KIOXIA Sampling UFS 5.0 Embedded Flash Memory Devices for Next-Generation Mobile Applications

­KIOXIA Europe, a world leader in memory solutions, today announced that KIOXIA Corporation has begun shipping evaluation samples of embedded flash memory compatible with the next-generation UFS standard, UFS 5.0, which is currently being standardized by JEDEC.

UFS 5.0 is a new standard for embedded flash storage currently being developed by JEDEC to meet the performance requirements of next-generation mobile devices such as high-end smartphones equipped with on-device AI functions. It utilizes MIPI M-PHY version 6.0 for the physical layer and UniPro version 3.0 for the protocol. M-PHY version 6.0 introduces the new HS-GEAR6 mode, theoretically supporting an interface speed of up to 46.6Gbps per lane; with 2 lanes, UFS 5.0 can achieve approximately 10.8GB/s of effective read/write performance.

The evaluation samples incorporate an in-house newly developed controller for UFS 5.0 and KIOXIA’s 8th-generation BiCS FLASH™ and are available in capacities of 512GB and 1TB. The package has been newly designed with a small 7.5 x 13 mm size, contributing to board space efficiency and design flexibility.

The samples are provided to customers who are developing UFS 5.0-compatible host systems, enabling them to evaluate performance and conduct interoperability testing.

KIOXIA will continue to introduce new flash memory technologies into its UFS products to meet the increasing demands for larger capacity and higher performance in the mobile market.

“As Large Language Models (LLMs) move onto mobile devices, storage must behave more like high-speed system memory to prevent processing bottlenecks,” said Axel Störmann, Chief Technology Officer & Vice President, KIOXIA Europe. "The massive data throughput of KIOXIA’s UFS 5.0 embedded flash memory device enables faster task completion and allows the device to return to a low-power idle state sooner. This high efficiency and fast processing speed are an essential combination for customers developing generative AI applications on battery-powered devices.”