• Various memory products for AI data centers, on-device, automotive businesses on display

Seoul, March 19, 2025

SK hynix Inc. (or “the company”, www.skhynix.com) announced today that it will participate in the GTC 2025, a global AI conference taking place March 17-21 in San Jose, California, with a booth titled “Memory, Powering AI and Tomorrow”.

The company will present HBM and other memory products for AI data centers and on-device¹ and memory solutions for automotive business essential for AI era.

¹On-device: a technology that implements certain functions on the device itself, instead of going through computation by a physically separated server. As for the on-device AI, a smart device’s direct collection and computation of information allows fast reactions of the AI performance, while promising an improved customized AI service

Among the industry-leading AI memory technology to be displayed at the show are 12-high HBM3E and SOCAMM², a new memory standard for AI servers.

²SOCAMM(Small Outline Compression Attached Memory Module): a low-power DRAM-based memory module for AI server

At the event, top company executives led by Chief Executive Officer Kwak Noh-Jung, President, Head of AI Infra and Chief Marketing Officer Juseon (Justin) Kim and Head of Global S&M Lee Sangrak will meet with the leaders of the global AI industry to enhance collaboration.

Following the industry’s first mass production and supply of the 12-high HBM3E, SK hynix is now planning to complete the preparatory works for large-scale production of the 12-high HBM4 within the second half for immediate start of supply to order. At GTC 2025, a model of the 12-high HBM4, which is under development, will also be displayed.

“We are proud to present our line-up of industry-leading products at GTC 2025,” President & Head of AI Infra Juseon (Justin) Kim said. “With a differentiated competitiveness in the AI memory space, we are on track to bring our future as the Full Stack AI Memory Provider³ forward.”

³Full Stack AI Memory Provider: SK hynix’s vision to be a provider of a full-range of AI memory products and technologies

About SK hynix Inc.

SK hynix Inc., headquartered in Korea, is the world’s top tier semiconductor supplier offering Dynamic Random Access Memory chips (“DRAM”) and flash memory chips (“NAND flash”) for a wide range of distinguished customers globally. The Company’s shares are traded on the Korea Exchange, and the Global Depository shares are listed on the Luxembourg Stock Exchange. Further information about SK hynix is available at www.skhynix.com, news.skhynix.com.

Media Contact

SK hynix Inc.
Global Public Relations

Technical Leader
Kanga Kong, Minseok Jang, Sooyeon Lee
E-Mail: global_newsroom@skhynix.com

The post SK hynix Showcases Industry-Leading Memory Technology at GTC 2025 first appeared on SK hynix Newsroom.

• The company plans to supply the highest-performing, highest-capacity 12-layer HBM3E to customers by the end of the year
• DRAM chips made 40% thinner to increase capacity by 50% at the same thickness as the previous 8-layer product
• The company to continue HBM’s success with outstanding product performance and competitiveness

Seoul, September 26, 2024

SK hynix Inc. (or “the company”, www.skhynix.com) announced today that it has begun mass production of the world’s first 12-layer HBM3E product with 36GB¹, the largest capacity of existing HBM² to date.

¹Previously, the maximum capacity of HBM3E was 24GB from eight vertically stacked 3GB DRAM chips.
²HBM (High Bandwidth Memory): This high-value, high-performance memory vertically interconnects multiple DRAM chips and dramatically increases data processing speed in comparison to traditional DRAM products. HBM3E is the extended version of HBM3, the fourth generation product that succeeds the previous generations of HBM, HBM2 and HBM2E.

The company plans to supply mass-produced products to customers within the year, proving its overwhelming technology once again six months after delivering the HBM3E 8-layer product to customers for the first time in the industry in March this year.

SK hynix is the only company in the world that has developed and supplied the entire HBM lineup from the first generation (HBM1) to the fifth generation (HBM3E), since releasing the world’s first HBM in 2013. The company plans to continue its leadership in the AI memory market, addressing the growing needs of AI companies by being the first in the industry to mass-produce the 12-layer HBM3E.

According to the company, the 12-layer HBM3E product meets the world’s highest standards in all areas that are essential for AI memory including speed, capacity and stability. SK hynix has increased the speed of memory operations to 9.6 Gbps, the highest memory speed available today. If ‘Llama 3 70B’³, a Large Language Model (LLM), is driven by a single GPU equipped with four HBM3E products, it can read 70 billion total parameters 35 times within a second.

³Llama 3: Open-source LLM released by Meta in April 2024, with 3 sizes in total: 8B (Billion), 70B, and 400B.

SK hynix has increased the capacity by 50% by stacking 12 layers of 3GB DRAM chips at the same thickness as the previous eight-layer product. To achieve this, the company made each DRAM chip 40% thinner than before and stacked vertically using TSV⁴ technology.

The company also solved structural issues that arise from stacking thinner chips higher by applying its core technology, the Advanced MR-MUF⁵ process. This allows to provide 10% higher heat dissipation performance compared to the previous generation, and secure the stability and reliability of the product through enhanced warpage controlling.

⁴TSV (Through Silicon Via): This advanced packaging technology links upper and lower chips with an electrode that vertically passes through thousands of fine holes on DRAM chips.
⁵MR-MUF (Mass Reflow Molded Underfill): The process of stacking semiconductor chips, injecting liquid protective materials between them to protect the circuit between chips, and hardening them. The process has proved to be more efficient and effective for heat dissipation, compared with the method of laying film-type materials for each chip stack. SK hynix’s advanced MR-MUF technology is critical to securing a stable HBM mass production as it provides good warpage control and reduces the pressure on the chips being stacked.

“SK hynix has once again broken through technological limits demonstrating our industry leadership in AI memory,” said Justin Kim, President (Head of AI Infra) at SK hynix. “We will continue our position as the No.1 global AI memory provider as we steadily prepare next-generation memory products to overcome the challenges of the AI era.”

About SK hynix Inc.

SK hynix Inc., headquartered in Korea, is the world’s top-tier semiconductor supplier offering Dynamic Random Access Memory chips (“DRAM”), flash memory chips (“NAND flash”), and CMOS Image Sensors (“CIS”) for a wide range of distinguished customers globally. The company’s shares are traded on the Korea Exchange, and the Global Depository shares are listed on the Luxembourg Stock Exchange. Further information about SK hynix is available at www.skhynix.com, news.skhynix.com.

Media Contact

SK hynix Inc.
Global Public Relations

Technical Leader
Sooyeon Lee
E-Mail: global_newsroom@skhynix.com

Technical Leader
Kanga Kong
E-Mail: global_newsroom@skhynix.com

The post SK hynix Begins Volume Production of the World’s First 12-Layer HBM3E first appeared on SK hynix Newsroom.

FMS 2024 features a broader focus on different memory types compared to previous years

SK hynix has returned to Santa Clara, California to present its full array of groundbreaking AI memory technologies at FMS: the Future of Memory and Storage (FMS) 2024 from August 6–8. Previously known as Flash Memory Summit, the conference changed its name to reflect its broader focus on all types of memory and storage products amid growing interest in AI. Bringing together industry leaders, customers, and IT professionals, FMS 2024 covers the latest trends and innovations shaping the memory industry.

Participating in the event under the slogan “Memory, The Power of AI,” SK hynix is showcasing its outstanding memory capabilities through a keynote presentation, multiple technology sessions, and product exhibits.

Keynote Presentation: Envisioning the Future of AI With Leading Memory & Storage Solutions

Keynote presentations have always been a highlight at FMS. The talks act as an important forum for attendees to learn about emerging memory and storage technologies from industry leaders. Due to its leadership in the AI memory field, SK hynix was selected to give a keynote presentation titled “AI Memory and Storage Solution Leadership and Vision for the AI Era” at the newly expanded event.

Held on the first day of FMS 2024, the keynote was delivered by Vice President Unoh Kwon, head of HBM Process Integration (PI) and Vice President Chunsung Kim, head of SSD Program Management Office (PMO). The pair provided insights into the company’s DRAM and NAND flash solutions which aim to solve the pain points of generative AI and promote continued development of AI. These pain points include maximizing the efficiency of AI training and inference¹ while minimizing floor space and power utilization for storing data.

¹AI inference: The process of running live data through a trained AI model to make a prediction or solve a task.

Kwon and Kim delivering their keynote on SK hynix’s leading AI memory products

Each speaker covered a particular type of memory. Kwon touched on the company’s DRAM memory products that are optimized for AI systems such as HBM², CXL®³, and LPDDR5T⁴. Meanwhile, Kim introduced the company’s best-in-class NAND flash storage devices including its SSD and UFS⁵ solutions, which will continue to be crucial for AI applications in the future.

²High Bandwidth Memory (HBM): A high-value, high-performance product that revolutionizes data processing speeds by connecting multiple DRAM chips with through-silicon via (TSV).
³Compute Express Link^® (CXL^®): A PCIe-based next-generation interconnect protocol on which high-performance computing systems are based.
⁴Low Power Double Data Rate 5 Turbo (LPDDR5T): Low-power DRAM for mobile devices aimed at minimizing power consumption and featuring low voltage operation. LPDDR5T is an upgraded product of the LPDDR5X and will be succeeded by LPDDR6.
⁵Universal Flash Storage (UFS): A high-performance interface for computing and mobile systems which require low power consumption.

In addition to its keynote, SK hynix also held five sessions that took a deeper look into its next-generation products set to solidify the company’s AI technology leadership. These sessions covered a variety of topics, including the company’s DRAM, SSD, and CXL solutions.

Product Booth: Presenting the Industry’s Best AI Memory

SK hynix’s booth at FMS 2024 consists of four sections showcasing many of the products which featured in the company’s keynote and session talks. One of the booth’s highlights is the samples of the 12-layer HBM3E, the next-generation AI memory solution which is expected to be mass-produced in the third quarter of 2024. The company is also holding demonstrations of select products with its partners’ systems, highlighting its strong collaboration with various major tech companies.

The AI Memory and Storage section includes industry-leading solutions such as SK hynix’s HBM3E and eSSD portfolio

• AI Memory and Storage: Features SK hynix’s flagship AI memory products such as samples of its 12-layer HBM3E, which is set to be the same height as the previous 8-layer version under JEDEC⁶ standards. The section also includes GDDR6-AiM⁷, a product suitable for machine learning due to its computational capabilities and rapid processing speeds, and the ultra-low power LPDDR5T optimized for on-device AI. Storage solutions on display include the PCIe Gen5-based eSSD PS1010, which is ideal for AI, big data, and machine learning due to its rapid sequential read speed.

⁶Joint Electron Device Engineering Council (JEDEC): A U.S.-based standardization body that is the global leader in developing open standards and publications for the microelectronics industry.
⁷Accelerator in Memory (AiM): A special-purpose hardware made using processing and computation chips.

At the NAND Tech, Mobile, and Automotive section, attendees can see products such as the company’s 321-layer NAND and ZUFS 4.0

• NAND Tech, Mobile, and Automotive: This section includes solutions such as the world’s highest 321-layer wafer technology as well as triple-level cell (TLC) and QLC NAND. Mobile technologies are also showcased including ZUFS⁸ 4.0, an industry-best NAND product optimized for on-device AI⁹ which boosts a smartphone’s operating system speed compared to standard UFS.

⁸Zoned Universal Flash Storage (ZUFS): A NAND flash product that improves efficiency of data management. It optimizes data transfer between an operating system and storage devices by storing data with similar characteristics in the same zone of the UFS.
⁸On-device AI: A technology that implements AI functions on the device itself, instead of going through computation by a physically separated server.

The AI PC and CMS 2.0 section features a demonstration of the company’s industry-leading SSD, PCB01

• AI PC and CMS 2.0: Attendees can see a system demonstration of the industry-best SSD PCB01, which is able to efficiently process large AI computing tasks when applied to on-device AI PCs. In addition, CMS¹⁰ 2.0, a next-generation memory solution that boasts equivalent data processing capabilities as a CPU, is applied to a vector database¹¹.

¹⁰Computational Memory Solution (CMS): A product that integrates computational functions into CXL memory.
¹¹Vector Database: A collection of data stored as mathematical representations, or vectors. As similar vectors are grouped together, vector databases can make low-latency inquiries, making them ideal for AI.

The OCS, Niagara, CMM section displays innovative solutions such as Niagara 2.0 and HMSDK

• OCS, Niagara, and CMM: This section features a demonstration of OCS¹² technology which enhances the data analysis and pooled memory solution Niagara 2.0¹³. It also includes a demonstration of CMM¹⁴– DDR5¹⁵, which expands system bandwidth by 50% and capacity by up to 100% compared to systems only equipped with DDR5.

¹²Object-based Computational Storage (OCS): A new computational storage platform for data analytics in high-performance computing. OCS has not only high scalability but also data-aware characteristics that enable it to perform analytics independently without help from compute nodes.
¹³Niagara 2.0: A solution that connects multiple CXL memories together to allow numerous hosts such as CPUs and GPUs to optimally share their capacity. This eliminates idle memory usage while reducing power consumption.
¹⁴CXL Memory Module (CMM): A new standardized interface that has an advantage in scalability and helps increase the efficiency of CPUs, GPUs, accelerators, and memory.
¹⁵Double Data Rate 5 (DDR5): A server DRAM that effectively handles the increasing demands of larger and more complex data workloads by offering enhanced bandwidth and power efficiency compared to the previous generation, DDR4.

Super Women Conference: Cherishing Diversity in the Memory & Storage Industry

Haesoon Oh delivers the keynote at the FMS Super Women Conference

SK hynix also co-sponsored the FMS Super Women Conference, an event held on the sidelines of FMS 2024 which celebrates the achievements of female leaders and promotes diversity in the memory industry. Head of NAND Advanced PI Haesoon Oh, the company’s first female executive-level research fellow, delivered a keynote address on the company’s next-generation innovations and the importance of understanding diversity.

Paving the Way Forward in the AI Era

At FMS 2024, SK hynix underlined its commitment to lead the industry by providing integrated AI memory solutions and expanding its expertise in the sector. Collaborating with other leading partners, the company will strive to provide customers with the best possible solutions that match their rapidly changing needs.

The post SK hynix Presents Extensive AI Memory Lineup at Expanded FMS 2024 first appeared on SK hynix Newsroom.