Samsung to develop custom CXL data centre AI chips
Samsung Electronics has teamed up with internet company Naver to develop custom AI chips for data centres.
Samsung will use its computational storage, processing-in-memory (PIM) and processing-near-memory (PNM) memory technologies as well as Compute Express Link (CXL) for the hardware to accelerate massive AI workloads.
Recent advances in hyperscale AI have led to an exponential growth in data volumes that need to be processed. However, the performance and efficiency limitations of current computing systems pose significant challenges in meeting these heavy computational requirements, fueling the need for new AI-optimized chips.
- Samsung ASIC enables industry’s first 512GB CXL memory module
- Samsung boosts AI in-memory processing with CXL
- First memory module with CXL interconnect standard
Developing such chips requires an extensive convergence of semiconductor and AI disciplines, says Samsung, So it is combining its semiconductor design and manufacturing expertise with Naver’s experience in the development and verification of AI algorithms and AI-driven services.
Samsung has been introducing memory and storage that support high-speed data processing in AI applications, from computational storage (SmartSSD) and PIM-enabled high bandwidth memory (HBM-PIM) to next-generation memory supporting the Compute Express Link (CXL) interface.
Naver will continue to refine its HyperCLOVA, a hyperscale language model with over 200 billion parameters, used for its Clova assistant. It will also improve its compression algorithms to create a more simplified model that significantly increases computation efficiency.
“Through our collaboration with Naver, we will develop cutting-edge semiconductor solutions to solve the memory bottleneck in large-scale AI systems,” said Jinman Han, Executive Vice President of Memory Global Sales & Marketing at Samsung Electronics.
“With tailored solutions that reflect the most pressing needs of AI service providers and users, we are committed to broadening our market-leading memory lineup including computational storage, PIM and more, to fully accommodate the ever-increasing scale of data.”
“Combining our acquired knowledge and know-how from HyperCLOVA with Samsung’s semiconductor manufacturing prowess, we believe we can create an entirely new class of solutions that can better tackle the challenges of today’s AI technologies,” said Suk Geun Chung, Head of Naver Clova. “We look forward to broadening our AI capabilities and bolstering our edge in AI competitiveness through this strategic partnership.”
Other related articles
- Chip makers back CXL 3.0 for data centre memory
- AMD pushes CXL, chiplets with latest data centre processor
- Software defined memory fabric drives IP maker into chip market
