Samsung Electronics, a world leader in advanced semiconductor technology, today announced that it has completed development of the industry’s first Graphics Double Data Rate 7 (GDDR7) DRAM. It will first be installed in next-generation systems of key customers for verification this year, driving future growth of the graphics market and further consolidating Samsung’s technological leadership in the field.

Following Samsung’s development of the industry’s first 24Gbps GDDR6 DRAM in 2022, the company’s 16-gigabit (Gb) GDDR7 offering will deliver the industry’s highest speed yet. Innovations in integrated circuit (IC) design and packaging provide added stability despite high-speed operations.

“Our GDDR7 DRAM will help elevate user experiences in areas that require outstanding graphics performance, such as workstations, PCs and game consoles, and is expected to expand into future applications such as AI, high-performance computing (HPC) and automotive vehicles,” said Yongcheol Bae, Executive Vice President of Memory Product Planning Team at Samsung Electronics. “The next-generation graphics DRAM will be brought to market in line with industry demand and we plan on continuing our leadership in the space.”

Samsung’s GDDR7 achieves an impressive bandwidth of 1.5-terabytes-per-second (TBps), which is 1.4 times that of GDDR6’s 1.1TBps and features a boosted speed per pin of up to 32Gbps. The enhancements are made possible by the Pulse Amplitude Modulation (PAM3) signaling method adopted for the new memory standard instead of the Non Return to Zero (NRZ) from previous generations. PAM3 allows 50% more data to be transmitted than NRZ within the same signaling cycle.

Significantly, in comparison with GDDR6, the latest design is 20% more energy efficient with power-saving design technology optimized for high-speed operations. For applications especially mindful of power usage, such as laptops, Samsung offers a low-operating voltage option.

To minimize heat generation, an epoxy molding compound (EMC) with high thermal conductivity is used for the packaging material in addition to IC architecture optimization. These improvements dramatically reduce thermal resistance by 70% in comparison to GDDR6, aiding in stable product performance even in conditions with high-speed operations.

With significant market growth in high-performance computing (HPC), artificial intelligence (AI), 5/6G connectivity and automotive applications, demand for advanced semiconductors has increased dramatically, making innovation in semiconductor process technology critical to the business success of foundry customers. To that end, Samsung highlighted its commitment to bringing its most advanced process technology, 1.4-nanometer (nm), for mass production in 2027.

During the event, Samsung also outlined steps its Foundry Business is taking in order to meet customers’ needs, including: △foundry process technology innovation, △process technology optimization for each specific applications, △stable production capabilities and △customized services for customers.

▲ Dr. Siyoung Choi, president and head of Foundry Business at Samsung Electronics, is giving his keynote speech at Samsung Foundry Forum 2022.

“The technology development goal down to 1.4nm and foundry platforms specialized for each application, together with stable supply through consistent investment are all part of Samsung’s strategies to secure customers’ trust and support their success,” said Dr. Siyoung Choi, president and head of Foundry Business at Samsung Electronics. “Realizing every customer’s innovations with our partners has been at the core of our foundry service.”

Showcasing Samsung’s Advanced Node Roadmap Down to 1.4nm in 2027

With the company’s success of bringing the latest 3nm process technology to mass production, Samsung will be further enhancing gate-all-around (GAA) based technology and plans to introduce the 2nm process in 2025 and 1.4nm process in 2027.

While pioneering process technologies, Samsung is also accelerating the development of 2.5D/3D heterogeneous integration packaging technology to provide a total system solution in foundry services.

Through continuous innovation, its 3D packaging X-Cube with micro-bump interconnection will be ready for mass production in 2024, and bump-less X-Cube will be available in 2026.

▲ Dr. Siyoung Choi, president and head of Foundry Business at Samsung Electronics, is giving his keynote speech at Samsung Foundry Forum 2022.

Proportion of HPC, Automotive and 5G To Be More Than 50% by 2027

Samsung actively plans to target high-performance and low-power semiconductor markets such as HPC, automotive, 5G and the Internet of Things (IoT).

To better meet customers’ needs, customized and tailored process nodes were introduced during this year’s Foundry Forum. Samsung will enhance its GAA-based 3nm process support for HPC and mobile, while further diversifying the 4nm process specialized for HPC and automotive applications.

For automotive customers specifically, Samsung is currently providing embedded non-volatile memory (eNVM) solutions based on 28nm technology. In order to support automotive-grade reliability, the company plans to further expand process nodes by launching 14nm eNVM solutions in 2024 and adding 8nm eNVM in the future. Samsung has been mass producing 8nm RF following 14nm RF, and 5nm RF is currently in development.

‘Shell-First’ Operation Strategy To Respond to Customer Needs in a Timely Manner

Samsung plans to expand its production capacity for the advanced nodes by more than three times by 2027 compared to this year.

Including the new fab under construction in Taylor, Texas, Samsung’s foundry manufacturing lines are currently in five locations: Giheung, Hwaseong and Pyeongtaek in Korea; and Austin and Taylor in the United States.

At the event, Samsung detailed its ‘Shell-First’ strategy for capacity investment, building cleanrooms first irrespective of market conditions. With cleanrooms readily available, fab equipment can be installed later and set up flexibly as needed in line with future demand. Through the new investment strategy, Samsung will be able to better respond to customers’ demands.

Investment plans in a new ‘Shell-First’ manufacturing line in Taylor, following the first line announced last year, as well as potential expansion of Samsung’s global semiconductor production network were also introduced.

Expanding the SAFE Ecosystem To Strengthen Customized Services

Following the ‘Samsung Foundry Forum,’ Samsung will hold the ‘SAFE Forum’ (Samsung Advanced Foundry Ecosystem) on October 4th. New foundry technologies and strategies with ecosystem partners will be introduced encompassing areas such as Electronic Design Automation (EDA), IP, Outsourced Semiconductor Assembly and Test (OSAT), Design Solution Partner (DSP) and the Cloud.

In addition to 70 partner presentations, Samsung Design Platform team leaders will introduce the possibility of applying Samsung’s processes such as Design Technology Co-Optimization for GAA and 2.5D/3DIC.

As of 2022, Samsung provides more than 4,000 IPs with 56 partners, and is also cooperating with nine and 22 partners in the design solution and EDA, respectively. It also offers cloud services with nine partners and packaging services with 10 partners.

Along with its ecosystem partners, Samsung provides integrated services that support solutions from IC design to 2.5D/3D packages.

Through its robust SAFE ecosystem, Samsung plans to identify new fabless customers by strengthening customized services with improved performance, rapid delivery and price competitiveness, while actively attracting new customers such as hyperscalers and start-ups.

Starting in the United States (San Jose) on October 3rd, the ‘Samsung Foundry Forum’ will be sequentially held in Europe (Munich, Germany) on the 7th, Japan (Tokyo) on the 18th and Korea (Seoul) on the 20th, through which customized solutions for each region will be introduced. A recording of the event will be available online from the 21st for those who were unable to attend in person.

Samsung Electronics, the world leader in advanced memory technology, today announced that it has begun sampling the industry’s first 16-gigabit (Gb) Graphics Double Data Rate 6 (GDDR6) DRAM featuring 24-gigabit-per-second (Gbps) processing speeds. Built on Samsung’s third-generation 10-nanometer-class (1z)¹ process using extreme ultraviolet (EUV) technology, the new memory is designed to significantly advance the graphics performance for next-generation graphics cards (Video Graphics Arrays), laptops and game consoles, as well as artificial intelligence-based applications and high-performance computing (HPC) systems.

“The explosion of data now being driven by AI and the metaverse is pushing the need for greater graphics capabilities that can process massive data sets simultaneously, at extremely high speeds,” said Daniel Lee, Executive Vice President of the Memory Product Planning Team at Samsung Electronics. “With our industry-first 24Gbps GDDR6 now sampling, we look forward to validating the graphics DRAM on next-generation GPU platforms to bring it to market in time to meet an onslaught of new demand.”

Engineered with an innovative circuit design and a highly advanced insulating material (High-K Metal Gate; HKMG) that minimizes current leakage, Samsung’s 24Gbps GDDR6 will deliver 30% faster speeds compared to the previous 18Gbps product. When integrated into a premium graphics card, the GDDR6 DRAM can transfer up to 1.1-terabytes (TB) of data, or about 275 Full HD movies, in just one second.

Designed to be fully compliant with JEDEC specifications, Samsung’s GDDR6 DRAM will be compatible across all GPU designs, facilitating broad market adoption in a wide array of graphics solutions.

Samsung’s new GDDR6 lineup will also feature low-power options that help extend the battery life of laptops. Utilizing dynamic voltage switching (DVS) technology which adjusts the operating voltage depending on performance requirements, Samsung will provide 20Gbps and 16Gbps versions with approximately 20% higher power efficiency at 1.1V, compared to the 1.35V GDDR6 industry standard.

Graphics DRAM is increasingly being sought for use beyond PCs, laptops and game consoles, extending into other graphics-intensive applications like HPC, autonomous driving and electric cars. Addressing these emerging markets, Samsung’s GDDR6 will enable seamless 4K and 8K video playback, while supporting demanding AI accelerator workloads.

Samsung continues to lead the graphics DRAM market globally and forecasts that the high-performance graphics portion will see double-digit growth annually in the coming years.

With customer verifications starting this month, Samsung plans to commercialize its 24Gbps GDDR6 DRAM in line with GPU platform launches, therein accelerating graphics innovation throughout the high-speed computing market.

¹ Samsung’s first-generation 10nm-class DRAM is termed 1x, followed by 1y (second-generation), 1z (third-generation), 1a (fourth-generation) and so on.

“H-Cube solution, which is jointly developed with Samsung Electro-Mechanics (SEMCO) and Amkor Technology, is suited to high-performance semiconductors that need to integrate a large number of silicon dies,” said Moonsoo Kang, Senior Vice President and Head of Foundry Market Strategy Team at Samsung Electronics. “By expanding and enriching the foundry ecosystem, we will provide various package solutions to find a breakthrough in the challenges our customers are facing.”

“In today’s environment where system integration is increasingly required and substrate supplies are constrained, Samsung Foundry and Amkor Technology have successfully co-developed H-Cube to overcome these challenges,” said JinYoung Kim, Senior Vice President of Global R&D Center at Amkor Technology. “This development lowers barriers to entry in the HPC/AI market and demonstrates successful collaboration and partnership between the foundry and outsourced semiconductor assembly and test (OSAT) company.”

H-Cube Structure and Features

2.5D packaging enables logic chips or high-bandwidth memory (HBM) to be placed on top of a silicon interposer in a small form factor. Samsung’s H-Cube technology features a hybrid substrate combined with a fine-pitch substrate which is capable of fine bump connection, and a High-Density Interconnection (HDI) substrate, to implement large sizes into 2.5D packaging.

With the recent increase in specifications required in the HPC, AI and networking application market segments, large-area packaging is becoming important as the number and size of chips mounted in one package increases or high-bandwidth communication is required. For attachment and connection of silicon dies including the interposer, fine-pitch substrates are essential but prices rise significantly following an increase in size.

H-Cube Package Structure Concept

When integrating six or more HBMs, the difficulty in manufacturing the large-area substrate increases rapidly, resulting in decreased efficiency. Samsung solved this problem by applying a hybrid substrate structure in which HDI substrates that are easy to implement in large-area are overlapped under a high-end fine-pitch substrate.

By decreasing the pitch of solder ball, which electrically connects the chip and the substrate, by 35% compared to the conventional ball pitch, the size of fine-pitch substrate can be minimized, while adding HDI substrate (module PCB) under the fine-pitch substrate to secure connectivity with the system board.

In addition, to enhance the reliability of the H-Cube solution, Samsung applied its proprietary signal/power integrity analysis technology that can stably supply power while minimizing the signal loss or distortion when stacking multiple logic chips and HBMs.

Looking ahead, in cooperation with its ecosystem partners, Samsung will hold its 3^rd Annual ‘Samsung Advanced Foundry Ecosystem (SAFE) Forum’ virtually on November 17 (PST).

For pre-registration on the SAFE forum, please visit https://www.samsungfoundry.com.

The new foundry line, which will focus on EUV-based 5 nanometer (nm) and below process technology, has just commenced construction this month and is expected to be in full operation in the second half of 2021. It will play a pivotal role as Samsung aims to expand the use of state-of-the-art process technologies across a myriad of current and next generation applications, including 5G, high-performance computing (HPC) and artificial intelligence (AI).

“This new production facility will expand Samsung’s manufacturing capabilities for sub-5nm process and enable us to rapidly respond to the increasing demand for EUV-based solutions,” said Dr. ES Jung, President and Head of Foundry Business at Samsung Electronics. “We remain committed to addressing the needs of our customers through active investments and recruitment of talents. This will enable us to continue to break new ground while driving robust growth for Samsung’s foundry business.”

Following the initial mass production of the EUV-based 7nm process in early 2019, Samsung recently added a new EUV-dedicated V1 line in Hwaseong, Korea, to its global foundry network. With the new Pyeongtaek facility starting full operation in 2021, Samsung’s foundry capacity based on EUV is expected to increase significantly.

Samsung is scheduled to start mass production of 5nm EUV process in the Hwaseong fab in the second half of this year.

With the addition of the Pyeongtaek fab, Samsung will have a total of seven foundry production lines located in South Korea and the United States, comprised of six 12-inch lines and one 8-inch line.

Baidu KUNLUN chip is built on the company’s advanced XPU, a home-grown neural processor architecture for cloud, edge, and AI, as well as Samsung’s 14-nanometer (nm) process technology with its I-Cube (Interposer-Cube) package solution.

The chip offers 512 gigabytes per second (GBps) memory bandwidth and supplies up to 260 Tera operations per second (TOPS) at 150 watts. In addition, the new chip allows Ernie, a pre-training model for natural language processing, to infer three times faster than the conventional GPU/FPGA-accelerating model.

Leveraging the chip’s limit-pushing computing power and power efficiency, Baidu can effectively support a wide variety of functions including large-scale AI workloads, such as search ranking, speech recognition, image processing, natural language processing, autonomous driving, and deep learning platforms like PaddlePaddle.

Through the first foundry cooperation between the two companies, Baidu will provide advanced AI platforms for maximizing AI performance, and Samsung will expand its foundry business into high performance computing (HPC) chips that are designed for cloud and edge computing.

“We are excited to lead the HPC industry together with Samsung Foundry,” said OuYang Jian, Distinguished Architect of Baidu. “Baidu KUNLUN is a very challenging project since it requires not only a high level of reliability and performance at the same time, but is also a compilation of the most advanced technologies in the semiconductor industry. Thanks to Samsung’s state of the art process technologies and competent foundry services, we were able to meet and surpass our goal to offer superior AI user experience. ”

“We are excited to start a new foundry service for Baidu using our 14nm process technology,” said Ryan Lee, vice president of Foundry Marketing at Samsung Electronics. “Baidu KUNLUN is an important milestone for Samsung Foundry as we’re expanding our business area beyond mobile to datacenter applications by developing and mass-producing AI chips. Samsung will provide comprehensive foundry solutions from design support to cutting-edge manufacturing technologies, such as 5LPE, 4LPE, as well as 2.5D packaging.”

As higher performance is required in diverse applications such as AI and HPC, chip integration technology is becoming more and more important. Samsung’s I-Cube technology, which connects a logic chip and high bandwidth memory (HBM) 2 with an interposer, provides higher density/ bandwidth on minimum size by utilizing Samsung’s differentiated solutions.

Compared to previous technology, these solutions maximize product performance with more than 50% improved power/signal integrity. It is anticipated that I-Cube technology will mark a new epoch in the heterogeneous computing market. Samsung is also developing more advanced packaging technologies, such as redistribution layers (RDL) interposer and 4x, 8x HBM integrated package.

2.5D Package Structure

About Baidu

Baidu, Inc. is the leading Chinese language Internet search provider. Baidu aims to make the complicated world simpler through technology. Baidu’s ADSs trade on the NASDAQ Global Select Market under the symbol “BIDU”. Currently, ten ADSs represent one Class A ordinary share.

Samsung Electronics, a world leader in advanced semiconductor technology, today held the first Samsung Advanced Foundry Ecosystem (SAFE) Forum 2019 in the United States. By sharing the latest technology trends and strengthening cooperation within the foundry ecosystem, Samsung showcased its strong dedication to customers.

SAFE Forum is designed to provide an opportunity for SAFE partner companies to directly meet with customers to discuss comprehensive design technology infrastructure, including electronic design automation (EDA), intellectual property (IP), cloud, design service, and packaging, which is critical to efficiently developing and manufacturing semiconductor products.

While the Samsung Foundry Forum (SFF) has served as a channel to present Samsung’s technology roadmap and leadership to customers, the newly held SAFE Forum is distinctive in that it allows its partners to engage deeper and more efficient collaboration within Samsung’s foundry ecosystem by directly communicating in detail with customers on their own design support solutions proven by Samsung.

“SAFE program has grown in quality over the past two years; it has expanded the number of competitive partnerships and support of flexible product design for customers as well as bolstered the relationship between our partners, customers, and Samsung foundry,” said Jae-hong Park, executive vice president of Foundry Design Platform Development at Samsung Electronics. “We will continue our efforts in enhancing accessibility to enable customers to more easily utilize Samsung’s excellent foundry solutions.”

As the latest system-on-chip (SoC) product requires more sophisticated features in a smaller surface size than before, the number of considerations in IC design optimization has increased exponentially: performance, power, security, design, density, etc.

To actively respond to these IC design trends and lower the design barrier for developing competitive SoCs, Samsung Electronics launched the SAFE program in early 2018.

Under the slogan “Partnering for a bold silicon future”, details on the latest global IC design trends as well as benefits of the efficient easy-to-use platform design infrastructure were introduced.

With more than 400 industry experts attending the first SAFE Forum, 12 detailed sessions were given by around 30 speakers from 15 partner companies, focusing on emerging high-growth applications, including high-performing computer (HPC), internet-of-things (IoT), and automotive. Attendees also had a chance to discover the optimal solution for implementing their new ideas into chips through 40 partner booths at the venue.

AMD and Samsung Electronics today announced a multi-year strategic partnership in ultra low power, high performance mobile graphics IP based on AMD Radeon graphics technologies. As part of the partnership, Samsung will license AMD graphics IP and will focus on advanced graphics technologies and solutions that are critical for enhancing innovation across mobile applications, including smartphones.

“As we prepare for disruptive changes in technology and discover new opportunities, our partnership with AMD will allow us to bring groundbreaking graphics products and solutions to market for tomorrow’s mobile applications,” said Inyup Kang, president of Samsung Electronics’ S.LSI Business. “We look forward to working with AMD to accelerate innovations in mobile graphics technologies that will help take future mobile computing to the next level.”

“Adoption of our Radeon graphics technologies across the PC, game console, cloud and HPC markets has grown significantly and we are thrilled to now partner with industry leader Samsung to accelerate graphics innovation in the mobile market,” said Dr. Lisa Su, AMD president and CEO. “This strategic partnership will extend the reach of our high-performance Radeon graphics into the mobile market, significantly expanding the Radeon user base and development ecosystem.”

Key terms of the partnership include:

• AMD will license custom graphics IP based on the recently announced, highly-scalable RDNA graphics architecture to Samsung for use in mobile devices, including smartphones, and other products that complement AMD product offerings.
• Samsung will pay AMD technology license fees and royalties.

“By developing innovative technologies in DRAM circuit design and process, we have broken through what has been a major barrier for DRAM scalability,” said Gyoyoung Jin, president of Memory Business at Samsung Electronics. “Through a rapid ramp-up of the 2nd-generation 10nm-class DRAM, we will expand our overall 10nm-class DRAM production more aggressively, in order to accommodate strong market demand and continue to strengthen our business competitiveness.”

Samsung’s 2nd-generation 10nm-class 8Gb DDR4 features an approximate 30 percent productivity gain over the company’s 1st–generation 10nm-class 8Gb DDR4. In addition, the new 8Gb DDR4’s performance levels and energy efficiency have been improved about 10 and 15 percent respectively, thanks to the use of an advanced, proprietary circuit design technology. The new 8Gb DDR4 can operate at 3,600 megabits per second (Mbps) per pin, compared to 3,200 Mbps of the company’s 1x-nm 8Gb DDR4.

To enable these achievements, Samsung has applied new technologies, without the use of an EUV process. The innovation here includes use of a high-sensitivity cell data sensing system and a progressive “air spacer” scheme.

In the cells of Samsung’s 2nd-generation 10nm-class DRAM, a newly devised data sensing system enables a more accurate determination of the data stored in each cell, which leads to a significant increase in the level of circuit integration and manufacturing productivity.

The new 10nm-class DRAM also makes use of a unique air spacer that has been placed around its bit lines to dramatically decrease parasitic capacitance**. Use of the air spacer enables not only a higher level of scaling, but also rapid cell operation.

With these advancements, Samsung is now accelerating its plans for much faster introductions of next-generation DRAM chips and systems, including DDR5, HBM3, LPDDR5 and GDDR6, for use in enterprise servers, mobile devices, supercomputers, HPC systems and high-speed graphics cards.

Samsung has finished validating its 2nd-generation 10nm-class DDR4 modules with CPU manufacturers, and next plans to work closely with its global IT customers in the development of more efficient next-generation computing systems.

In addition, the world’s leading DRAM producer expects to not only rapidly increase the production volume of the 2nd-generation 10nm-class DRAM lineups, but also to manufacture more of its mainstream 1st-generation 10nm-class DRAM, which together will meet the growing demands for DRAM in premium electronic systems worldwide.

* Editors’ Note 1: 10nm-class denotes a process technology node somewhere between 10 and 19 nanometers. Samsung launched its first DRAM product based on a 10nm-class process in February, 2016.

** Editors’ Note 2: Parasitic capacitance is unwanted capacitance that exists between the parts of an electronic circuit or electronic part, because of their proximity to each other. When two electrical conductors at different voltages are too close together, they are adversely affected by each other’s electric field and store opposite electric charges such as those produced by a capacitor.