoming impossible to ignore. Leading AI providers continue to invest billions into compute infrastructure while simultaneously facing rising inference costs, infrastructure strain, and growing pressure to improve operational efficiency and profitability. These pressures point to a larger architectural shift, scaling AI infrastructure is becoming as much an execution and systems architecture challenge as a compute challenge.

The NOVA microhypervisor was designed to address these demands through trusted isolation and secure shared-service execution at large AI infrastructure scale, supporting fully isolated virtual machines with up to 256TB of physical memory and 128 petabytes of virtual address space per workload.

AI Workloads Are Changing Infrastructure Requirements

As AI systems become more agentic, continuously active, and increasingly distributed, infrastructure efficiency and execution coordination are emerging as core business constraints. Future AI infrastructure architectures will need to prioritize isolation, predictability, reduced trusted complexity, and more efficient execution at scale rather than relying solely on continuously expanding compute capacity.

“The AI industry is entering a new phase where infrastructure architecture will increasingly determine who can operate efficiently at scale,” said Harold Byun, CEO of BlueRock. “As workloads become more dynamic, continuous, and resource-intensive, the underlying systems must evolve alongside them. We believe the next generation of AI infrastructure will prioritize trusted isolation, execution efficiency, reduced complexity, and secure shared-service operation at massive scale. NOVA was built for that shift.”

New AMD DMA Isolation Capabilities

NOVA’s security and isolation capabilities now include DMA remapping support on AMD platforms using hardware IOMMU functionality. The capability is enabled by default as a core enforcement mechanism within the platform.

NOVA can:

• Prevent hardware devices assigned to one virtual machine from accessing the memory of neighboring workloads
• Enforce fine-grained memory access controls at the hardware layer
• Restrict access at per-device and per-memory-page granularity
• Abort unauthorized memory transactions directly through the IOMMU
• Optionally record DMA remapping faults for diagnostic analysis

“Enterprise AI workloads require an infrastructure built on absolute certainty rather than assumed security. To meet this standard, organizations must transition away from implicit trust models, establishing definitive, provable trustworthiness through the rigorous formal verification of foundational source code", said Udo Steinberg, Fellow & Co-Founder of BlueRock. “As traditional systems built for predictable enterprise applications are increasingly leveraged for highly dynamic, continuous AI execution, infrastructure security must evolve. NOVA addresses this critical shift by minimizing the trusted computing base and enforcing isolation directly at the hardware-software boundary.”

The architecture lays the foundation for future execution-aware security and introspection capabilities by enforcing protections beneath guest operating systems, helping maintain isolation even if workloads are compromised. Released as open source under the GPLv2 license, the NOVA Microhypervisor enables infrastructure trust and enforcement mechanisms to be independently inspectable and verifiable by the broader technical community.

The community repository is available on GitHub. Learn more about NOVA Microhypervisor here.

About BlueRock

BlueRock helps organizations operate AI and agentic systems with greater visibility, trust, and control. The company’s agentic operations platform enables teams to understand how AI systems execute across tools, infrastructure, models, and environments while applying context-aware protections and operational controls at the point of action. This helps enterprises move AI from experimentation into scalable production operations by improving execution visibility, strengthening trusted infrastructure foundations, and enabling more predictable operation of increasingly autonomous and distributed systems. BlueRock is headquartered in San Francisco, California and backed by Mayfield, Wing Ventures, and the Aziz Family Office. For more information, please visit our website www.bluerock.io.

View source version on businesswire.com: https://www.businesswire.com/news/home/20260609762631/en/

Media Contact:
MSR Communications
Jordan Slade
jordan@msrcommunications.com

Source: BlueRock