Samsung has unveiled the industry’s fastest UFS 5.0 storage solution, designed for next-generation on-device AI applications. The new standard integrates the latest embedded memory interface specification from JEDEC and reaches a bandwidth of up to 10.8 gigabytes per second (GB/s). The solution delivers a sequential read speed of up to 10.8 GB/s and a sequential […]
Hardware
Google Eyes Samsung’s 2nm Process for ‘Icefish’ TPU
Google is reportedly in talks with Samsung to manufacture a component of its next-generation AI processor using Samsung’s 2-nanometer production technology, according to a report by The Information. The chip in question, codenamed “Icefish,” is a tensor processing unit (TPU) co-designed with MediaTek, with TSMC expected to handle the main computing portion while Samsung may […]
Samsung Unveils HBM5 Architecture at Computex 2026 with New In-Package Thermal Design
Samsung has unveiled the first physical mockup of its eighth-generation high-bandwidth memory, HBM5, at the ongoing Computex 2026 in Taipei. The display, held within the Samsung Display booth, paired the next-generation AI memory with a new in-package thermal structure called Heat Path Block, or HPB. HPB addresses heat buildup at the die-to-die interface — the […]
Samsung Showcases Ultra Slim Laptop OLED Panel at Computex 2026
Samsung Display has a booth at Computex to showcase the latest display technologies, and it is also showcasing its Ultra Slim laptop OLED panel. An under-development display panel for laptops that reduces module outer-edge thickness by more than 20% compared to the current set of panels in mass production. Samsung says the slimmer profile is the […]
Samsung Ships Industry-First HBM4E Samples to Global Customers
Samsung has begun shipping samples of its HBM4E memory to major global customers, enabling Samsung to extend its high-bandwidth memory roadmap and address the increasing demand for AI infrastructure. The 12-layer HBM4E delivers a stable pin speed of 14Gbps, scalable to 16Gbps, representing an increase of performance of 20% over HBM4. Memory bandwidth reaches up […]