Micron Readies Hybrid Memory Cube for Debut

By Tiffany Trader

January 17, 2013

The next-generation memory-maker Micron Technology was one of the many innovative companies demonstrating its wares on the Supercomputing Conference (SC12) show floor last November. Micron’s General Manager of Hybrid Technology Scott Graham was on hand to discuss the latest developments in their Hybrid Memory Cube (HMC) technology, a multi-chip module (MCM) that aims to address one of the biggest challenges in high performance computing: scaling the memory wall.

Memory architectures haven’t kept pace with the bandwidth requirements of multicore processors. As microprocessor speeds out-accelerated DRAM memory speeds, a bottleneck developed that is referred to as the memory wall. Stacked memory applications, however, enable higher memory bandwidth.

The Hybrid Memory Cube (HMC) is a new memory architecture that combines a high-speed logic layer with a stack of through-silicon-via (TSV) bonded memory die that enables impressive advantages over current technology. According to company figures, a single HMC offers a 15x performance increase and uses 70 percent less energy per bit when compared to DDR3 memory, and takes up 90 percent less space than today’s RDIMMs. The Cube is also scalable per application, which is not possible with DDR3 and DDR4. System designers have the option of employing the HMC as near memory for best performance or in a scalable module form factor, as far memory, for optimum power efficiency.

Micron HMC demo
Micron HMC demo at SC12 – screen shot

This is a huge leap forward from a technology perspective, noted Graham, compared to DDRx and other boutique memory products that are out there.

As HPCwire editor Michael Feldman explained in an earlier review of the technology:

The speedup and better energy efficiency is achieved principally through parallelism. Because the memory chips are stacked, there is more space for I/O pins through the TSVs. Thus each DRAM can be accessed with more (and/or wider) channels. The end result is that the controller can access many more banks of memory concurrently than can be accomplished with a two-dimensional DIMM. And because the controller and DRAM chips are in close proximity, latencies can be extremely low.

Judging by the degree and caliber of community involvement, Micron’s HMC technology represents a real breakthrough in how memory is used. In October 2011, Micron together with Samsung Electronics Co., Ltd., formed the Hybrid Memory Cube Consortium, tasked with developing an open industry standard that facilitates HMC integration into a wide variety of systems, platforms and applications.

The consortium is managed by a group of ten developers (Altera, ARM, HP, IBM, Micron, Microsoft, Open Silicon, Samsung, SK Hynix, and Xilinx), which have equal voting power on the final specification, along with an additional 75 adopters. The members are currently reviewing a draft specification, scheduled to be released next month, that details the communication interface between the Cube and the processor – CPU or GPU or FPGA.

Speaking to the initial set of targeted applications, the driving body notes that the “Hybrid Memory Cube represents the key to extending network system performance to push through the challenges of new 100G and 400G infrastructure growth. Eventually, HMC will drive exascale CPU system performance growth for next generation HPC systems.”

Companies are eager to get their hands on this product and Micron is working with an aggressive roadmap to meet that demand, Graham told HPCwire. The Gen1 demo, on display at SC12, was real silicon, and engineering samples for the Gen2 device are due out this summer. If all goes as planned, the Hybrid Memory Cube will be in full production at the end of this year or early 2014. In fact, contracts are already in place for the 2014 timeframe.

Hybrid Memory Cube demo
Side shot of the HMC demo at SC12. The actual Cube is on the far corner of the board.

High-speed networking vendors have signed up for the first productized version – with an HPC-centric product not far behind. Micron was not at liberty to identify these initial customers, but a look at the list of consortium partners turns up candidates like Lawrence Livermore, Cray, NEC, and T-Platforms.

The first couple of HMC implementations will be straight DRAM, but Micron and others are researching alternative memory combinations, for example multi-memory stacks that employ NAND flash and DRAM.

“There are all kinds of things you can do within the logic layer to pull different types of functionality, that are maybe off-chip today, into the logic layer and innovate further, with more functionality, better performance, and lower energy,” noted Graham.

Micron is framing this as an aggressive technology, emphasizing that this is the first time that all three of the largest memory makers (Micron, Samsung, and presumably SK Hynix) have teamed up.

“All of the memory manufacturers face the same challenge of being able to scale beyond 20nm, so we’re all coming up to even a bigger memory wall eventually,” explained Graham “Beyond 20nm, you’re going to have to move to some kind of management layer in order to continue with DRAM technology.”

The logic layer developed for the Cube allows for different flavors of technology – like spin-torque, memristor and others – to extend the viability of DRAM memory. “This means we can be really innovative with different types of cell technology and process technology so we can bring a more standard memory into the marketplace without these major shifts,” said Graham.

According to the Micron rep, they’ve also seen interest from companies outside the consortium. Most notably absent from the member roster are AMD and Intel, but that by no means implies a lack of involvement. Intel, for its part, demonstrated a prototype HMC device during the fall Intel Developer Forum in September 2011, deeming it the fastest and most efficient DRAM ever built. As Graham put it, these companies have opted not to be involved in the open standard in order to develop their own way of using the technology.

Still a year away from production, pricing for Cube products has not been announced, but early adopters should expect to pay a premium for the benefits of increased performance, power efficiency and space savings. The exascale community, in particular, will be paying close attention. If they’re to realize their goal of a 10^18 FLOPS machine within a 20MW power envelope, they’ll need all the help they can get.

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!

ISC 2024 Takeaways: Love for Top500, Extending HPC Systems, and Media Bashing

May 23, 2024

The ISC High Performance show is typically about time-to-science, but breakout sessions also focused on Europe's tech sovereignty, server infrastructure, storage, throughput, and new computing technologies. This round Read more…

HPC Pioneer Gordon Bell Passed Away

May 22, 2024

Legendary computer scientist Gordon Bell passed away last Friday at his home in Coronado, CA. He was 89. The New York Times has a nice tribute piece. A long-time pioneer with Digital Equipment Corp, he pushed hard for de Read more…

ISC 2024 — A Few Quantum Gems and Slides from a Packed QC Agenda

May 22, 2024

If you were looking for quantum computing content, ISC 2024 was a good place to be last week — there were around 20 quantum computing related sessions. QC even earned a slide in Kathy Yelick’s opening keynote — Bey Read more…

Atos Outlines Plans to Get Acquired, and a Path Forward

May 21, 2024

Atos – via its subsidiary Eviden – is the second major supercomputer maker outside of HPE, while others have largely dropped out. The lack of integrators and Atos' financial turmoil have the HPC market worried. If Atos goes under, HPE will be the only major option for building large-scale systems. Read more…

Core42 Is Building Its 172 Million-core AI Supercomputer in Texas

May 20, 2024

UAE-based Core42 is building an AI supercomputer with 172 million cores which will become operational later this year. The system, Condor Galaxy 3, was announced earlier this year and will have 192 nodes with Cerebras Read more…

Google Announces Sixth-generation AI Chip, a TPU Called Trillium

May 17, 2024

On Tuesday May 14th, Google announced its sixth-generation TPU (tensor processing unit) called Trillium.  The chip, essentially a TPU v6, is the company's latest weapon in the AI battle with GPU maker Nvidia and clou Read more…

ISC 2024 Takeaways: Love for Top500, Extending HPC Systems, and Media Bashing

May 23, 2024

The ISC High Performance show is typically about time-to-science, but breakout sessions also focused on Europe's tech sovereignty, server infrastructure, storag Read more…

ISC 2024 — A Few Quantum Gems and Slides from a Packed QC Agenda

May 22, 2024

If you were looking for quantum computing content, ISC 2024 was a good place to be last week — there were around 20 quantum computing related sessions. QC eve Read more…

Atos Outlines Plans to Get Acquired, and a Path Forward

May 21, 2024

Atos – via its subsidiary Eviden – is the second major supercomputer maker outside of HPE, while others have largely dropped out. The lack of integrators and Atos' financial turmoil have the HPC market worried. If Atos goes under, HPE will be the only major option for building large-scale systems. Read more…

Google Announces Sixth-generation AI Chip, a TPU Called Trillium

May 17, 2024

On Tuesday May 14th, Google announced its sixth-generation TPU (tensor processing unit) called Trillium.  The chip, essentially a TPU v6, is the company's l Read more…

Europe’s Race towards Quantum-HPC Integration and Quantum Advantage

May 16, 2024

What an interesting panel, Quantum Advantage — Where are We and What is Needed? While the panelists looked slightly weary — their’s was, after all, one of Read more…

The Future of AI in Science

May 15, 2024

AI is one of the most transformative and valuable scientific tools ever developed. By harnessing vast amounts of data and computational power, AI systems can un Read more…

Some Reasons Why Aurora Didn’t Take First Place in the Top500 List

May 15, 2024

The makers of the Aurora supercomputer, which is housed at the Argonne National Laboratory, gave some reasons why the system didn't make the top spot on the Top Read more…

ISC 2024 Keynote: High-precision Computing Will Be a Foundation for AI Models

May 15, 2024

Some scientific computing applications cannot sacrifice accuracy and will always require high-precision computing. Therefore, conventional high-performance c 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…

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…

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…

Atos Outlines Plans to Get Acquired, and a Path Forward

May 21, 2024

Atos – via its subsidiary Eviden – is the second major supercomputer maker outside of HPE, while others have largely dropped out. The lack of integrators and Atos' financial turmoil have the HPC market worried. If Atos goes under, HPE will be the only major option for building large-scale systems. 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…

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…

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…

Some Reasons Why Aurora Didn’t Take First Place in the Top500 List

May 15, 2024

The makers of the Aurora supercomputer, which is housed at the Argonne National Laboratory, gave some reasons why the system didn't make the top spot on the Top Read more…

Leading Solution Providers

Contributors

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…

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…

The NASA Black Hole Plunge

May 7, 2024

We have all thought about it. No one has done it, but now, thanks to HPC, we see what it looks like. Hold on to your feet because NASA has released videos of wh 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…

Intel Plans Falcon Shores 2 GPU Supercomputing Chip for 2026  

August 8, 2023

Intel is planning to onboard a new version of the Falcon Shores chip in 2026, which is code-named Falcon Shores 2. The new product was announced by CEO Pat Gel 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…

How the Chip Industry is Helping a Battery Company

May 8, 2024

Chip companies, once seen as engineering pure plays, are now at the center of geopolitical intrigue. Chip manufacturing firms, especially TSMC and Intel, have b Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire