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 industy updates delivered to you every week!

SRC Spends $200M on University Research Centers

January 16, 2018

The Semiconductor Research Corporation, as part of its JUMP initiative, has awarded $200 million to fund six research centers whose areas of focus span cognitive computing, memory-centric computing, high-speed communicat Read more…

By John Russell

US Seeks to Automate Video Analysis

January 16, 2018

U.S. military and intelligence agencies continue to look for new ways to use artificial intelligence to sift through huge amounts of video imagery in hopes of freeing analysts to identify threats and otherwise put their Read more…

By George Leopold

URISC@SC17 and the #LongestLastMile

January 11, 2018

A multinational delegation recently attended the Understanding Risk in Shared CyberEcosystems workshop, or URISC@SC17, in Denver, Colorado. URISC participants and presenters from 11 countries, including eight African nations, 12 U.S. states, Canada, India and Nepal, also attended SC17, the annual international conference for high performance computing, networking, storage and analysis that drew nearly 13,000 attendees. Read more…

By Elizabeth Leake, STEM-Trek Nonprofit

HPE Extreme Performance Solutions

HPE and NREL Take Steps to Create a Sustainable, Energy-Efficient Data Center with an H2 Fuel Cell

As enterprises attempt to manage rising volumes of data, unplanned data center outages are becoming more common and more expensive. As the cost of downtime rises, enterprises lose out on productivity and valuable competitive advantage without access to their critical data. Read more…

When the Chips Are Down

January 11, 2018

In the last article, "The High Stakes Semiconductor Game that Drives HPC Diversity," I alluded to the challenges facing the semiconductor industry and how that may impact the evolution of HPC systems over the next few years. I thought I’d lift the covers a little and look at some of the commercial challenges that impact the component technology we use in HPC. Read more…

By Dairsie Latimer

SRC Spends $200M on University Research Centers

January 16, 2018

The Semiconductor Research Corporation, as part of its JUMP initiative, has awarded $200 million to fund six research centers whose areas of focus span cognitiv Read more…

By John Russell

When the Chips Are Down

January 11, 2018

In the last article, "The High Stakes Semiconductor Game that Drives HPC Diversity," I alluded to the challenges facing the semiconductor industry and how that may impact the evolution of HPC systems over the next few years. I thought I’d lift the covers a little and look at some of the commercial challenges that impact the component technology we use in HPC. Read more…

By Dairsie Latimer

How Meltdown and Spectre Patches Will Affect HPC Workloads

January 10, 2018

There have been claims that the fixes for the Meltdown and Spectre security vulnerabilities, named the KPTI (aka KAISER) patches, are going to affect applicatio Read more…

By Rosemary Francis

Momentum Builds for US Exascale

January 9, 2018

2018 looks to be a great year for the U.S. exascale program. The last several months of 2017 revealed a number of important developments that help put the U.S. Read more…

By Alex R. Larzelere

ANL’s Rick Stevens on CANDLE, ARM, Quantum, and More

January 8, 2018

Late last year HPCwire caught up with Rick Stevens, associate laboratory director for computing, environment and life Sciences at Argonne National Laboratory, f Read more…

By John Russell

Chip Flaws ‘Meltdown’ and ‘Spectre’ Loom Large

January 4, 2018

The HPC and wider tech community have been abuzz this week over the discovery of critical design flaws that impact virtually all contemporary microprocessors. T Read more…

By Tiffany Trader

The @hpcnotes Predictions for HPC in 2018

January 4, 2018

I’m not averse to making predictions about the world of High Performance Computing (and Supercomputing, Cloud, etc.) in person at conferences, meetings, causa Read more…

By Andrew Jones

Fast Forward: Five HPC Predictions for 2018

December 21, 2017

What’s on your list of high (and low) lights for 2017? Volta 100’s arrival on the heels of the P100? Appearance, albeit late in the year, of IBM’s Power9? Read more…

By John Russell

US Coalesces Plans for First Exascale Supercomputer: Aurora in 2021

September 27, 2017

At the Advanced Scientific Computing Advisory Committee (ASCAC) meeting, in Arlington, Va., yesterday (Sept. 26), it was revealed that the "Aurora" supercompute Read more…

By Tiffany Trader

Japan Unveils Quantum Neural Network

November 22, 2017

The U.S. and China are leading the race toward productive quantum computing, but it's early enough that ultimate leadership is still something of an open questi Read more…

By Tiffany Trader

AMD Showcases Growing Portfolio of EPYC and Radeon-based Systems at SC17

November 13, 2017

AMD’s charge back into HPC and the datacenter is on full display at SC17. Having launched the EPYC processor line in June along with its MI25 GPU the focus he Read more…

By John Russell

Nvidia Responds to Google TPU Benchmarking

April 10, 2017

Nvidia highlights strengths of its newest GPU silicon in response to Google's report on the performance and energy advantages of its custom tensor processor. Read more…

By Tiffany Trader

IBM Begins Power9 Rollout with Backing from DOE, Google

December 6, 2017

After over a year of buildup, IBM is unveiling its first Power9 system based on the same architecture as the Department of Energy CORAL supercomputers, Summit a Read more…

By Tiffany Trader

Fast Forward: Five HPC Predictions for 2018

December 21, 2017

What’s on your list of high (and low) lights for 2017? Volta 100’s arrival on the heels of the P100? Appearance, albeit late in the year, of IBM’s Power9? Read more…

By John Russell

GlobalFoundries Puts Wind in AMD’s Sails with 12nm FinFET

September 24, 2017

From its annual tech conference last week (Sept. 20), where GlobalFoundries welcomed more than 600 semiconductor professionals (reaching the Santa Clara venue Read more…

By Tiffany Trader

Chip Flaws ‘Meltdown’ and ‘Spectre’ Loom Large

January 4, 2018

The HPC and wider tech community have been abuzz this week over the discovery of critical design flaws that impact virtually all contemporary microprocessors. T Read more…

By Tiffany Trader

Leading Solution Providers

Perspective: What Really Happened at SC17?

November 22, 2017

SC is over. Now comes the myriad of follow-ups. Inboxes are filled with templated emails from vendors and other exhibitors hoping to win a place in the post-SC thinking of booth visitors. Attendees of tutorials, workshops and other technical sessions will be inundated with requests for feedback. Read more…

By Andrew Jones

Tensors Come of Age: Why the AI Revolution Will Help HPC

November 13, 2017

Thirty years ago, parallel computing was coming of age. A bitter battle began between stalwart vector computing supporters and advocates of various approaches to parallel computing. IBM skeptic Alan Karp, reacting to announcements of nCUBE’s 1024-microprocessor system and Thinking Machines’ 65,536-element array, made a public $100 wager that no one could get a parallel speedup of over 200 on real HPC workloads. Read more…

By John Gustafson & Lenore Mullin

Delays, Smoke, Records & Markets – A Candid Conversation with Cray CEO Peter Ungaro

October 5, 2017

Earlier this month, Tom Tabor, publisher of HPCwire and I had a very personal conversation with Cray CEO Peter Ungaro. Cray has been on something of a Cinderell Read more…

By Tiffany Trader & Tom Tabor

Flipping the Flops and Reading the Top500 Tea Leaves

November 13, 2017

The 50th edition of the Top500 list, the biannual publication of the world’s fastest supercomputers based on public Linpack benchmarking results, was released Read more…

By Tiffany Trader

GlobalFoundries, Ayar Labs Team Up to Commercialize Optical I/O

December 4, 2017

GlobalFoundries (GF) and Ayar Labs, a startup focused on using light, instead of electricity, to transfer data between chips, today announced they've entered in Read more…

By Tiffany Trader

HPC Chips – A Veritable Smorgasbord?

October 10, 2017

For the first time since AMD's ill-fated launch of Bulldozer the answer to the question, 'Which CPU will be in my next HPC system?' doesn't have to be 'Whichever variety of Intel Xeon E5 they are selling when we procure'. Read more…

By Dairsie Latimer

Nvidia, Partners Announce Several V100 Servers

September 27, 2017

Here come the Volta 100-based servers. Nvidia today announced an impressive line-up of servers from major partners – Dell EMC, Hewlett Packard Enterprise, IBM Read more…

By John Russell

Intel Delivers 17-Qubit Quantum Chip to European Research Partner

October 10, 2017

On Tuesday, Intel delivered a 17-qubit superconducting test chip to research partner QuTech, the quantum research institute of Delft University of Technology (TU Delft) in the Netherlands. The announcement marks a major milestone in the 10-year, $50-million collaborative relationship with TU Delft and TNO, the Dutch Organization for Applied Research, to accelerate advancements in quantum computing. Read more…

By Tiffany Trader

  • arrow
  • Click Here for More Headlines
  • arrow
Share This