Computer Express Link (CXL) improves how CPUs and GPUs interact with memory and accelerators, standardizing communication across devices, reducing delays, and making systems faster and more capable of handling large amounts of data – especially important for applications requiring rapid data processing, such as AI.
At a recent media briefing, Jangseok Choi, Vice President of Samsung‘s new business planning team, revealed the company was forging ahead with its plans to begin making and shipping CXL enabled memory modules.
“We plan to mass-produce 256 GB DRAM supporting CXL 2.0 within this year. We expect the CXL market to start blooming in the second half and explosively grow from 2028,” Choi told media.
A decade in the making
Samsung predicts that the adoption of CXL technology will result in an eight to tenfold increase in memory capacity per server, translating to a substantial leap in computational capabilities. CXL, “expands the highway linking the CPU and memory chips from two to three lanes to more than eight lanes,” a Samsung official explained to The Korea Economic Daily.
Samsung’s CXL 2.0 DRAM, released in May 2023, supports memory pooling, a memory management technique that binds multiple CXL memory blocks on a server platform to form a pool and allows hosts to dynamically allocate memory from the pool as needed, leading to more efficient use of memory capacity and optimized resource allocation.
Both Micron and SK Hynix are developing CXL-based memory products, but “As the only memory maker on the CXL consortium board, Samsung is committed to further expanding the CXL ecosystem through partnerships with data centers, servers, and chipset companies across the industry,” Choi said.
“Samsung has been working to develop and mass-produce high-quality CXL for more than a decade,” he added. “We are testing our products with our partners for performance verification.”