With broad expertise spanning DRAM, NAND, enterprise storage and relevant advanced semiconductor technologies, Samsung presented its latest AI memory portfolio and technology roadmap, including a preview of its zHBM and zNAND-O concept models, the industry-first introduction of its V10 BV-NAND with 400-plus layers and a comprehensive range of solutions designed to advance future AI infrastructure. Samsung is also featuring its AI cloud server-inspired booth at FMS 2026, where approximately 30 memory and storage technologies are on display.  

At the opening keynote event, Samsung’s Memory Business executives Jin-Yub Lee, Executive Vice President and Head of Flash Product & Technology and Kyungryun Kim, Vice President and Project Leader of the DRAM Design Team, delivered their address on next-generation 3D structures in future memory solutions.

Titled “Driving the Wave of AI Revolution: 3D Innovations in Memory & Storage Architecture,” the keynote presented Samsung’s vision to maximize AI system performance and power efficiency while addressing the rapidly growing demands of high-performance computing (HPC) and AI infrastructure.

The company also unveiled V10 BV-NAND, an architecture enabled by a new wafer bonding technology — for the first time in the industry.

Samsung’s Vision for Next-Generation 3D Memory

At FMS 2026, Samsung unveiled the industry’s first concept models of zHBM and zNAND-O, presenting its vision for the next generation of 3D memory architectures.

Designed for advanced AI computing, zHBM presents a new memory architecture that vertically stacks HBM directly above AI accelerators, moving beyond conventional designs in which HBM is positioned alongside the processor.

By minimizing the distance that data travels between the AI processor and memory, zHBM is designed to deliver higher bandwidth and improved power efficiency, enabling the ultra-fast data processing required for large-scale AI training and inference.

A next-generation interface system incorporating zHBM is expected to deliver approximately eight times the performance of HBM5. With next-generation wafer bonding technology, zHBM can achieve more than 10 times the memory density of HBM5 while enhancing energy efficiency threefold and reducing thermal resistance by more than half, maximizing the stability and power efficiency of high-capacity, high-bandwidth systems.

zHBM also supports customer-specific designs, enabling customized IP to be integrated into the interlayer between the memory and AI accelerator to expand memory capacity and enhance accelerator performance.

Building on close collaboration with customers, Samsung plans to further optimize the integration of AI processors and memory through zHBM to maximize AI system performance.

The company also introduced zNAND-O, a next-generation high-performance NAND solution built on its V-NAND technology and in development in four- and eight-layer versions. By combining high space efficiency, improved I/O performance and low latency, zNAND-O is optimized for edge AI environments supporting real-time, data-intensive AI applications.

Industry-First V10 BV-NAND

Samsung unveiled V10 BV-NAND, featuring its new Bonding V-NAND architecture. The announcement comes 13 years after the company introduced the industry’s first V-NAND technology at the 2013 Flash Memory Summit, marking another milestone in the company’s NAND innovation.

With more than 400 layers, V10 BV-NAND delivers higher performance and power efficiency while significantly increasing storage density. By applying wafer bonding technology to stack memory cells, Samsung has increased memory density by approximately 58% over the previous generation (V9).

Beyond the increased layer count, V10 BV-NAND also improves read, write and I/O performance over the previous generation, supporting high-performance, high-capacity NAND for future AI systems and applications.

AI Memory Roadmap from HBM to PIM and Enterprise Storage

Samsung also presented its latest AI memory and storage portfolio — including HBM4E, HBM5, LPDDR5X-PIM and PM1763 — highlighting its roadmap for next-generation AI computing and data center infrastructure.

Following the industry’s first mass production of HBM4 using its 1c DRAM and 4-nanometer (nm) base die technologies in February, Samsung was the first to begin shipping HBM4E samples to global customers in May, reinforcing its leadership in next-generation HBM.

Along with its HBM4E samples and HBM5 model, the company showcased its LPDDR5X-PIM, the industry’s first LPDDR memory with processing-in-memory technology. The new solution is built to perform data processing within the memory itself to improve the efficiency of both data movement and power.

The exhibition also featured Samsung’s latest enterprise storage solutions — including PM1763 and BM1773 — designed to meet the growing storage demands of AI data centers.

One-Stop Turnkey Solutions

As the world’s only integrated device manufacturer (IDM) with industry-leading capabilities spanning memory, foundry and advanced packaging, Samsung presented its end-to-end strategy for next-generation AI infrastructure, which provides customers with one-stop turnkey solutions supporting the evolving needs of the AI era.

From product design through mass production, Samsung delivers integrated development and manufacturing services that help shorten development cycles while optimizing performance and power efficiency, enabling customers to quickly bring differentiated AI semiconductor solutions to market.

The milestone sets a new benchmark for the next-generation mobile memory market as the enhanced performance is expected to allow mobile device users with significantly reduced latency and faster response times when running large language models (LLMs) in on-device AI environments.

“In the era of on-device AI, storage devices are evolving into a key driver defining AI experiences,” said Jangseok Choi, head of Memory Product Planning at Samsung Electronics. “As we successfully move beyond the development stage of the industry’s first UFS 5.0 solution, Samsung is setting a new standard for storage on the go and will continue to drive innovation for the next-generation mobile platform market.”

Generative AI is rapidly shifting from the cloud to the device, driving a surge in the scale of data required for local processing. As a result, storage is evolving from a medium used primarily to store data to core infrastructure that supports AI computation.

Samsung’s UFS 5.0 integrates the latest embedded memory interface standard from JEDEC, achieving unparalleled performance levels with the industry’s highest bandwidth of up to 10.8 gigabytes per second (GB/s).

The new storage solution delivers a sequential read speed of up to 10.8 GB/s and a sequential write speed of up to 9.5 GB/s, speeds that are respectively more than twice as fast as those of the previous UFS 4.1 standard. This significant advancement enables much faster storage and processing of large data for on-device AI applications.

Power efficiency in Samsung’s UFS 5.0 is also improved by more than 40% compared to the company’s UFS 4.1 solution. This is achieved by implementing a number of new innovations, including clock gating and multi-voltage technologies. These enhancements help to considerably reduce the power required to transfer the same amount of data, drastically lowering overall power consumption and extending the battery life of next-generation mobile devices.

Samsung has engineered the UFS 5.0 solution into an ultra-compact package measuring just 7.5mm x 13mm x 0.9mm — making it 16.7% smaller than its predecessor. This form factor significantly boosts design flexibility and internal space utilization for a wide range of applications, including mobile, wearable and extended reality (XR) devices.

Samsung will begin mass production of its UFS 5.0 in the fourth quarter of this year in a variety of capacities up to one terabyte (TB). Through this breakthrough in UFS 5.0 technology, Samsung is staying ahead of industry needs and plans to scale up supply to meet the growth of next-generation device markets — ranging from flagship smartphones to XR headsets and AI wearables.

Samsung Electronics, the world leader in advanced memory technology, today announced that it is introducing the industry’s first embedded Universal Flash Storage (eUFS) solution for use in next-generation automotive applications. Consisting of 128-gigabyte (GB) and 64GB versions, the new eUFS solution has been designed for advanced driver-assistance systems (ADAS), next-generation dashboards and infotainment systems that provide comprehensive connected features for drivers and passengers worldwide.

“We are taking a major step in accelerating the introduction of next-generation ADAS and automotive infotainment systems by offering the industry’s first eUFS solution for the market much earlier than expected,” said Jinman Han, Senior Vice President of Memory Product Planning & Application Engineering at Samsung Electronics. “Samsung is taking the lead in the growth of the memory market for sophisticated automotive applications, while continuing to deliver leading-edge UFS solutions with higher performance, density and reliability.”

Embedded UFS solutions have been used in a variety of mobile applications since early 2015, when Samsung introduced 128GB embedded memory based on the JEDEC UFS 2.0 standard, for the first time in the industry. Since then, the high performance and proven quality of UFS has led to its wide adoption in large numbers of mobile devices from flagship smartphones initially, to also now in mid-market smartphones.

Configured on the most up-to-date UFS standard (JEDEC UFS 2.1), the new Samsung eUFSwill provide advanced data transfer speeds and robust data reliability. For example, the new Samsung 128GB eUFS can read data at up to 850 megabytes per second (MB/s), which is approximately 3.4 times faster than the 250MB/s read speed of today’s eMMC 5.0 solutions. It also offers about 6.3 times faster random reading than eMMC at 45,000 IOPS. This will contribute to significantly enhanced performance in upcoming automotive infotainment systems for better managing audio content, increasing navigation responsiveness, accessing Internet-enabled traffic and weather reports, improving handling of hands-free voice commands, and speeding up rear-seat social media interplay.

The new eUFS solution also features an efficient and reliable error-handling process, which is essential for next-generation in-vehicle infotainment. Based on the MIPI UniPro^®* protocol, the eUFS enables detecting and recovering from I/O error on hardware layers, without having to involve the host software or restarting tasks.

In addition, the Samsung eUFS supports advanced data refresh and temperature notification features for superior system reliability. The advanced data refresh operation allows a choice of refresh methods, and provides information on the refresh unit, frequency and progress for the host device’s control. This enables optimal data reliability, an essential element of automotive applications.

When it comes to thermal management, the Samsung eUFS equips the temperature sensor inside the controller to enable highly reliable device temperature control. This prevents the eUFS from crossing well-defined upper and lower temperature boundaries, thereby allowing its NAND cells to flawlessly function within a tough automotive temperature environment.

In light of the eUFS’ high performance and reliability, Samsung expects rapid adoption in the automotive market. Samsung will continue to satisfy the growing storage needs of leading automotive manufacturers by offering a variety of advanced eUFS lineups, while more thoroughly addressing the ever-increasing demand for leading-edge memory solutions in other market segments, too.

* Editor’s Note: MIPI UniPro^® is a general purpose, unified protocol that services a wide range of interface needs in mobile and connected devices. The interface was developed by the MIPI Alliance UniPro Working Group and has been available since 2007. Its current version, v1.61, was released in 2015. For more information, please visit https://mipi.org.

Samsung Electronics, the world leader in advanced memory technology, today announced that it is increasing the production volume of its 8-gigabyte (GB) High Bandwidth Memory-2 (HBM2) to meet growing market needs across a wide range of applications including artificial intelligence, HPC (high-performance computing), advanced graphics, network systems and enterprise servers.

“By increasing production of the industry’s only 8GB HBM2 solution now available, we are aiming to ensure that global IT system manufacturers have sufficient supply for timely development of new and upgraded systems,” said Jaesoo Han, executive vice president, Memory Sales & Marketing team at Samsung Electronics. “We will continue to deliver more advanced HBM2 line-ups, while closely cooperating with our global IT customers.”

Samsung’s 8GB HBM2 delivers the highest level of HBM2 performance, reliability and energy efficiency in the industry, underscoring the company’s commitment to DRAM innovation. Among the HBM2 and TSV (Through Silicon Via) technologies that were utilized for the latest DRAM solution, more than 850 of them have been submitted for patents or already patented.

The 8GB HBM2 consists of eight 8-gigabit (Gb) HBM2 dies and a buffer die at the bottom of the stack, which are all vertically interconnected by TSVs and microbumps. With each die containing over 5,000 TSVs, a single Samsung 8GB HBM2 package has over 40,000 TSVs. The utilization of so many TSVs, including spares, ensures high performance, by enabling data paths to be switched to different TSVs when a delay in data transmission occurs. The HBM2 is also designed to prevent overheating beyond certain temperature to guarantee high reliability.

First introduced in June 2016, the HBM2 boasts a 256GB/s data transmission bandwidth, offering more than an eight-fold increase over a 32GB/s GDDR5 DRAM chip. With capacity double that of 4GB HBM2, the 8GB solution contributes greatly to improving system performance and energy efficiency, offering ideal upgrades to data-intensive, high-end computing applications that deal with machine learning, parallel computing and graphics rendering.

In meeting increasing market demand, Samsung anticipates that its volume production of the 8GB HBM2 will cover more than 50 percent of its HBM2 production by the first half of next year.

Samsung Electronics, the world leader in advanced memory technology, announced today that it has begun mass producing the industry’s first NVMe* PCIe solid state drive (SSD) in a single ball grid array (BGA) package, for use in next-generation PCs and ultra-slim notebook PCs. The new BGA NVMe SSD, named PM971-NVMe, features an extremely compact package that contains all essential SSD components including NAND flash memory, DRAM and controller while delivering outstanding performance.

“Samsung’s new BGA NVMe SSD triples the performance of a typical SATA SSD, in the smallest form factor available, with storage capacity reaching up to 512GB,” said Jung-bae Lee, senior vice president, Memory Product Planning & Application Engineering Team, Samsung Electronics. “The introduction of this small-scale SSD will help global PC companies to make timely launches of slimmer, more stylish computing devices, while offering consumers a more satisfactory computing environment.”

Configuring the PM971-NVMe SSD in a single BGA package was enabled by combining 16 of Samsung’s 48-layer 256-gigabit (Gb) V-NAND flash chips, one 20-nanometer 4Gb LPDDR4 mobile DRAM chip and a high-performance Samsung controller. The new SSD is 20mm x 16mm x 1.5mm and weighs only about one gram (an American dime by comparison weighs 2.3 grams). The single-package SSD’s volume is approximately a hundredth of a 2.5” SSD or HDD, and its surface area is about a fifth of an M.2 SSD, allowing much more design flexibility for computing device manufacturers.

In addition, the PM971-NVMe SSD delivers a level of performance that easily surpasses the speed limit of a SATA 6Gb/s interface. It enables sequential read and write speeds of up to 1,500MB/s (megabytes per second) and 900MB/s respectively, when TurboWrite** technology is used. The performance figures can be directly compared to transferring a 5GB-equivalent, Full-HD movie in about 3 seconds or downloading it in about 6 seconds. It also boasts random read and write IOPS (input output operations per second) of up to 190K and 150K respectively, to easily handle high-speed operations. A hard drive, by contrast, will only process up to 120 IOPS in random reads, making the new Samsung SSD more than 1500 times faster than an HDD in this regard.

The PM971-NVMe SSD line-up will be available in 512GB, 256GB and 128GB storage options. Samsung will start providing the new SSDs to its customers this month worldwide.

As a leading SSD provider, Samsung has a history of introducing advanced SSDs ahead of the industry. In June 2013, Samsung introduced XP941 SSD in M.2 (mini PCI-Express 2.0) form factor (80mm x 22mm), which was also the industry’s first PCIe SSD for PCs. Now, Samsung plans to rapidly expand its market base in the next-generation premium notebook PC sector with the new high-performance, BGA package, NVMe SSD. Later this year, Samsung plans to introduce more high-capacity and ultra-fast NVMe SSDs to meet increasing customer needs for improved performance and greater density.

* Often shortened as NVMe, NVM Express (Non-Volatile Memory Express) is an optimized, high performance, scalable host controller interface with a streamlined register interface and command set designed for enterprise, datacenter and client systems that use non-volatile memory storage. For more information, please visit www.nvmexpress.org

** TurboWrite is a Samsung proprietary technology that temporarily uses certain portions of an SSD as a write buffer. TurboWrite delivers better PC experiences as users can enjoy much faster sequential write speeds.