Samsung Electronics, the world leader in advanced memory technology, today announced its development of the industry’s first 512-gigabyte (GB) Compute Express Link (CXL) DRAM, taking an important step toward the commercialization of CXL which will enable extremely high memory capacity with low latency in IT systems.

Since introducing the industry’s first CXL DRAM prototype with a field-programmable gate array (FPGA) controller in May 2021, Samsung has been working closely with data center, enterprise server and chipset companies to develop an improved, customizable CXL device.

The new CXL DRAM is built with an application-specific integrated circuit (ASIC) CXL controller and is the first to pack 512GB of DDR5 DRAM, featuring four times the memory capacity and one-fifth the system latency over the previous Samsung CXL offering.

“CXL DRAM will become a critical turning point for future computing structures by substantially advancing artificial intelligence (AI) and big data services, as we aggressively expand its usage in next-generation memory architectures including software-defined memory (SDM),” said Cheolmin Park, Vice President of Memory Global Sales & Marketing at Samsung Electronics, and Director of the CXL Consortium. “Samsung will continue to collaborate across the industry to develop and standardize CXL memory solutions, while fostering an increasingly solid ecosystem.”

“As an active member of the CXL Consortium, Lenovo is committed to developing this important standard and helping build the ecosystem around the new CXL interconnect,” said Greg Huff, Chief Technology Officer, Lenovo Infrastructure Solutions Group. “We are excited to be part of Samsung’s CXL development program, working to foster the growth and adoption of innovative CXL products in future Lenovo systems.”

“CXL is a key technology that enables more innovative ways to manage memory expansion and pooling which will play an important role in next-generation server platforms,” said Christopher Cox, Vice President of Strategic Technology at Montage Technology. “Montage is excited to continue partnering with Samsung to help the CXL ecosystem expand rapidly.”

In recent years, the growth of the metaverse, AI and big data has been generating explosive amounts of data. However, conventional DDR design limits the scaling of memory capacity beyond the tens of terabyte range, requiring an entirely new memory interface technology like CXL.

The large pool of memory that is shared between CXL and main memory allows a server to expand its memory capacity to tens of terabytes, and at the same time increase its bandwidth to several terabytes per second.

Samsung’s 512GB CXL DRAM will be the first memory device that supports the PCIe 5.0 interface and will come in an EDSFF (E3.S) form factor — especially suitable for next-generation high-capacity enterprise servers and data centers.

Later this month, Samsung plans to unveil an updated version of its open-source Scalable Memory Development Kit (SMDK). The toolkit is a comprehensive software package that allows the CXL memory expander to work seamlessly in heterogeneous memory systems — enabling system developers to incorporate CXL memory into various IT systems running AI, big data and cloud applications, without having to modify existing application environments.

Samsung will begin sampling its 512GB CXL DRAM with customers and partners for joint evaluation and testing in the third quarter of this year, and plans to have the memory ready for commercialization as next-generation server platforms become available. As a member of the CXL Consortium Board of Directors, Samsung is openly collaborating with many global data center, server and chipset vendors to deliver next-generation interface technologies that can bring highly tangible benefits to the IT industry.

Samsung Electronics, the world leader in advanced memory technology, today announced that it has launched an 800-gigabyte (GB) solid state storage drive—the SZ985 Z-SSD, for the most advanced enterprise applications including supercomputing for AI analysis.

Developed in 2017, the new 800GB Z-SSD provides the most efficient storage solution for high-speed cache data and log data processing, as well as other enterprise storage applications that are being designed to meet rapidly growing demand within the AI, big data and IoT markets.

“With our leading-edge 800GB Z-SSD, we expect to contribute significantly to market introductions of next-generation supercomputing systems in the near future, enabling improved IT investment efficiency and exceptional performance,” said Jinman Han, senior vice president, Memory Product Planning & Application Engineering at Samsung Electronics. “We will continue to develop next-generation Z-SSDs with higher density and greater product competitiveness, in order to lead the industry in accelerating growth of the premium SSD* market.”

The new single port, four-lane Z-SSD features Z-NAND chips that provide 10 times higher cell read performance than 3-bit V-NAND chips, along with 1.5GB LPDDR4 DRAM and a high performance controller. Armed with some of the industry’s most advanced components, the 800GB Z-SSD features 1.7 times faster random read performance at 750K IOPS, and five times less write latency – at 16 microseconds, compared to an NVMe SSD PM963, which is based on 3-bit V-NAND chips. The Z-SSD also delivers a random write speed of up to170K IOPS.

Due to its high reliability, the 800GB Z-SSD guarantees up to 30 drive writes per day (DWPD) for five years, or a total of 42 petabytes. That translates into storing a total of about 8.4 million 5GB-equivalent full-HD movies during a five-year period. The reliability of the new Z-SSD is further underscored by a mean time between failures (MTBF) of two million hours.

Samsung will introduce its new Z-SSD in 800GB and 240GB versions, as well as related technologies at ISSCC 2018 (International Solid-State Circuits Conference), which will be held February 11-15 in San Francisco.

Note: All brand, product, service names and logos are trademarks and/or registered trademarks of their respective owners and are hereby recognized and acknowledged. Z-SSD is a trademark of Samsung Electronics Co., Ltd.

* Editor’s Note: The premium SSD means an SSD with IOPs exceeding 550K for random reads, and latency lower than 20us.

When we look at the content people enjoy on their mobile phones, we find that end users enjoy video content more and more. As a result, 40 to 60 percent of total mobile traffic comes from video. As end users are getting more dependent on video content and have less patience when they cannot enjoy smooth video experience because of repetitive buffering and stalling issues due to network congestion, it is getting critical for mobile service providers (MSPs) to ensure the best quality of experience (QoE) in video for their customers.

MSPs have tried to prepare for a tsunami of data usage on their networks by having a wider network spectrum, expanding backhaul and clustering networks. However, MSPs, which are under tremendous competitive pressure, continuously focus on cost efficiency while pursuing customer retention through innovation programs, such as customer experience management and revenue growth.

Big Data Activities in Mobile Networks

Mobile networks adopt Big Data for several purposes. For example, MNOs provide personalized services, targeted mobile advertisement, and more, combining customer profiles with data like location, time, network conditions and device capabilities. They can also collect data from sensors and gateways including telematics data in cars, vending machines, smart meter readings, patient data, and more. Service providers can also include services like data storage and management.

Recently, MNOs are beginning to introduce Big Data to improve their network quality, supply chain management and operational efficiency. In addition to these moves, the use of advanced analytics technology is becoming increasingly more important for intelligent network operations and service optimization.

To minimize CAPEX/OPEX, MNOs need to implement initiatives in sales and marketing, network operations, customer service and administration. In network operations, this can include deployment of small cells and Wi-Fi offloading, data traffic optimization and consolidation of OSS/BSS systems. In addition, MNOs should increase their use of business intelligence and analytics to improve customer service through automation and proactive care. To enhance operational efficiency in systems deployment and services, mobile networks are encouraged to improve churn and maintenance predictions and optimize network traffic.

The customer data collected from MNOs offers a great deal of insight about customers, such as their spending habits. Such information has become important for MNOs and will give marketing departments more opportunities to do highly effective personalized campaigns. In recent years, MNOs are showing great interest in exploring new uses with their customer data not only for operational efficiency but also for external business opportunities.

There are a variety of new revenue opportunities that can be explored. Those avenues can include customer experience management, direct marketing, cross-selling, fraud detection, customer retention and more. MNOs have a great opportunity to generate new revenue by delivering personalized services. Expertise in advanced analytics will be required to identify the appropriate tools.

Big Data Activities of Network Equipment Vendors

Network equipment vendors (NEPs) have focused on introducing innovative and advanced analytics technology while also developing cost-effective network equipment. Advanced technology in measuring analytics is the most important competitive feature among network vendors. Network equipment vendors provide predictive maintenance, traffic monitoring, security, and better QoE services. NEPs are in a unique position to provide differentiation by offering real-time, advanced analytics that combine radio and service optimization. Leveraging recent progress in Big Data, network optimization and root-cause analysis is possible on an unprecedented scale.

MNOs are increasingly taking advantage of predictive maintenance to help them achieve success. Maintenance and repairs pose substantial logistical challenges to service providers in remote areas and in high-density areas with small-cell (picocell or femtocell) deployment. But through predictive maintenance, service providers can reduce the cost of their maintenance services. This would cause less disruption to service and would help to quickly identify when equipment would fail. Predictive maintenance also offers service providers a great tool to take proactive measures in controlling OPEX.

But when does predictive maintenance matter? When used properly, predictive maintenance helps to prevent many other difficulties. For example, in cases when equipment cost is high, predictive maintenance can keep costs down. In mission-critical services or in scenarios with high technical or environmental complexity, this type of maintenance helps to protect businesses and makes sure that the network is up and running properly. Difficult-to-reach locations also benefit from predictive maintenance by reducing travel cost.

Using network analytics involves software monitoring and analyzing historical and real-time data running across networks, cloud service providers, and enterprises. Network analytics not only enhance customer engagement but also customer experience. It’s an opportunity for MNOs to provide premium services with dynamic pricing plans.

Video, Video and Video

Among those services, Samsung has focused on advanced analytics technology to improve video services.

When end users only use the voice service on their mobile phones, service providers only need to satisfy the voice quality of that service. With widespread use of smartphones and affordable data pricing offers, applications such as web surfing and video are becoming more important. MNOs need to ensure web and video service quality is sustainable as well. Hence, it is critical for MNOs to have powerful tools to ensure an enjoyable data experience.

MNOs have been monitoring the quality of data services by conducting test drives with smartphones. They take their smartphones in their car and test the smartphone’s data experience. However, not only is this not cost effective in terms of time and human resources, but it is also inaccurate because it limits the test to the device itself instead of the network as a whole. A recent study shows that mobile video experience is tightly linked to Net Promoter Score, which is a key metric in predicting customer churn. The mobile industry should instead work on improving the legacy of QoE tools.

Easy and Simple Network Operation: Self Optimization of Services

Samsung has developed a groundbreaking solution that analyzes video quality on networks. It analyzes buffering and stalling time of individual video services and enables comprehensive real-time video QoE optimization. Furthermore, root-cause analysis based on data mining automates troubleshooting for any service quality degradation.

After implementing the world’s first LTE technologies, Samsung incorporated important aspects when developing such tools, so that MNOs can provide the most optimal user experience to their customers. Samsung strives to provide effective network support solutions to service providers, empowering them to meet and exceed the expectations placed on them in an ever-evolving, connected world. At this year’s Mobile World Congress (MWC), Samsung will demonstrate CognitiV Analytics, a tool that is an essential part of Samsung’s OSS solutions, which works to enhance Samsung’s professional service capabilities.