The world runs on data—a ceaseless tide of ones and zeros surging through networks, powering everything from streaming services to AI. To handle this data deluge, data centers must employ more advanced memory solutions that meet ever-growing performance demands.

However, traditional methods of scaling memory are facing limitations. The constraints of processors and memory technologies, coupled with escalating costs and power consumption for data centers, have highlighted the need for a revolutionary approach. Enter Compute Express Link^® (CXL^®), a transformative memory interconnect technology designed to tackle the challenges of the AI era.

This Rulebreakers’ Revolutions  episode will cover SK hynix’s development of CXL solutions, detailing how the company overcame obstacles, such as a lack of industry specifications, to become a leader in the CXL field and a key contributor to the CXL ecosystem.

Mission: Harnessing New Interconnect Tech for Memory Scaling

In the AI era, data centers need to continuously expand their memory capacity to handle ever-growing volumes of data. However, scaling memory capacity through traditional methods is becoming prohibitively expensive and inefficient. For example, adding terabyte (TB)-scale memory to a single CPU system can significantly increase the total cost of ownership¹ (TCO) and power consumption. Attempting to address this by increasing memory channels or integrating higher capacity memory often results in even greater power usage and heat generation, further inflating cooling system and management costs. This has underlined the need for innovative memory system designs which can process data faster, more efficiently, and cost effectively.

¹Total cost of ownership: The complete cost of acquiring, operating, and maintaining an asset, including purchase, energy, and maintenance expenses.

Data center memory capacity needs to increase to handle the growing demands of the AI era

Over the past decade, the industry has been developing new memory interconnect technologies to meet this market demand. Memory interconnect technology refers to the method by which processors exchange data with memory, playing a critical role in determining the speed and efficiency of data processing. In traditional memory architectures, memory is physically connected to a nearby single processor, which can lead to an over-provision of memory resources when applications are not using the memory. New memory interconnect technologies such as CXL can overcome this issue by allowing multiple processors to share memory for improved efficiency.

This has led to great interest in CXL, however developing the technology would prove challenging as there was no precedent for the process and initially no industry-established specifications. Without the JEDEC² specifications which are generally provided for DRAM products, the development process for CXL was fundamentally more complex than usual.

²JEDEC Solid State Technology Association: With over 350 member companies, JEDEC is the global leader in developing open standards for the microelectronics industry.

Faced with having to develop new CXL products without industry specifications to break the barriers of memory scaling, SK hynix tapped into its internal expertise and collaborated with industry partners.

Into the Unknown: Developing Pioneering CXL Tech From Scratch

Following the introduction of CXL in 2019, SK hynix soon recognized the technology’s capability to meet ever-growing memory scaling needs. As an open industry-standard interconnect, CXL unifies the interfaces of different system devices such as memory, storage, and processors. It supports features such as memory sharing, allowing multiple processors to access the same memory for improved data sharing, and memory pooling, in which memory from a common pool is assigned to processors for enhanced efficiency. Furthermore, CXL also enables memory switching, allowing hundreds of devices such as processors to share memory resources while independently processing data.

In addition to these innovative features, SK hynix became further convinced of CXL’s immense potential after observing increased market and customer commitment to the technology and identifying its promise in addressing technical and cost challenges. However, the company had to begin the project by overcoming a significant obstacle—a lack of industry specifications. SK hynix therefore soon set about developing its own basic requirement document after participating in CXL standardization activities and working with customers to define specifications. The company also collaborated with CXL controller companies to define controller requirements for the specifications document. Furthermore, the company has worked with JEDEC and the CXL Consortium³ to enhance DRAM-related specifications for industry CXL standards.

³CXL Consortium: An open industry standards group that develops technical specifications for CXL.

SK hynix’s CXL technology overcomes memory scaling challenges by expanding system capacity and bandwidth

Having helped set industry standards and develop relevant specifications, the company has accelerated its CXL development. For this process, SK hynix has identified key criteria to meet customer requirements—cost efficiency, high capacity, optimized bandwidth, and reliability.

First, cost efficiency is paramount in CXL development. To counteract the high cost of CXL controllers, it is crucial to minimize the costs of memory media such as modules. As high capacity is essential to facilitate large-scale data processing, the company determined CXL memory should offer storage two to four times larger than existing DDR products. Furthermore, bandwidth design must be optimized to utilize the full performance potential of CXL modules. Finally, reliability and data integrity must match the high standards of the host memory to earn customer trust.

To meet these criteria, multiple departments across SK hynix are working on making terabyte-scale memory more affordable and efficient. This includes pioneering memory pooling technologies that enable resource sharing among multiple devices and developing NMP⁴ technologies to handle data close to its source. These innovations are poised to deliver significant benefits to applications such as high-performance computing (HPC), in-memory databases, and AI.

⁴Near-memory processing (NMP): A technique that performs computations near data storage, reducing latency and boosting performance in high-bandwidth tasks like AI and HPC.

Through these efforts, SK hynix has been able to advance the development of groundbreaking CXL products which are set to revolutionize the memory field.

SK hynix’s Growing Product Lineup Driving the Future of CXL

Since developing its first DDR5-based CXL sample in 2022, SK hynix has been strengthening its CXL portfolio which includes the innovative CXL Memory Module-Double Data Rate 5 (CMM-DDR5). Leveraging high-speed PCIe Gen5 connections, CMM-DDR5 ensures smooth and rapid data processing. Available with up to 128 GB of storage, CMM-DDR5 also offers the high capacity required for the demands of today’s AI and HPC applications. In addition, the module boasts high levels of power efficiency and security.

Real-world performance tests highlight the transformative impact of CMM-DDR5. The product can expand system bandwidth by up to 82% and capacity by up to 100% compared to systems equipped with only DDR5 DRAM. Tests also showed how AI workloads experienced a 31% increase in token per second performance and that HPC enjoyed a 33% improvement in throughput efficiency. As well as providing outstanding performance, CMM-DDR5 has aligned with both JEDEC and CXL Consortium standards. Currently, the verification and certification of CMM-DDR5 is being carried out by customers as the product moves closer to mass production.

SK hynix’s CXL-based CMM-DDR5 enhances AI and HPC performance

SK hynix’s other CXL solutions include Niagara 2.0, an integrated hardware and software solution that allows multiple hosts to efficiently share large memory pools to minimize unused or underutilized memory. Furthermore, CXL Memory Module-Ax (CMM-Ax), a high-performance memory module optimized for computational workloads, is notable for improving AI and data center efficiency.

Beyond hardware advancements, SK hynix has developed the Heterogeneous Memory Software Development Kit (HSMDK) to maximize the potential of its CXL memory. This software toolkit has even been integrated into Linux’s operating system, further enhancing its accessibility and usability. The development of both hardware and software solutions as well as its standardization efforts highlights how SK hynix is committed to creating a thriving CXL ecosystem.

Rulebreaker Interview: “Thomas” Wonha Choi, Next-Gen Memory & Storage

In an interview with the SK hynix Newsroom, Distinguished Engineer⁵ (DE) “Thomas” Wonha Choi of Next-Gen Memory & Storage discussed the company’s rulebreaking mentality for developing CXL technology. Responsible for standardization efforts with JEDEC and the CXL Consortium and pathfinding next-generation memory such as CXL, Choi spoke about CXL’s development and its future impact.

⁵Distinguished Engineer: Senior SK hynix engineers who excel in their fields and are tasked with solving technical challenges and mentoring the next generation.

<Other articles from this series>

[Rulebreakers’ Revolutions] How MR-MUF’s Heat Control Breakthrough Elevated HBM to New Heights

[Rulebreakers’ Revolutions] How SK hynix Broke Barriers in Mobile DRAM Scaling With World-First HKMG Application

[Rulebreakers’ Revolutions] Innovative Design Scheme Helps HBM3E Reach New Heights

[Rulebreakers’ Revolutions] How SK hynix’s Server DRAM Validation Process Succeeds in a Diverse Server CPU Market

[Rulebreakers’ Revolutions] Flexible & Collaborative eSSD Virtualization Development for Today’s Data Centers

[Rulebreakers’ Revolutions] How SK hynix’s Design Innovations Pushed GDDR7 to New Limits of Speed

The post [Rulebreakers’ Revolutions] How CXL Tech Expands Data Center Memory Scaling Boundaries in the AI Era first appeared on SK hynix Newsroom.

• SK hynix to showcase technological capabilities, participating in the world’s largest consumer electronics show, CES 2025, from January 7-10
• Featuring a wide range of products driving the AI era, from HBM, the core of AI infrastructure, to next-gen memories like PIM
• Company to present new possibilities in the AI era through technological innovation and provide irreplaceable value

Seoul, January 3, 2025

SK hynix Inc. (or “the company”, www.skhynix.com) announced today that it will showcase its innovative AI memory technologies at CES 2025, to be held in Las Vegas from January 7 to 10 (local time).

A large number of C-level executives, including CEO Kwak Noh-Jung, CMO (Chief Marketing Officer) Justin Kim and Chief Development Officer (CDO) Ahn Hyun, will attend the event. “We will broadly introduce solutions optimized for on-device AI and next-generation AI memories, as well as representative AI memory products such as HBM and eSSD at this CES,” said Justin Kim. “Through this, we will publicize our technological competitiveness to prepare for the future as a ‘Full Stack AI Memory Provider¹’.”

¹Full Stack AI Memory Provider: Refers to an all-round AI memory provider, which provides comprehensive AI-related memory products and technologies

SK hynix will also run a joint exhibition booth with SK Telecom, SKC and SK Enmove, under the theme “Innovative AI, Sustainable Tomorrow.” The booth will showcase how SK Group’s AI infrastructure and services are transforming the world, represented in waves of light.

SK hynix, which is the world’s first to produce 12-layer HBM products for 5th generation and supply them to customers, will showcase samples of HBM3E 16-layer products, which were officially developed in November last year. This product uses the advanced MR-MUF process to achieve the industry’s highest 16-layer configuration while controlling chip warpage and maximizing heat dissipation performance.

In addition, the company will display high-capacity, high-performance enterprise SSD products, including the ‘D5-P5336’ 122TB model developed by its subsidiary Solidigm in November last year. This product, with the largest existing capacity, high power and space efficiency, has been attracting considerable interest from AI data center customers.

“As SK hynix succeeded in developing QLC²(Quadruple Level Cell)-based 61TB products in December, we expect to maximize synergy based on a balanced portfolio between the two companies in the high-capacity eSSD market” said Ahn Hyun, CDO at SK hynix. The company will also showcase on-device AI products such as ‘LPCAMM2³’ and ‘ZUFS 4.0⁴,’ which improve data processing speed and power efficiency to implement AI in edge devices like PCs and smartphones. The company will also present CXL and PIM (Processing in Memory) technologies, along with modularized versions, CMM(CXL Memory Module)-Ax and AiMX⁵, designed to be core infrastructures for next-generation data centers.

²QLC: NAND flash is divided into SLC (Single Level Cell), MLC (Multi Level Cell), TLC (Triple Level Cell), QLC (Quadruple Level Cell), and PLC (Penta Level Cell) depending on how much information is stored in one cell. As the amount of information stored increases, more data can be stored in the same area.
³Low Power Compression Attached Memory Module 2 (LPCAMM2): LPDDR5X-based module solution that provides power efficiency and high performance as well as space savings. It has the performance effect of replacing two existing DDR5 SODIMMs with one LPCAMM2.
⁴Zoned Universal Flash Storage (ZUFS): A NAND Flash product that improves efficiency of data management. The product optimizes data transfer between an operating system and storage devices by storing data with similar characteristics in the same zone of the UFS, a flash memory product for various electronic devices such as digital camera and mobile phone.
⁵Accelerator-in-Memory based Accelerator (AiMX): SK hynix’s accelerator card product that specializes in large language models using GDDR6-AiM chips

In particular, CMM-Ax is a groundbreaking product that adds computational functionality to CXL’s advantage of expanding high-capacity memory, contributing to improving performance and energy efficiency of the next-generation server platforms⁶.

⁶Platform: Refers to a computing system that integrates both hardware and software technologies. It includes all key components necessary for computing, such as the CPU and memory.

“The changes in the world triggered by AI are expected to accelerate further this year, and SK hynix will produce 6^th generation HBM (HBM4) in the second half of this year to lead the customized HBM market to meet the diverse needs of customers,” said Kwak Noh-Jung, CEO at SK hynix. “We will continue to do our best to present new possibilities in the AI era through technological innovation and provide irreplaceable value to our customers.”

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 Luxemburg 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 to Unveil ‘Full Stack AI Memory Provider’ Vision at CES 2025 first appeared on SK hynix Newsroom.

SK hynix’s booth at SC24

Returning for its second year, SK hynix is underlining its AI memory leadership through a display of innovative memory products and insightful presentations on AI and HPC technologies. In line with the conference’s “HPC Creates” theme which underscores the impact of supercomputing across various industries, the company is showing how its memory solutions drive progress in diverse fields.

Showcasing Advanced Memory Solutions for AI & HPC

At the booth, SK hynix is demonstrating and displaying a range of groundbreaking products tailored for AI and HPC. The products being demonstrated include its CMM (CXL^®1 Memory Module)-DDR5²,  AiMX³ accelerator card, and Niagara 2.0 among others.

¹Compute Express Link^® (CXL^®): A PCIe-based next-generation interconnect protocol on which high-performance computing systems are based.
²CXL Memory Module-DDR5 (CMM-DDR5): A next-generation DDR5 memory module utilizing CXL technology to boost bandwidth and performance for AI, cloud, and high-performance computing.
³Accelerator-in-Memory Based Accelerator (AiMX): SK hynix’s specialized accelerator card tailored for large language model processing using GDDR6-AiM chips.

Live demonstrations of CMM-DDR5 and AiMX at the booth

The live demonstration of CMM-DDR5 with a server platform featuring Intel^® Xeon^® 6 processors shows how CXL^® memory technology accelerates AI workloads under various usage models. Moreover, visitors to the booth can learn about the latest CMM-DDR5 product with EDSFF⁴ which offers improvements in TCO⁵ and performance. Another live demonstration features AiMX integrated in an ASRock Rack Server to run Meta’s Llama 3 70B, a large language model (LLM) with 70 billion parameters. This demonstration highlights AiMX’s efficiency in processing large datasets while achieving high performance and low power consumption, addressing the computational load challenges posed by attention layers⁶ in LLMs.

⁴Enterprise and Data Center Standard Form Factor (EDSFF): A collection of SSD form factors specifically used for data center servers.
⁵Total cost of ownership (TCO): The complete cost of acquiring, operating, and maintaining an asset, including purchase, energy, and maintenance expenses.
⁶Attention layer: A mechanism that enables a model to assess the relevance of input data, prioritizing more important information for processing.

SK hynix’s Niagara 2.0, customized HBM, OCS, and SSD products

Among the other technologies being demonstrated is Niagara 2.0. The CXL pooled memory solution enables data sharing to minimize GPU memory shortages during AI inference⁷, making it ideal for LLM models. The company is also demonstrating an HBM with near-memory processing (NMP)⁸ which accelerates indirect memory access⁹, a frequent occurrence in HPC. Developed with Los Alamos National Laboratory (LANL), the solution highlights the potential of NMP-enabled HBM to advance next-generation technologies.

Another demonstration is showcasing SK hynix’s updated OCS¹⁰ solution, which offers significant improvements in analytical performance for real-world HPC workloads compared to the iteration displayed at SC23. Co-developed with LANL, OCS addresses performance issues in traditional HPC systems by enabling storage to independently analyze data, reducing unnecessary data movement and improving resource efficiency. Additionally, the company is demonstrating a checkpoint offloading SSD¹¹ prototype that improves LLM training resource utilization by enhancing performance and scalability.

⁷AI inference: The process of using a trained AI model to analyze live data for predictions or task completions.
⁸Near-memory processing (NMP): A technique that performs computations near data storage, reducing latency and boosting performance in high-bandwidth tasks like AI and HPC.
⁹Indirect memory access: A computing addressing method in which an instruction providing the address of a memory location that contains the actual address of the desired data or instruction.
¹⁰Object-based computational storage (OCS): A storage architecture that integrates computation within the storage system, enabling local data processing and minimizing movement to enhance analytical efficiency.
¹¹Checkpoint offloading SSD: A storage solution that stores intermediate data during AI training, improving efficiency and reducing training time.

SK hynix presented various data center solutions, including HBM3E, DDR5, and eSSD products

In addition to running product demonstrations, SK hynix is also displaying a robust lineup of data center solutions, including its industry-leading HBM3E¹². The fifth-generation HBM provides high-speed data processing, optimal heat dissipation, and high capacity, making it essential for AI applications. Alongside HBM3E are the company’s rapid DDR5 RDIMM and MCR DIMM products, which are tailored for AI computing in high-performance servers. Enterprise SSDs (eSSDs) including the Gen 5 PS1010 and PEB110 are also on display. Offering ultra-fast read/write speeds, these SSD solutions are vital for accelerating AI training and inference in large-scale environments.

¹²HBM3E: The fifth-generation High Bandwidth Memory (HBM), a high-value, high-performance product that revolutionizes data processing speeds by connecting multiple DRAM chips with through-silicon via (TSV).

Highlighting the Potential of Memory Through Expert Presentations

During the conference, Jongryool Kim, research director of AI System Infra, presented on “Memory & Storage: The Power of HPC/AI,” highlighting the memory needs for HPC and AI systems. He focused on two key advancements including near-data processing technology using CXL, HBM, and SSDs to improve performance, and CXL pooled memory for better data sharing across systems.

(From first image) Research Director Jongryool Kim presenting on advancements in memory and storage for HPC and AI systems; Technical Leader Jeoungahn Park delivering a presentation on OCS

Technical Leader Jeoungahn Park of the Sustainable Computing team also took to the stage for his talk on “Leveraging Open Standardized OCS to Boost HPC Data Analytics.” Park explained how OCS enables storage to automatically recognize and analyze data, thereby accelerating data analysis in HPC. He added how OCS enhances resource efficiency and integrates seamlessly with existing analytics systems, as well as how its analysis performance has been verified in real-world HPC applications.

At SC24, SK hynix is solidifying its status as a pioneer in memory solutions which are driving innovations in AI and HPC technologies. Looking ahead, the company will continue to push technological boundaries with support from its partners to shape the future of AI and HPC.

The post SK hynix Presents Innovative AI & HPC Solutions at SC24 first appeared on SK hynix Newsroom.

Organized by the Korea Semiconductor Industry Association, SEDEX is South Korea’s largest semiconductor exhibition. This year’s event, the 26^th edition of the exhibition, is themed “The Integration of AI Semiconductors and Cutting-Edge Packaging Technology.” Featuring 600 booths, it brings together 250 companies representing the entire semiconductor ecosystem, including semiconductor devices, system semiconductors, equipment and components, materials, facilities, and sensors.

Visitors to SK hynix’s exhibition explore the company’s advanced products

Under the slogan of “Memory, The Heart of AI,” SK hynix is presenting advanced technologies which are driving AI innovation and underlining its AI memory leadership. These include its industry-leading HBM¹, CXL^®2, the next-generation AI memory solution, and PIM³, the next-generation intelligent memory. Additionally, it features server products for high-performance computing in data centers and on-device AI⁴ solutions for smart devices.

¹High Bandwidth Memory (HBM): A high-performance, high-value memory that achieves high bandwidth by connecting multiple DRAM chips using through-silicon via (TSV). This memory significantly boosts data processing speeds compared to traditional DRAM.
²Compute Express Link^® (CXL^®): A next-generation interface designed to efficiently utilize high-performance computing systems by connecting CPU, GPU, memory, and other components.
³Processing-In-Memory (PIM): A technology which enhances memory performance through its processing capabilities, helping to address data transfer bottlenecks in AI and big data applications.
⁴On-Device AI: A technology that enables AI processing directly on the device, improving responsiveness and delivering personalized, real-time services without the need for cloud-based computation.

SK hynix is also sharing its new vision through its 41st anniversary brand film and the Yongin Semiconductor Cluster exhibition as the company looks to leverage 40 years of expertise to strengthen its position as the global no. 1 AI memory provider.

As well as technological innovations, SK hynix is promoting its social value (SV) initiatives such as the Happy Bread bakery project. This initiative is run by Happy Moa, an SK hynix subsidiary that aims to increase employment opportunities for the disabled. The SV zone features various attractions for visitors, including interactive games and exhibits.

During the three-day event, SK hynix also delivered a keynote address on the key role of packaging for AI technologies. To shed light on SK hynix’s activities at SEDEX 2024, the newsroom visited the company’s booth, capturing its technological vision as a total AI memory provider.

Showcasing Global No. 1 AI Memory Technology: From HBM to Server & On-Device AI Solutions

A simulation of virtual GPUs powered by HBM3E

At the center of the exhibition hall, SK hynix has set up a large LED wall that immerses visitors in a virtual AI data center. The wall includes simulations of virtual GPUs powered by the industry-leading HBM3E, offering a realistic experience of an operational data center. Behind it, an exhibition space highlights SK hynix’s flagship AI memory products.

The HBM exhibition zone features a display of the 12-layer HBM3E and a rice-based art installation to highlight the product’s capacity

The main product at the center of the exhibition is HBM, the highest-performing DRAM for AI workloads. On display is the world’s first 12-layer HBM3E, which SK hynix began mass producing in September 2024. A standout feature of the HBM exhibit, which covers the developmental history of the product, is an art installation illustrating the high capacity of the 12-layer HBM3E compared with the world’s first DRAM from 1970. It uses grains of rice to visually convey the dramatic leap in memory technology driven by SK hynix’s technological prowess.

To the left of the HBM exhibition zone, a dedicated space is showcasing next-generation AI memory technologies including PIM and CXL.

The PIM zone features AiM and AiMX products

The PIM section introduces SK hynix’s AiM⁵ product and the AiMX accelerator card. Combining multiple GDDR6-AiM chips, AiMX is a high-speed, low-power, cost-effective memory solution which can perform computational functions—making it optimized for generative AI applications.

⁵Accelerator-in-Memory (AiM): SK hynix’s PIM semiconductor product, which features the GDDR6-AiM.

CMM-DDR5 and CMM-Ax are on display in the CXL zone

In the CXL section, SK hynix is presenting its CMM (CXL Memory Module)-DDR5⁶ which expands system bandwidth by up to 50% and capacity by up to 100% compared to systems equipped with only DDR5. A sample of CMM-Ax⁷, which integrates machine learning and data filtering functions into CXL memory, is also on display. A live demonstration of a system equipped with CMM-Ax highlights its exceptional performance.

⁶CXL Memory Module-DDR5 (CMM-DDR5): A next-gen DDR5 memory module based on CXL that enhances system bandwidth, speed, and performance for AI, cloud, and high-performance computing.
⁷CXL Memory Module-Ax (CMM-Ax): A high-performance memory module optimized for computational workloads, improving AI and data center efficiency.

To the right of the HBM exhibition, SK hynix is displaying AI solutions for servers and on-device applications.

AI solutions for servers, including DDR5 RDIMM, are also being showcased

These include products gaining attention in the high-performance computing (HPC) market such as the world’s first 1cnm DDR5 RDIMM and DDR5 MCR DIMM. The DDR5 products are showcased alongside a lineup of enterprise SSDs (eSSDs) compatible with various server form factors.

The 1cnm DDR5 RDIMM, first revealed at the TSMC Open Innovation Platform (OIP) Ecosystem Forum in September 2024, offers 11% faster operating speeds and over 9% improved power efficiency compared to the previous generation. When applied to data centers, the product is expected to reduce operational costs by up to 30%.

The on-device AI exhibition includes key products such as LPCAMM2 and ZUFS 4.0

In the on-device AI solution section, SK hynix is displaying LPCAMM2, which packages LPDDR5X⁸, and the next-generation mobile NAND solution, ZUFS 4.0⁹. LPCAMM2 provides the performance of two SODIMM¹⁰ DRAM modules in a single package, offering space savings, lower power consumption, and high performance—ideal for on-device AI applications. As the highest-performing product in the industry, ZUFS 4.0 enhances smartphone application launch speeds by approximately 45% over previous versions in long-term usage environments, making it an optimal solution for on-device AI in mobile devices.

In addition to these innovative displays, SK hynix shared its industry expertise through a keynote address by Kangwook Lee, head of Package Development. Held on the second day of the event, Lee’s presentation covered the role of advanced packaging in the AI era.

⁸Low Power Double Data Rate 5X (LPDDR5X): A low-voltage DRAM standard for mobile devices like smartphones and tablets, designed to reduce power consumption.
⁹Zoned Universal Flash Storage (ZUFS): An advanced version of UFS that improves data management efficiency by organizing data into zones, optimizing transfer between the operating system and storage device.
¹⁰Small Outline DIMM (SODIMM): A compact memory module typically used in laptops and desktop PCs.

Sharing a Vision for the Future of the AI Era

A special exhibit introducing the Yongin Semiconductor Cluster and SK hynix’s industrial AI start-up, Gauss Labs

Aside from the main exhibition area, SK hynix is presenting a special exhibit highlighting the Yongin Semiconductor Cluster and its industrial AI start-up, Gauss Labs.

The Yongin Semiconductor Cluster is currently undergoing development in the South Korean city of Yongin. During the exhibition, SK hynix is sharing the goals and vision of the cluster, which aims to become a hub for the AI memory ecosystem and a key component of the company’s long-term growth strategy.

(From left) The Tube T31 and Beetle X31 are shown at the Brand SSD zone

A separate exhibition zone is also being dedicated to brand SSDs, a type of B2C product aimed at general consumers. This zone includes a U.S. promotional video for the portable Beetle X31 SSD,  along with displays of the PCIe SSDs Platinum P41 and P51, as well as the stick-type SSD Tube T31.

A selection of breads prepared by the Happy Bread bakery

The company is also introducing its social value initiative, the Happy Bread bakery. As the bakery brand of Happy Moa under SK hynix, it employs approximately 190 individuals with developmental disabilities with customized jobs across various baking processes. Visitors to the booth can enjoy breads and cookies made by the Happy Bread bakery.

Visitors enjoying taking part in a quiz and playing various games organized by SK hynix

In addition to these activities, SK hynix is engaging visitors through a variety of events and games throughout the exhibition hall. At the entrance of the Brand SSD zone, an interactive “Find the Beetle X31” game highlights the performance of the portable SSD. A dedicated gaming zone is also centered around the company’s memory innovations where visitors can play jumping games, pinball, and layer stacking games. This area also features interactive activities such as a quiz and a raffle with attractive prizes.

At SEDEX 2024, SK hynix is underscoring the critical role of its memory solutions in the AI era. By showcasing its diverse portfolio of cutting-edge products and technologies in one place, SK hynix is solidifying its position as a total AI memory provider.

The post SK hynix Showcases AI Memory Leadership & Shares Future Vision at SEDEX 2024 first appeared on SK hynix Newsroom.

SK hynix is showcasing its leading AI and data center memory products at the 2024 Open Compute Project (OCP) Global Summit held October 15–17 in San Jose, California. The annual summit brings together industry leaders to discuss advancements in open source hardware and data center technologies. This year, the event’s theme is “From Ideas to Impact,” which aims to foster the realization of theoretical concepts into real-world technologies.

SK hynix’s booth at the 2024 OCP Global Summit

In addition to presenting its advanced memory products at the summit, SK hynix is also strengthening key industry partnerships and sharing its AI memory expertise through insightful presentations. This year, the company is holding eight sessions—up from five in 2023—on topics including HBM¹ and CMS².

¹High Bandwidth Memory (HBM): A high-value, high-performance product that revolutionizes data processing speeds by connecting multiple DRAM chips with through-silicon via (TSV).
²Compute Memory Solution (CMS): A memory solution optimized for AI, HPC, and data centers, enhancing speed, efficiency, and scalability for compute-heavy workloads.

Displays & Demonstrations at the Booth: Transforming AI & Data Centers

Visitors to SK hynix’s booth can see a range of the company’s cutting-edge AI and data center solutions and view demonstrations with high-performance customer systems.

SK hynix’s groundbreaking AI and data center products on display

Among the products being demonstrated is CMM-Ax³, formerly known as CMS 2.0, which was shown under its new name for the first time. For the demonstration, SK hynix is highlighting the product’s role in next-generation compute memory for AI infrastructure, particularly for multi-modal applications. Meanwhile, a heterogeneous memory management solution involving CMM (CXL Memory Module)-DDR5⁴ and HMSDK⁵ is also being demonstrated as well as Niagara 2.0⁶, which is illustrating its efficient utilization of pooled memory resources. Another demonstration is highlighting the computational storage drive’s (CSD) AI storage capabilities for large-scale training systems.

³CXL Memory Module-Ax (CMM-Ax): A high-performance memory module optimized for computational workloads, improving AI and data center efficiency.
⁴CXL Memory Module-DDR5 (CMM-DDR5): A next-gen DDR5 memory module based on CXL that enhances system bandwidth, speed, and performance for AI, cloud, and high-performance computing.
⁵Heterogeneous Memory Software Development Kit (HMSDK): A software development kit specially designed to support CXL memory, a next-generation memory system based on the CXL open industry standard.
⁶Niagara 2.0: An integrated HW/SW solution for pooled memory that allows multiple hosts (CPUs and GPUs) to efficiently share large memory pools to minimize unused or underutilized memory known as stranded memory. By supporting optimal data placement through hot and cold data detection, it can significantly improve system performance.

SK hynix is showcasing CXL-based solutions including CMM-Ax and Niagara 2.0

In addition, a live demonstration of the GDDR6-AiM⁷-based accelerator card AiMX is being held using Meta’s latest large language model (LLM), Llama3 70B, which has 70 billion parameters. The demonstration shows AiMX’s capability to tackle industry challenges. For example, data centers’ LLM services improve GPU efficiency by simultaneously processing requests from multiple users. However, as the length of the generated token increases, the computation of the attention layer⁸ increases, lowering GPU efficiency. Through the demonstration, AiMX shows it can overcome this issue by handling large amounts of data while offering greater efficiency and lower power consumption compared to the latest accelerators.

⁷Accelerator-in-Memory (AiM): SK hynix’s PIM semiconductor product. PIM is next-generation technology that adds computational functions to memory semiconductors, solving the data transfer bottleneck in AI and big data processing fields.
⁸Attention layer: A mechanism which allows a model to determine the importance of input data to focus on more relevant information.

The AiMX card is being demonstrated with Meta’s latest LLM, Llama3 70B

The company also displayed a range of its industry-leading AI memory and data center products. HBM3E is shown along with the NVIDIA H200 Tensor Core GPU and NVIDIA GB200 Grace Blackwell Superchip. The booth also features SK hynix’s DDR5 RDIMM and MCR DIMM server DRAM, as well as enterprise SSDs (eSSDs), with Supermicro servers. The DDR5 products on display include the world’s first DDR5 DRAM built using the 1c node, the sixth generation of the 10nm process technology. Designed to meet the growing computational and energy demands of AI-driven data centers, the 16 Gb 1c DDR5 offers improved performance and energy efficiency from the previous generation. Additionally, SK hynix unveiled the 1bnm 96 GB DDR5 which can reach speeds of up to 7,200 megabits per second (Mbps), making it ideal for supporting massive data flows in data centers.

HBM3E is presented alongside NVIDIA’s H200 and GB200, while DDR5 RDIMM and MCR DIMM products are shown with Supermicro servers

In the SSD section, the Gen5 eSSDs PS1010 and PS1030 and the Gen4 PE9010 are among those on display. Offering ultra-fast read/write speeds, these SSD solutions are vital for accelerating AI training and inference in large-scale environments. Through all these innovations, SK hynix is continuing to lead the way in AI memory and storage solutions, fueling the future of AI and transforming data center operations.

Gen5 eSSDs showcased at the summit

Expanded Presentation Sessions: Sharing AI Memory Expertise

Reflecting SK hynix’s growing influence as the leading AI memory provider, the company is holding eight insightful sessions—three more than in 2023—on the future of AI memory solutions.

SK hynix is sharing its industry expertise through eight presentations

• Youngpyo Joo, head of Software Solution: Joo discussed how AI-driven technological advancements are reshaping computing architecture, focusing on innovations such as CXL^®9-based memory and computational memory solutions for AI workloads.
• Technical Leader Jungmin Choi, Composable System: In his talk, Choi explored how memory disaggregation can improve system efficiency.
• Technical Leader Honggyu Kim, System SW: Kim explained how SK hynix’s HMSDK solution optimizes memory pooling and sharing in AI workloads, improving performance and reducing network congestion.
• Technical Leader Younsoo Kim, DRAM Technology Planning: Kim addressed the future of HBM memory and its pivotal role in AI applications in his presentation.
• Euicheol Lim, head of Solution Advanced Technology (Solution AT): Lim discussed the role of SK hynix’s AiMX card to reduce operational costs in LLM processing in data centers and on-device services.
• Technical Leader Kevin Tang and Team Leader Jongryool Kim, AI System Infra: Tang and Kim delivered a joint presentation about improving LLM training efficiency and scalability through checkpoint¹⁰
• Hoshik Kim, head of SOLAB: As part of a panel discussion, Kim discussed various issues, solutions, and visions that near-data computing¹¹ needs to address for application to various real systems.
• Technical Leader Myoungseo Kim, AI Open Innovation: Kim will deliver the final talk with Vikrant Soman, Solution Architect at Uber, and Jackrabbit Labs CTO Grant Mackey on CMS composable memory architecture and the need for scalable, interoperable memory solutions. The presentation will reveal the results of SK hynix’s CXL pooled memory prototype integration with Jackrabbit Labs’ open source cluster orchestration software to address the pain point of stranded memory in the Uber Data Center Kubernetes Cluster environment.

⁹Compute Express Link (CXL): A PCIe-based next-generation interconnect protocol on which high-performance computing systems are based.
¹⁰Checkpoint: A technology that stores model parameters and related key data at a specific point during the learning (training) process, enabling the learning process to restart from the saved point in case of a system failure.
¹¹Near-data computing: A computing method aimed at addressing the bottleneck issue between the memory and processor, a limitation of the von Neumann architecture. It delivers only refined data processed by memory to the processor to minimize the movement of data within the system, improving performance and cost efficiency.

Shaping the Future: Advancing AI Memory & Data Center Innovation

At the 2024 OCP Global Summit, SK hynix is reinforcing its industry leadership by not only showcasing its advanced AI memory and data center solutions but also sharing its expertise. Looking ahead, the company is dedicated to pioneering breakthroughs that will define the next generation of AI and data center technologies.

The post SK hynix at the 2024 OCP Global Summit: Leading the Future of AI & Data Center Memory Solutions first appeared on SK hynix Newsroom.

SK hynix has embarked on a 41-year journey to become a leader in HBM and AI memory

The Rise of SK hynix & Its HBM Propelled by the AI Era

SK hynix’s rise to become the leader in the global memory market has been driven by the growth of the AI industry. Since the emergence of generative AI in 2022, a wide range of products and services have adopted AI as the technology has rapidly evolved. This has led to a surge in demand for high-performance memory, which is essential for processing massive datasets and enabling fast training and inference¹. In response to this demand, SK hynix is providing advanced memory products and thereby playing a defining role in the development of the AI industry.

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

SK hynix has continually advanced its HBM lineup to reach new standards in performance

SK hynix solidified its capabilities even before the AI boom by focusing on developing the early generations of HBM, a high-bandwidth memory which rapidly transmits large volumes of data. The company then gained market leadership and expanded its influence with the third-generation HBM, HBM2E. HBM3, the successor to HBM2E which is optimized for AI and high-performance computing (HPC), also drew significant attention. Most notably, the company established itself as a key partner in the AI and data center markets by supplying HBM products to NVIDIA. Around this time, SK hynix achieved a 50% market share in the HBM sector to strengthen its HBM leadership.

Moving into 2024, SK hynix has maintained its prominence in the AI memory market. The company began supplying the world’s best-performing 8-layer HBM3E, first developed in 2023, to leading global tech giants in March 2024. Offering maximum data processing speeds of around 1.2 terabytes (TB) per second, HBM3E helped SK hynix further bolster its status as the global no. 1 AI memory provider.

Next-Generation HBM: Utilizing 15 Years of HBM Technology Know-How

SK hynix’s HBM success story can be traced back to 2009. This was the year when the company began full-scale product development after discovering that TSV² and WLP³ technologies could break memory performance barriers. Four years later, the company introduced the first-generation HBM, incorporating these TSV and WLP technologies. Although HBM was hailed as an innovative memory solution, it did not receive an explosive market response because the HPC sector had not yet sufficiently matured enough for widespread HBM adoption.

²Through-silicon via (TSV): A technology that drills thousands of microscopic holes in the DRAM chip and connects the upper and lower chip layers with electrodes that vertically penetrate through these holes.
³Wafer-level packaging (WLP): A method that is a step beyond the conventional package, where wafers are cut into individual chips and then packaged. In WLP, the packaging is completed at the wafer level, producing finished products.

Building on its 15-year HBM history, SK hynix is well-placed to develop next-generation HBM products

Despite this, SK hynix pressed forward, focusing on developing the next generation of HBM and pursuing the goal of achieving the “highest performance.” During this period, the company applied MR-MUF⁴ technology, known for its high thermal dissipation and production efficiency, to HBM2E which changed the market landscape. Building upon this, SK hynix developed Advanced MR-MUF technology, which excelled in thin chip stacking, thermal management, and productivity, and applied it to both HBM3 and HBM3E. Leveraging this technology, SK hynix set a series of industry-best performance records, successfully mass-producing the 12-layer HBM3 (24 GB) in 2023 and the 12-layer HBM3E (36 GB) in 2024.

⁴Mass reflow-molded underfill (MR-MUF): A technology that ensures secure and reliable connections in densely stacked chip assemblies by melting the bumps between stacked chips.

These achievements were driven by a strategy that precisely aligned with the rise of the AI revolution. SK hynix launched its AI memory products at the right time, fully meeting market demands. This was made possible through 15 years of accumulated technological expertise based on research and development, unwavering employee trust in the company’s know-how, and forward-looking strategic investments.

SK hynix has continued taking strategic steps to strengthen its AI leadership in 2024. In April, the company signed an investment agreement to build an advanced packaging production facility in the U.S. state of Indiana which will produce next-generation HBM and AI memory. In the same month, SK hynix entered a technology agreement with TSMC. The deal aims to establish a collaborative three-way framework between the customer, foundry, and memory provider to overcome technological limits and secure an advantage in the AI market.

Beyond HBM: Relentless Innovation & Strengthening the AI Memory Lineup

SK hynix’s pursuits and innovations are unfolding across all areas of memory. The company has established its “memory-centric”⁵ vision and is developing a wide range of memory solutions based on over 40 years of accumulated technological knowledge. In 2024, SK hynix is making concerted efforts to strengthen its lineup with PIM, CXL, and AI SSD products to mark the first year of its renaissance.

⁵Memory-centric: An environment where memory semiconductors play the central role in ICT devices.

SK hynix’s AI memory lineup includes PIM, CXL, and AI SSD products

SK hynix is developing its lineup of processing-in-memory (PIM), an intelligent semiconductor memory which breaks the boundary between storage and computation. PIM, which features a processor for computational functions, is capable of processing and delivering the data required for AI computation. In terms of PIM-based products, SK hynix has launched the GDDR6-Accelerator-in-Memory (AiM) and last year introduced the accelerator card AiMX, an AiM-based accelerator that boosts performance by connecting multiple AiM units. In 2024, the company drew attention by unveiling a 32 GB version of AiMX which offers double the capacity of its predecessor.

SK hynix is also actively investing in Compute Express Link (CXL), a technology that integrates different interfaces such as those for CPUs and memory, to expand memory bandwidth and capacity. In May 2024, the company introduced the CXL Memory Module (CMM)-DDR5 which offers 50% greater bandwidth and double the capacity compared to standard DDR5. Then in September, SK hynix integrated key features of its CXL-optimized software HMSDK⁶ into the open-source operating system Linux, setting a new standard for the use of CXL technology.

⁶Heterogeneous Memory Software Development Kit (HMSDK): SK hynix’s proprietary heterogeneous memory software development tool. Enhances the performance of heterogeneous memory systems, including CXL memory, through effective memory control.

Ultra-high-speed, high-capacity enterprise SSDs (eSSDs) for AI servers and data centers are another area of focus for SK hynix. A prime example is the 60 TB Quad Level Cell (QLC) eSSD, co-developed with the company’s U.S. subsidiary Solidigm. This product stores 4 bits per cell while maintaining low power consumption. Looking ahead, the company is planning to develop a 300 TB eSSD and launch the product in 2025.

The company also offers a robust lineup for on-device AI. SK hynix developed the low-power DRAM, LPDDR5T⁷, in January 2023 to enhance the performance of AI smartphones. In November of the same year, the company unveiled the modularized version of the LPDDR5X, LPCAMM2, which is expected to deliver excellent performance in AI desktops and laptops. SK hynix has also completed the development of the high-performance client SSD (cSSD), PCB01, for AI PCs and the mobile NAND solution for AI, Zoned UFS (ZUFS) 4.0.

⁷Low Power Double Data Rate 5 Turbo (LPDDR5T): Low-power DRAM for mobile devices, including smartphones and tablets, aimed at minimizing power consumption and featuring low voltage operation. LPDDR5T is an upgraded product of the 7th generation LPDDR5X and will be succeeded by the 8th generation LPDDR6.

Shaping the Future of Total AI Memory

Today, AI is being used to write reports, generate images, and create various types of content. In healthcare, AI aids in making diagnoses, while in education AI serves as an assistant for teachers. These are just a small selection of the current applications of AI, and the possibilities for the future are expected to be almost limitless as the technology continues to advance.

SK hynix plans to develop customized AI memory and emerging memory products

At the center of this technological revolution is AI memory. Various AI memory solutions, such as HBM, PIM, CXL, and SSDs, transmit large volumes of data quickly with high bandwidth or send only the processed results directly to the processor, minimizing bottlenecks and enhancing AI learning and inference performance. Furthermore, these technologies improve the energy efficiency of AI systems, contributing to the establishment of more sustainable AI infrastructure. These advanced AI memory technologies are expected to be applied across a wider range of industries such as the automotive and healthcare sectors, enabling faster and more efficient AI services.

To further AI’s development, SK hynix is continuously overcoming technological limitations. The company is focused on developing custom AI memory optimized for each customer in line with the growing diversification of AI services. Moreover, SK hynix is also working on next-generation emerging memory, which is based on new structures and principles as well as innovative components, such as ReRAM⁸, MRAM⁹, and PCM¹⁰. By relentlessly investing in technology development, SK hynix aims to secure differentiated competitiveness with advanced technologies and establish a leading position in future markets.

⁸Resistive RAM (ReRAM): A type of emerging memory with a simple structure containing a filament in which data is stored by applying voltage to the filament. It features a large data storage capacity through process miniaturization and low power consumption.
⁹Magnetic Random Access Memory (MRAM): A type of emerging memory which utilizes both charge and spin, with resistance in the device changing based on the direction of the spin.
¹⁰Phase-Change Memory (PCM): Semiconductor memory which stores data by utilizing the phase change of a specific material (phase-change memory). It combines the benefits of non-volatile flash memory, which retains data even when powered off, with the rapid processing speeds of DRAM.

The semiconductor market itself is poised for significant growth. The World Semiconductor Trade Statistics (WSTS) forecasts that the semiconductor market will expand by 16% year-on-year in 2024. In particular, the semiconductor memory sector is predicted to grow by an impressive 76.8% as demand surges for AI memory such as HBM.

Standing at the forefront of the huge AI wave, SK hynix is preparing for another leap forward by building on its past achievements. As SK hynix celebrates its 41st anniversary, the company aims to maintain HBM leadership while securing dominance in the next-generation semiconductor market to stand alone in an era where its products become “the heart of AI.”

The post [SK hynix’s 41st Anniversary] “Celebrating 40+1” … Harnessing 40 Years of Technological Expertise to Stand Alone as the Global No. 1 AI Memory Provider first appeared on SK hynix Newsroom.

• HMSDK, SK hynix’s open source memory control solution lauded for its performance, is now available on Linux, the world’s largest open source operating system
• HMSDK optimizes performance between heterogeneous memories, increasing bandwidth by 30% and performance by over 12%
• The company will foster the ecosystem by increasing software competitiveness as well as AI memory such as HBM

Seoul, September 23, 2024

SK hynix Inc. (or “the company”, www.skhynix.com) announced today that the key features of its Heterogeneous Memory Software Development Kit (HMSDK)¹ are now available on Linux², the world’s largest open source operating system.

¹Heterogeneous Memory Software Development Kit (HMSDK): SK hynix’s software development kit. It enables effective memory control, improving the performance of heterogeneous memory systems such as CXL memory.
²Linux: An operating system developed in 1991 by Linus Torvalds that has since expanded to become the world’s largest open source operating system. Most operating systems for cloud systems and supercomputers, as well as smartphones, cars, and appliances, are built on Linux.

HMSDK is SK hynix’s software for optimizing the operation of Compute Express Link (CXL)³, which is gaining attention as a next-generation AI memory technology along with High Bandwidth Memory (HBM). Having received global recognition for HMSDK’s performance, SK hynix is now integrating it with Linux. This accomplishment marks a significant milestone for the company as it highlights the company’s competitiveness in software, adding to the recognition for its high-performance memory hardware such as HBM.

³Compute Express Link (CXL): A next-generation interface that efficiently connects CPU, GPU, memory, and other components in high-performance computing systems to support massive, ultra-fast computation. By applying CXL to existing memory modules, the capacity can be expanded by more than 10 times.

In the future, developers around the world working on Linux will be able to use SK hynix’s technology as the industry standard for CXL memory, putting the company in an advantageous position for global collaboration on next-generation memory.

SK hynix’s HMSDK enhances memory package’s bandwidth by over 30% without modifying existing applications. It achieves this by selectively allocating memory based on the bandwidth between existing memory and expanded CXL memory. Additionally, the software improves performance by more than 12% over conventional systems through optimization based on access frequency, a feature which relocates frequently accessed data to faster memory.

The semiconductor industry anticipates full commercialization of CXL in the second half of 2024, coinciding with the release of the first server CPUs featuring the “CXL 2.0” specification. In preparation for this, SK hynix is currently validating CXL 2.0 memory in 96 GB and 128 GB capacities with customers. The company plans to begin mass production by the end of the year.

“For the development and spread of AI systems such as large language models (LLMs), it is now necessary to significantly improve not only semiconductors but also the level of system applications to support them,” said Youngpyo Joo, Head of Software Solution at SK hynix. “With this Linux integration and collaboration, we will strive to improve our status as a total AI memory solutions provider by innovating technologies and expanding the ecosystem in this field.”

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 Applies CXL Optimization Solution to Linux first appeared on SK hynix Newsroom.

SK hynix’s booth at HPE Discover 2024

SK hynix has returned to Las Vegas to showcase its leading AI memory solutions at HPE Discover 2024, Hewlett Packard Enterprise’s (HPE) annual technology conference. Held from June 17–20, HPE Discover 2024 features a packed schedule with more than 150 live demonstrations, as well as technical sessions, exhibitions, and more. This year, attendees can also benefit from three new curated programs on edge computing and networking, hybrid cloud technology, and AI.

Under the slogan “Memory, The Power of AI,” SK hynix is displaying its latest memory solutions at the event including those supplied to HPE. The company is also taking advantage of the numerous networking opportunities to strengthen its relationship with the host company and its other partners.

The World’s Leading Memory Solutions Driving AI

SK hynix’s booth at HPE Discover 2024 consists of three product sections and a demonstration zone which showcase the unprecedented capabilities of its AI memory solutions.

SK hynix’s AI memory solutions on display including its HBM3E and CMM-DDR5

The first section features the company’s groundbreaking memory solutions for AI, including HBM¹ solutions. In particular, the industry-leading HBM3E has emerged as a core product to meet the growing demands of AI systems due to its exceptional processing speed, capacity, and heat dissipation. A key solution from the company’s CXL^®2 lineup, CXL Memory Module-DDR5³ (CMM-DDR5), is also on display in this section. In the AI era where high performance and capacity are vital, CMM-DDR5 has gained attention for its ability to expand system bandwidth by up to 50% and capacity by up to 100% compared to systems only equipped with DDR5 DRAM.

¹High Bandwidth Memory (HBM): A high-value, high-performance product that revolutionizes data processing speeds by connecting multiple DRAM chips with through-silicon via (TSV).
²Compute Express Link^® (CXL^®): A PCIe-based next-generation interconnect protocol on which high-performance computing systems are based.
³Double 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.

SK hynix’s server DRAM products are optimized for AI computing

In the second section of the booth, SK hynix is presenting its leading server DRAM solutions. The company’s power-efficient and rapid DDR5 RDIMM⁴ and MCR DIMM⁵ are featured, showcasing their ability to support AI computing in high-performance servers. Equipped with 1bnm, the fifth generation of the 10 nm process technology, DDR5 RDIMM can reach speeds of up to 6,400 megabits per second (Mbps), while MCR DIMM boasts speeds of up to 8,800 Mbps. Additionally, SK hynix is displaying its LPCAMM2⁶, a module solution that is increasingly being applied in AI PCs due to its low-power and high-performance features.

⁴Registered Dual In-line Memory Module (RDIMM): A high-density memory module used in servers and other applications to vertically connect DRAM dies.
⁵Multiplexer Combined Ranks Dual In-line Memory Module (MCR DIMM): A module product with multiple DRAMs bonded to a motherboard in which two ranks—basic information processing units—operate simultaneously, resulting in improved speed.
⁶Low Power Compression Attached Memory Module 2 (LPCAMM2): LPDDR5X-based module solution that offers power efficiency and high performance as well as space savings. It offers performance levels equivalent to two DDR5 SODIMMs, making it optimized for on-device AI.

SK hynix presents its SSD portfolio including products supplied to HPE

Visitors could also see some of SK hynix’s latest enterprise SSDs (eSSD) in the third section of the booth. These include the PCle Gen5-based PS1010 and PS1030, which are recognized to be ideal for AI, big data, and machine learning applications due to their rapid sequential read speeds. Within the same section, SK hynix’s U.S. subsidiary Solidigm is presenting its QLC⁷-based eSSDs such as D5-P5430, D5-P5316, and D5-P5336. Offering industry-leading performance and massive capacity, these products will serve as optimal solutions for various customers that require immense storage space.

⁷Quadruple Level Cell (QLC): A form of NAND flash memory that can store up to 4 bits of data per memory cell.

Sharing the Latest Innovations and Trends in AI Memory

SK hynix hosted sessions on how its memory solutions are fueling innovation in AI

During the presentation sessions at the conference, SK hynix held talks that focused on how the company’s memory products are fueling innovation in AI. On June 18, Technical Leader Brian Yoon of DRAM Technology Planning at SK hynix America provided an overview of CXL and discussed enabling memory expansion with CMM-DDR5. Yoon also touched on the features of HMSDK⁸, a software that supports CMM-DDR5. Hours later, Director Santosh Kumar of NAND Technology Planning at SK hynix America and Technical Leader Seonjae Kim of SSD Enablement at SK hynix covered SSD technology trends and how SK hynix and Solidigm can meet future SSD demands. During the talk, the pair shared how the companies’ SSD products are optimized for AI storage and modern data center workloads.

⁸Heterogeneous Memory Software Development Kit (HMSDK): A software development kit specially designed to support CXL memory, a next-generation memory system based on the CXL open industry standard.

Embracing the Memory Community to Power the Future of AI

At HPE Discover 2024, SK hynix has underlined how it is spearheading innovations in the AI memory sector. The event is not only a chance for the company to showcase its industry-leading solutions, but also a time to strengthen its partnership with HPE and other industry players.

“SK hynix is maintaining a close partnership with HPE based on its industry-leading memory technology, including securing contracts to supply high-capacity DDR5 and 16-channel Gen5 eSSD products,” said Vice President Myoungsoo Park, head of US/EU Sales at SK hynix. “We will continue to strengthen our cooperation with global partners to further solidify our technological leadership as the world’s number one AI memory provider.”

The post SK hynix Showcases Power of Its Groundbreaking AI Memory Solutions at HPE Discover 2024 first appeared on SK hynix Newsroom.

SK hynix’s booth at COMPUTEX Taipei 2024

SK hynix presented its leading AI memory solutions at COMPUTEX Taipei 2024 from June 4–7. As one of Asia’s premier IT shows, COMPUTEX Taipei 2024 welcomed around 1,500 global participants including tech companies, venture capitalists, and accelerators under the theme “Connecting AI”. Making its debut at the event, SK hynix underlined its position as a first mover and leading AI memory provider through its lineup of next-generation products.

“Connecting AI” With the Industry’s Finest AI Memory Solutions

Themed “Memory, The Power of AI,” SK hynix’s booth featured its advanced AI server solutions, groundbreaking technologies for on-device AI PCs, and outstanding consumer SSD products.

SK hynix’s memory solutions with high bandwidth and capacity are optimized for AI servers

HBM3E, the fifth generation of HBM¹, was among the AI server solutions on display. Offering industry-leading data processing speeds of 1.18 terabytes (TB) per second, vast capacity, and advanced heat dissipation capability, HBM3E is optimized to meet the requirements of AI servers and other applications.

¹High Bandwidth Memory (HBM): A high-value, high-performance product that possesses much higher data processing speeds compared to existing DRAMs by vertically connecting multiple DRAMs with through-silicon via (TSV).

Another technology which has become crucial for AI servers is CXL^®2 as it can increase system bandwidth and processing capacity. SK hynix highlighted the strength of its CXL portfolio by presenting its CXL Memory Module-DDR5³ (CMM-DDR5), which significantly expands system bandwidth and capacity compared to systems only equipped with DDR5. Other AI server solutions on display included the server DRAM products DDR5 RDIMM⁴ and MCR DIMM⁵. In particular, SK hynix showcased its tall 128-gigabyte (GB) MCR DIMM for the first time at an exhibition.

²Compute Express Link^® (CXL^®): A PCIe-based next-generation interconnect protocol on which high-performance computing systems are based.
³Double 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.
⁴Registered Dual In-line Memory Module (RDIMM): A high-density memory module used in servers and other applications to vertically connect DRAM dies.
⁵Multiplexer Combined Ranks Dual In-line Memory Module (MCR DIMM): A module product with multiple DRAMs bonded to a motherboard in which two ranks—basic information processing units—operate simultaneously, resulting in improved speed.

Visitors to the booth could also see some of the company’s enterprise SSDs (eSSD), including the PS1010 and PE9010. In particular, the PCIe⁶ Gen5-based PS1010 is ideal for AI, big data, and machine learning applications due to its rapid sequential read speed. Additionally, SK hynix’s U.S. subsidiary Solidigm strengthened the eSSD lineup by presenting its flagship products D5-P5430 and D5-P5336 that have ultrahigh capacities of up to 30.72 TB and 61.44 TB, respectively.

⁶Peripheral Component Interconnect Express (PCIe): A high-speed input/output interface with a serialization format used on the motherboard of digital devices.

SK hynix offers leading solutions optimized for on-device AI PCs

In line with the growing on-device AI⁷ trend, SK hynix showcased its groundbreaking memory solutions for on-device AI PCs. These included PCB01, a PCIe Gen5 client SSD for on-device AI which offers the industry’s highest sequential read speed of 14 gigabytes per second (GB/s) and a sequential write speed of 12 GB/s. Alongside PCB01, SK hynix displayed other products optimized for on-device AI PCs, including the next-generation graphic DRAM GDDR7 and LPCAMM2⁸, a module solution that has the performance effect of replacing two existing DDR5 SODIMMs⁹.

⁷On-device AI: The performance of AI computation and inference directly within devices such as smartphones or PCs, unlike cloud-based AI services that require a remote cloud server.
⁸Low Power Compression Attached Memory Module 2 (LPCAMM2): LPDDR5X-based module solution that offers power efficiency and high performance as well as space savings.
⁹Small Outline Dual In-line Memory Module (SODIMM): A server DRAM smaller than the regular DIMM used in desktop PCs.

SK hynix’s advanced consumer SSD products are changing the storage device game

Attendees could also get a glimpse of SK hynix’s consumer SSD products. Platinum P51 and Platinum P41, highly reliable consumer SSD solutions which offer excellent speed to boost PC performance, were displayed at the show. Set to be mass-produced later in 2024, Platinum P51 utilizes SK hynix’s “Aries”—the industry’s first high-performance in-house controller. Platinum P51 offers sequential read speeds of up to 14 GB/s and sequential write speeds of up to 12 GB/s, nearly doubling the speed specifications of the previous generation Platinum P41. This enables the loading of LLMs¹⁰ required for AI training and inference in less than one second.

¹⁰Large language model (LLM): As language models trained on vast amounts of data, LLMs are essential for performing generative AI tasks as they create, summarize, and translate texts.

An updated version of the portable SSD Beetle X31 was also unveiled at the event. This compact and stylish SSD uses a USB 3.2 Gen 2 interface to reach a rapid operation speed of 10 gigabits per second (Gbps). In addition to the existing 512 GB and 1 TB versions, SK hynix plans to launch the higher-capacity 2 TB version in the third quarter of 2024.

Earlier in May, the outstanding design of SK hynix’s SSD lineup was highlighted when its stick-type SSD Tube T31 and heat sink for Platinum P41, Haechi H02, both won a prestigious 2024 Red Dot Design Award.

Lastly, SK hynix’s ESG strategy was highlighted at the show, including its efforts to enhance the energy efficiency of its products. The company’s range of energy-efficient solutions are particularly suited for improving the sustainability of AI applications, which require significant amounts of power.

Continuing to Push the Boundaries of AI Memory

In line with the theme of COMPUTEX Taipei 2024, SK hynix continues to advance its technologies to help realize a future where “Connecting AI” becomes an everyday reality. The company will continue to participate in global conferences that present the industry’s latest trends to push its AI memory capabilities to greater heights.

The post “Memory, The Power of AI”: SK hynix Showcases Strength of Its Next-Gen Solutions at COMPUTEX Taipei 2024 first appeared on SK hynix Newsroom.