AMD expands open artificial intelligence software ecosystem with Brium acquisition

AMD acquires Brium to further strengthen its open Artificial Intelligence software ecosystem, targeting performance and developer empowerment.

AMD has announced the acquisition of Brium, a firm with renowned expertise in compiler technologies and Artificial Intelligence software development. Brium´s team will infuse AMD´s offerings with advancements in machine learning, Artificial Intelligence inference, and performance optimization, strengthening AMD´s open software ecosystem. Their specialized knowledge spans areas such as compiler technology, model execution frameworks, and streamlined end-to-end inference solutions, all crucial for effectively deploying Artificial Intelligence workloads at scale.

The move is a deliberate part of AMD´s broader strategy to foster long-term innovation and empower developers working on the next generation of intelligent applications. With Brium now part of its portfolio, AMD reiterates its dedication to building a high-performance open-source ecosystem that truly leverages the potential of its hardware, particularly in Artificial Intelligence development and deployment scenarios.

This transaction marks the latest in a string of targeted investments for AMD, which previously acquired companies like Silo AI, Nod.ai, and Mipsology. Collectively, these acquisitions consolidate AMD´s commitment to supporting the open-source community and delivering optimized efficiency and adaptability on its hardware platforms. Brium´s integration represents another decisive step toward making AMD a formidable player in the competitive landscape of Artificial Intelligence hardware and software synergy.

68

Impact Score

Samsung to supply half of NVIDIA’s SOCAMM2 modules in 2026

Hankyng reports Samsung Electronics has secured a deal to supply half of NVIDIA’s SOCAMM2 modules in 2026 for the Vera Rubin Superchip, which pairs two ‘Rubin’ Artificial Intelligence GPUs with one ‘Vera’ CPU and moves from hardwired memory to DDR5 SOCAMM2 modules.

NVIDIA announces CUDA Tile in CUDA 13.1

CUDA 13.1 introduces CUDA Tile, a virtual instruction set for tile-based parallel programming that raises the programming abstraction above SIMT and abstracts tensor cores to support current and future tensor core architectures. The change targets workloads including Artificial Intelligence where tensors are a fundamental data type.

Contact Us

Got questions? Use the form to contact us.

Contact Form

Clicking next sends a verification code to your email. After verifying, you can enter your message.