DDR5 Memory Spec Doubles Data Rate, Quadruples Density

By Tiffany Trader

July 16, 2020

Standards group JEDEC announced the publication of the DDR5 SDRAM spec, the next-generation standard for random access memory (RAM). Compared to DDR4, the DDR5 spec delivers twice the performance and improved power efficiency, addressing ever-growing demand from datacenter and cloud environments, as well as artificial intelligence and HPC applications.

Providing up to 6.4 Gbps, DDR5 doubles the bandwidth of its predecessor, DDR4, which tops out at 3.2 Gpbs. At launch, DDR5 modules will reach 4.8 Gbps, providing a 50 percent improvement versus the previous generation. Density goes up four-fold with maximum density increasing from 16 Gigabits per die to 64 Gigabits per die in the new spec. JEDEC representatives indicated there will be both 8 Gigabit and 16 Gigabit DDR5 products at launch.

DDR5 boosts signaling rates to 6,400 MT/s, but Desi Rhoden, chairman, JEDEC JC-42 memory committee, and executive vice president of Montage Technology, says there are discussions about going beyond that. “I think you can expect that you might see something above that as well — and much improved channel utilization,” he said in a press briefing held earlier this week.

DDR DRAM Generational Evolution (Source: JEDEC)

A new feature, Decision Feedback Equalization, was added to improve IO speed scalability. “It enables us to build really high frequency interfaces,” said Rhoden. “We didn’t need this before because we were at performances that did not demand it, but now we have to use equalization to get to the high speed IO. And this is the first time we’ve ever had it in the DRAM itself. We’ve had it in support logic before but the first time in the DRAM itself.”

A fine grain refresh feature, all bank refresh, improves 16 Gigabit device latency. Same bank refresh offers the ability to refresh in one part of the die while other parts are in use, providing higher utilization.

Additional features/specs include:

• On-die ECC and other scaling features enable manufacturing on advanced process nodes.
• Improved power efficiency enabled by Vdd going from 1.2V to 1.1V as compared to DDR4.
• Use of the MIPI Alliance I3C Basic specification for system management bus.
• At the module level, voltage regulator on DIMM design enables pay as you go scalability, better voltage tolerance for improved DRAM yields and the potential to further reduce power consumption.
• The DIMM has two 40-bit (32 data bits plus eight ECC bits) independent sub-channels on the same module for efficiency and improved reliability.

The DDR5 spec also increases stacking capability, doubling the height from the previous generation. “The DDR4 spec defines up to an 8-high stack, and for most of the industry the maximum stack height was 4-high. For DDR5, we have defined up to a 16-high stack, and expect up to 8-high stack products,” said Johnny Kim, chairman, JEDEC JC-42.3C subcommittee and staff engineer, memory product planning and enabling at Samsung.

With a DDR5 DIMM supporting 40 placements of DRAM, an 8-high stack at 64 gigabits per die brings the upper capacity to 2 terabytes.

Devices are sampling now and CPUs are available to work with them, JEDEC said. Historically, it’s taken about 18 months to transition from one generation to the next and the JEDEC representatives expect that trend to hold with the server market leading. “The server datacenter market led for the transition to DDR4 back in 2014, and the datacenter market has grown substantially since that time. So we think that that’ll [even more so] be the snowplow for DDR5 adoption,” said Paul Fahey, JEDEC board of directors and vice president DRAM technology at SK hynix.

The previous two DDR generations have come at about a seven-year cadence, and this longevity, along with the demands of the data age, set a high bar for the DDR5 spec and roadmap. “These generations always live longer than initially anticipate them to live,” said Rhoden. “DDR5, because it does have so much capability built into it, has the potential to live quite a long life.”

“We added a lot into the spec to give it that longevity,” noted Frank Ross, JEDEC board of directors and senior member of technical staff, lead architect, Micron. “Whether we use all of those features and all of the capacities and so forth is yet to be seen. But we’ve seen each subsequent DRAM generation last longer than previous one as new applications come around. We’ve improved DRAM reliability quite a bit over the years. You have applications that will continue to use DDR3 and DDR4 for a long time, and I imagine DDR5 will be the same.”

Going forward though, the expectation is that all new designs will be focused on the newest standard. “To take advantage of the kinds of things that DDR5 offers, I think people will be wanting to design in it and as quickly as possible,” said Ross.

“We’ve got probably the best standard we’ve ever produced,” Ross added. “I think the industry is going to be very impressed. And everyone has to remember, DDR5 is a system level solution. So we’re producing a component spec at the same time we’re producing a module spec, as well as support components. So there’s just a tremendous amount of work that goes into the spec and in the end, we have an extremely high quality document.”

Over 150 companies were involved in the creation of this spec. Micron, Samsung, SK hynix, Synopsys, Intel and AMD are among the companies expressing their support and engagement.

Micron Technology, which announced DDR5 RDIMM samples in January (2020), is now launching an enablement program to provide early access to technical resources, products and ecosystem partners. The program will aid in the design, development and qualification of next-generation computing platforms that use DDR5, said Mircon.

SK Hynix has been working on DDR5 samples since 2018, and expects to start mass manufacturing by the end of this year.

Synopsys introduced the industry’s first JEDEC DDR5 compliant Verification IP (VIP) for DDR5 DRAM/DIMM to enable the design and verification of next-generation memory devices.

The DDR5 SDRAM (JESD79-5) spec document is available for download from the JEDEC website.

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industry updates delivered to you every week!

Anders Dam Jensen on HPC Sovereignty, Sustainability, and JU Progress

April 23, 2024

The recent 2024 EuroHPC Summit meeting took place in Antwerp, with attendance substantially up since 2023 to 750 participants. HPCwire asked Intersect360 Research senior analyst Steve Conway, who closely tracks HPC, AI, Read more…

AI Saves the Planet this Earth Day

April 22, 2024

Earth Day was originally conceived as a day of reflection. Our planet’s life-sustaining properties are unlike any other celestial body that we’ve observed, and this day of contemplation is meant to provide all of us Read more…

Intel Announces Hala Point – World’s Largest Neuromorphic System for Sustainable AI

April 22, 2024

As we find ourselves on the brink of a technological revolution, the need for efficient and sustainable computing solutions has never been more critical.  A computer system that can mimic the way humans process and s Read more…

Empowering High-Performance Computing for Artificial Intelligence

April 19, 2024

Artificial intelligence (AI) presents some of the most challenging demands in information technology, especially concerning computing power and data movement. As a result of these challenges, high-performance computing Read more…

Kathy Yelick on Post-Exascale Challenges

April 18, 2024

With the exascale era underway, the HPC community is already turning its attention to zettascale computing, the next of the 1,000-fold performance leaps that have occurred about once a decade. With this in mind, the ISC Read more…

2024 Winter Classic: Texas Two Step

April 18, 2024

Texas Tech University. Their middle name is ‘tech’, so it’s no surprise that they’ve been fielding not one, but two teams in the last three Winter Classic cluster competitions. Their teams, dubbed Matador and Red Read more…

Anders Dam Jensen on HPC Sovereignty, Sustainability, and JU Progress

April 23, 2024

The recent 2024 EuroHPC Summit meeting took place in Antwerp, with attendance substantially up since 2023 to 750 participants. HPCwire asked Intersect360 Resear Read more…

AI Saves the Planet this Earth Day

April 22, 2024

Earth Day was originally conceived as a day of reflection. Our planet’s life-sustaining properties are unlike any other celestial body that we’ve observed, Read more…

Kathy Yelick on Post-Exascale Challenges

April 18, 2024

With the exascale era underway, the HPC community is already turning its attention to zettascale computing, the next of the 1,000-fold performance leaps that ha Read more…

Software Specialist Horizon Quantum to Build First-of-a-Kind Hardware Testbed

April 18, 2024

Horizon Quantum Computing, a Singapore-based quantum software start-up, announced today it would build its own testbed of quantum computers, starting with use o Read more…

MLCommons Launches New AI Safety Benchmark Initiative

April 16, 2024

MLCommons, organizer of the popular MLPerf benchmarking exercises (training and inference), is starting a new effort to benchmark AI Safety, one of the most pre Read more…

Exciting Updates From Stanford HAI’s Seventh Annual AI Index Report

April 15, 2024

As the AI revolution marches on, it is vital to continually reassess how this technology is reshaping our world. To that end, researchers at Stanford’s Instit Read more…

Intel’s Vision Advantage: Chips Are Available Off-the-Shelf

April 11, 2024

The chip market is facing a crisis: chip development is now concentrated in the hands of the few. A confluence of events this week reminded us how few chips Read more…

The VC View: Quantonation’s Deep Dive into Funding Quantum Start-ups

April 11, 2024

Yesterday Quantonation — which promotes itself as a one-of-a-kind venture capital (VC) company specializing in quantum science and deep physics  — announce Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Leading Solution Providers

Contributors

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Eyes on the Quantum Prize – D-Wave Says its Time is Now

January 30, 2024

Early quantum computing pioneer D-Wave again asserted – that at least for D-Wave – the commercial quantum era has begun. Speaking at its first in-person Ana Read more…

GenAI Having Major Impact on Data Culture, Survey Says

February 21, 2024

While 2023 was the year of GenAI, the adoption rates for GenAI did not match expectations. Most organizations are continuing to invest in GenAI but are yet to Read more…

The GenAI Datacenter Squeeze Is Here

February 1, 2024

The immediate effect of the GenAI GPU Squeeze was to reduce availability, either direct purchase or cloud access, increase cost, and push demand through the roof. A secondary issue has been developing over the last several years. Even though your organization secured several racks... Read more…

Intel’s Xeon General Manager Talks about Server Chips 

January 2, 2024

Intel is talking data-center growth and is done digging graves for its dead enterprise products, including GPUs, storage, and networking products, which fell to Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire