As a breakthrough generation of flash memory that has separate paths for reading and writing data, Universal Flash Storage (UFS) is capable of simultaneously transferring data in both directions. It is one of several standards of flash memory¹ storage for embedded systems², and it also refers to products made for this standard.

¹Flash memory: A non-volatile storage medium that can erase and rewrite data.
²Embedded systems: Computer systems that fulfill a specific purpose. These systems are used to power devices such as smartphones, GPS navigations, TVs, wearables, and digital cameras.

In the video above, you can see a road sign that says “one-way eMMC.”

Like UFS, embedded MultiMediaCard (eMMC)³ is one of the standards for flash memory storage devices. For eMMC products, the direction of data can only be changed when either the host or the device sends data and the other side receives all of it, signifying that data cannot be sent from both sides at the same time. This is explained by the “one-way eMMC ” road in the video where cars on one side must finish getting through before cars on the other side can use the road.

³Embedded MultiMediaCard (eMMC): A small storage device made up of NAND flash memory and a simple storage controller.

Today, the amount of data to be processed is continuing to expand due to the ever-increasing resolutions of videos and images taken by mobile devices. Moreover, data processing needs to be even faster as we approach a hyper-connected society made possible through digital technologies like the metaverse and cloud computing. Such changes demand a storage standard that has better performance capabilities than the existing eMMC—something that can go beyond the limitations of a one-way road.

Thus, UFS comes in. With UFS, both the host and device are able to send data in both directions at the same time, just like a two-way road. In addition, UFS speeds up performance as it is capable of handling multiple I/O commands simultaneously.

SK hynix has released its UD310 and UD220 memory solutions based on UFS 3.1 and UFS 2.2 specifications, respectively. Not only are they both smaller and more energy efficient than previous products, but they also offer faster reading and writing speeds. After SK hynix developed the world’s highest 238-layer NAND in August 2022, the company is seeking ways to apply this advanced technology to future versions of UFS.

As a global technology company that develops and produces some of the world’s most advanced NAND products, SK hynix is leading the future of memory and storage devices.

<Other articles from this series>
[We Do Future Technology] Become a Semiconductor Expert with SK hynix – HBM

[We Do Future Technology] Become a Semiconductor Expert with SK hynix – AI Semiconductors

The post [We Do Future Technology] Become a Semiconductor Expert with SK hynix – UFS first appeared on SK hynix Newsroom.

AI semiconductors are ultra-fast and low-power chips that efficiently process big data and algorithms that are applied to AI services. In the video above, the exhibition “Today’s Record” shows how humans have been recording information through a variety of ways including drawing and writing for thousands of years. Today, people record information in the form of data at an ever-increasing rate. As this large volume of data is used to create new data, we call this the era of big data.

It is now believed that the total amount of data created up until the early 2000s can be generated in a single day. As ICT and AI technology advances and takes on a bigger role in our lives, the amount of data will only continue to grow exponentially. This is because, in addition to data recording and processing, AI technologies learn from existing data and create large amounts of new data. To process this massive volume of data, memory chips and processors need to constantly operate and work together.

In the Von Neumann architecture¹ that is commonly used for most modern computers, the processor and memory communicate through I/O² pins that are mounted on a motherboard. This creates a bottleneck when transferring data and consumes about 1,000 times more power compared to standard computing operations. Therefore, the role of memory solutions in facilitating fast and efficient data transfer is crucial for the proper function of AI semiconductors and AI services.

¹Von Neumann architecture: A computing structure that sequentially processes commands through three stages:  memory, CPU, and I/O device.

²Input/Output (I/O): An information processing system designed to send and receive data from a computer hardware component, device, or network.

Ultimately, AI semiconductors need to combine the functions of a processor and memory while providing more enhanced qualities than the Von Neumann architecture. SAPEON Korea, an AI startup jointly founded by SK hynix, recently developed an AI semiconductor for data centers named after the company. The SAPEON AI processor offers a deep learning computation speed which is 1.5 times faster than that of conventional GPUs and uses 80% less power. In the future, SAPEON will be expanded to other areas like autonomous cars and mobile devices. SK hynix’s commitment to developing technologies to support AI is further highlighted by its establishment of the SK ICT Alliance alongside SK Telecom and SK Square. The alliance invests and develops in diverse ICT areas such as semiconductors and AI to secure global competitiveness. Furthermore, SK hynix is also developing a next-generation CIM³ with neuromorphic semiconductor⁴ devices.

³Computing-in-memory (CIM): The next generation of intelligent memory that combines the processor and semiconductor memory on a single chip.

⁴Neuromorphic semiconductor: A semiconductor for computing that can simultaneously compute and store like a human brain, reducing power consumption while increasing computational speed.

As AI technology and services continue to rapidly develop, SK hynix’s semiconductors for AI will also evolve to meet the market and consumer needs. The company’s chips will be the backbone for key AI services in the big data era and beyond.

<Other articles from this series>
[We Do Future Technology] Become a Semiconductor Expert with SK hynix – HBM

[We Do Future Technology] Become a Semiconductor Expert with SK hynix – UFS

The post [We Do Future Technology] Become a Semiconductor Expert with SK hynix – AI Semiconductors first appeared on SK hynix Newsroom.

A premium, high-performance technology which has revolutionized data processing speeds by vertically stacking multiple DRAMs using through-silicon via (TSV)¹—it is none other than High Bandwidth Memory (HBM). This groundbreaking memory solution utilizes an advanced packaging method to vertically interconnect the upper and lower chips through thousands of microscopic holes in the DRAMs. Through this process, the performance of the HBM product is increased while its size is reduced.

¹Through-silicon via (TSV): A type of vertical interconnect access (via) that completely passes through a silicon die or wafer to enable the stacking of silicon dice.

As a next-generation memory technology, HBM offers solutions to key problems faced in the memory sector. In the video above, a data bottleneck is demonstrated by the long line of people—representing data—standing at the platform of D (DRAM) Station. So, what causes data to be stuck at a standstill like this?

To provide some context to this issue, it is necessary to know that there are eight DQs², or paths for data input/output, per chip in a typical DRAM. When organized into units of DIMM³ modules, there are a total of 64 DQs. However, as system requirements for DRAMs and processing speed have increased, the amount of data being transferred has risen as well. Consequently, the number of DQs—the number of entrances and exits at D Station—was no longer sufficient for the smooth passage of data.

²DQ: A path for data transfer that acts as the data bus for the communication between the processor and memory. It has the characteristic of being bidirectional as it must be capable of both reading and writing.

³Dual in-line memory module (DIMM): A memory module that is mounted on a printed circuit board and contains multiple memory chips. It is usually used as a primary memory unit in a PC or server.

HBM is the solution for such data bottlenecks. It has a whopping 1,024 DQs and its form factor, which refers to the physical area, is more than 10 times smaller than a standard DRAM thanks to SIP⁴ and TSV technology. As a vast amount of space is required for conventional DRAMs to communicate with processors like CPUs and GPUs since they need to be connected through wire bonding⁵ or PCB traces⁶, it is impossible for DRAMs to conduct parallel processing for large amounts of data. In contrast, HBM products can communicate over very short distances which allows for the increase in DQ paths. These HBM technologies dramatically increase the movement of signals traveling between stacked DRAMs and enable data transfer at high speeds with low power consumption.

⁴System-in-package (SIP): A type of package in which multiple devices are made into a single package to implement a system.

⁵Wire bonding: A method for creating electrical interconnections between electrical device components.

⁶PCB trace: An electrical connection formed on a printed circuit board.

SK hynix, which developed the industry’s first HBM in 2013, began mass production of HBM3 in June 2022. As the fourth generation of HBM, HBM3 is approximately 78% faster than its predecessor, HBM2E. With such capabilities, HBM products can be deployed in high-performance data centers and applied to machine learning, supercomputers, artificial intelligence systems, and other advanced technologies.

SK hynix will continue to develop HBM products while ensuring that all its solutions adhere to ESG management standards to maintain its position as a leader in the premium memory market.

<Other articles from this series>
[We Do Future Technology] Become a Semiconductor Expert with SK hynix – AI Semiconductors

[We Do Future Technology] Become a Semiconductor Expert with SK hynix – UFS

The post [We Do Future Technology] Become a Semiconductor Expert with SK hynix – HBM first appeared on SK hynix Newsroom.