Commodity Memory for a High Performance World: The View from Samsung

By Nicole Hemsoth

February 21, 2012

As CPUs get ever more powerful, their hunger for data is outstripping the ability of memory systems to feed them. This is especially true in high performance computing, where memory capacity is often constrained by cost, and more recently, energy consumption. With larger supercomputers now incorporating upwards of hundreds of terabytes of main memory, and often with multiple terabytes of flash storage, this challenge will continue to grow.

As one of the world leaders in memory solutions, Samsung Semiconductor has been a key supplier of DRAM and NAND components that end up in high performance computing systems. Dr. Byungse So, who heads the Memory Product Planning & Application Engineering team at Samsung, shares his thoughts about the memory technologies needed by performance-minded users today and what might come next.

HPCwire: The memory wall is perhaps one of the biggest impediments in high performance computing today. What is the main reason that DRAM performance has failed to keep pace with processor performance?

Byungse So: In current system architectures, the CPU always needs high bandwidth and high density memory with low cost to keep feeding data to the computing engine. Therefore system memory has typically been a module-based commodity solution using multiple standard DRAM components. Due to its cost-driven design, system performance is compromised. It is time to shift gears by switching from cost-optimized to performance-optimized designs via application specific memory.

HPCwire: So what types of innovations will be needed? Are there DRAM technologies on the horizon that promise to do this?

So: Samsung has been exploring ways of narrowing the gap. Short term, Samsung will continue to provide the highest speed system and graphic memory. In the long run, Samsung will be investigating new interface technologies to meet high bandwidth requirements aimed at double-digit performance improvements over DDR3. To make this happen, close collaboration with CPU producers, platform builders as well as system users, is required.

HPCwire: Memory capacity can be an additional impediment to performance. Given the need for terabytes of memory for some HPC applications and the expense that entails, is there a way to build reasonably-priced systems that can support big memory applications?

So: Samsung has been leading the market with the highest capacity memory solutions and is already providing solutions which allow building terascale system memory for a single dual-processor system. Combined with the most advanced production process, Samsung will keep investigating how new stacking technologies including 3DS — 3D-Stacking –can allow adequate memory support of even most capacity-hungry systems.

HPCwire: The commodity DRAM business is well known for being rather unforgiving to suppliers, with some firms like OCZ exiting the market and others like Qimonda eventually going bankrupt. Why is the DRAM business so precarious and how has Samsung managed to maintain its viability in this segment?

So: DRAM as commodity memory has been under continuous pressure from its primary users, that is, the PC and notebook market, to continuously lower its cost. This enormous cost pressure has kept a number of suppliers in the red for a long time, ultimately pushing some suppliers out of the market, while also leading to designs compromising between cost and performance. Samsung’s way out of this dilemma is a combined focus on industry-best economies of scale, industry leading process technology and optimized, application-oriented product solutions for both mobile and server applications.

HPCwire: How do you think NAND memory technology can best be applied in high performance computing systems?

So: Solid state drives are the next-generation storage devices that have overcome the shortcomings of rotating media in high performance computing systems. The SSD adoption rate in volume servers is supposed to grow dramatically. Its interface will slowly be changing from SATA to SAS or PCIe for easy migration.

The most important parts in this emerging product line are the NAND flash components as well as the controllers which manage the input and output of data. Other major components are DRAM, which help buffer during data input and output, and the firmware that drives an SSD.

Samsung is able to combine its extensive know-how, stemming from the design and the production of billions of NAND flash and DRAM components, with its long history of designing countless controllers and firmware, as a company not being “only” vertically integrated.

HPCwire: Are there other solid state memory technologies that you believe will prove their worth commercially? If so, how will they change the memory-storage hierarchy?

So: Many studies and researches on fast non-volatile memory have been conducted in the past years, such as PRAM and MRAM as potential future memory technologies. However, more time is needed to examine their commercial value, as currently no existing hardware can fully utilize the features of these NVM solutions in their different roles.

Based on the maturity of the chosen technology, the usage model might also affect the memory hierarchy. It seems quite obvious that DRAM speed like fast NVM can change the existing memory hierarchy. OS experts may have better answers to this question.

HPCwire: Will these newer technologies eventually displace NAND or even DRAM?

So: It will take more than just better technology to replace existing memories, as they possibly impact system architecture and the value chain. Hence we expect that these new technologies will slowly penetrate into different parts of systems and industries and start to gradually build a new ecosystem. Eventually though, a large portion of NAND and DRAM will be replaced.

Dr. So will be delivering a keynote on advanced memory technology at this year’s International Supercomputing Conference (ISC’12) in Hamburg Germany. His presentation will take place on Tuesday, June 19.

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!

Data Vortex Users Contemplate the Future of Supercomputing

October 19, 2017

Last month (Sept. 11-12), HPC networking company Data Vortex held its inaugural users group at Pacific Northwest National Laboratory (PNNL) bringing together about 30 participants from industry, government and academia t Read more…

By Tiffany Trader

AI Self-Training Goes Forward at Google DeepMind

October 19, 2017

DeepMind, Google’s AI research organization, announced today in a blog that AlphaGo Zero, the latest evolution of AlphaGo (the first computer program to defeat a Go world champion) trained itself within three days to play Go at a superhuman level (i.e., better than any human) – and to beat the old version of AlphaGo – without leveraging human expertise, data or training. Read more…

By Doug Black

Researchers Scale COSMO Climate Code to 4888 GPUs on Piz Daint

October 17, 2017

Effective global climate simulation, sorely needed to anticipate and cope with global warming, has long been computationally challenging. Two of the major obstacles are the needed resolution and prolonged time to compute Read more…

By John Russell

HPE Extreme Performance Solutions

Transforming Genomic Analytics with HPC-Accelerated Insights

Advancements in the field of genomics are revolutionizing our understanding of human biology, rapidly accelerating the discovery and treatment of genetic diseases, and dramatically improving human health. Read more…

Student Cluster Competition Coverage New Home

October 16, 2017

Hello computer sports fans! This is the first of many (many!) articles covering the world-wide phenomenon of Student Cluster Competitions. Finally, the Student Cluster Competition coverage has come to its natural home: H Read more…

By Dan Olds

Data Vortex Users Contemplate the Future of Supercomputing

October 19, 2017

Last month (Sept. 11-12), HPC networking company Data Vortex held its inaugural users group at Pacific Northwest National Laboratory (PNNL) bringing together ab Read more…

By Tiffany Trader

AI Self-Training Goes Forward at Google DeepMind

October 19, 2017

DeepMind, Google’s AI research organization, announced today in a blog that AlphaGo Zero, the latest evolution of AlphaGo (the first computer program to defeat a Go world champion) trained itself within three days to play Go at a superhuman level (i.e., better than any human) – and to beat the old version of AlphaGo – without leveraging human expertise, data or training. Read more…

By Doug Black

Student Cluster Competition Coverage New Home

October 16, 2017

Hello computer sports fans! This is the first of many (many!) articles covering the world-wide phenomenon of Student Cluster Competitions. Finally, the Student Read more…

By Dan Olds

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

Fujitsu Tapped to Build 37-Petaflops ABCI System for AIST

October 10, 2017

Fujitsu announced today it will build the long-planned AI Bridging Cloud Infrastructure (ABCI) which is set to become the fastest supercomputer system in Japan Read more…

By John Russell

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

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

Intel Debuts Programmable Acceleration Card

October 5, 2017

With a view toward supporting complex, data-intensive applications, such as AI inference, video streaming analytics, database acceleration and genomics, Intel i Read more…

By Doug Black

Reinders: “AVX-512 May Be a Hidden Gem” in Intel Xeon Scalable Processors

June 29, 2017

Imagine if we could use vector processing on something other than just floating point problems.  Today, GPUs and CPUs work tirelessly to accelerate algorithms Read more…

By James Reinders

NERSC Scales Scientific Deep Learning to 15 Petaflops

August 28, 2017

A collaborative effort between Intel, NERSC and Stanford has delivered the first 15-petaflops deep learning software running on HPC platforms and is, according Read more…

By Rob Farber

Oracle Layoffs Reportedly Hit SPARC and Solaris Hard

September 7, 2017

Oracle’s latest layoffs have many wondering if this is the end of the line for the SPARC processor and Solaris OS development. As reported by multiple sources 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

How ‘Knights Mill’ Gets Its Deep Learning Flops

June 22, 2017

Intel, the subject of much speculation regarding the delayed, rewritten or potentially canceled “Aurora” contract (the Argonne Lab part of the CORAL “ Read more…

By Tiffany Trader

Google Releases Deeplearn.js to Further Democratize Machine Learning

August 17, 2017

Spreading the use of machine learning tools is one of the goals of Google’s PAIR (People + AI Research) initiative, which was introduced in early July. Last w 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

Graphcore Readies Launch of 16nm Colossus-IPU Chip

July 20, 2017

A second $30 million funding round for U.K. AI chip developer Graphcore sets up the company to go to market with its “intelligent processing unit” (IPU) in Read more…

By Tiffany Trader

Leading Solution Providers

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

Amazon Debuts New AMD-based GPU Instances for Graphics Acceleration

September 12, 2017

Last week Amazon Web Services (AWS) streaming service, AppStream 2.0, introduced a new GPU instance called Graphics Design intended to accelerate graphics. The Read more…

By John Russell

EU Funds 20 Million Euro ARM+FPGA Exascale Project

September 7, 2017

At the Barcelona Supercomputer Centre on Wednesday (Sept. 6), 16 partners gathered to launch the EuroEXA project, which invests €20 million over three-and-a-half years into exascale-focused research and development. Led by the Horizon 2020 program, EuroEXA picks up the banner of a triad of partner projects — ExaNeSt, EcoScale and ExaNoDe — building on their work... Read more…

By Tiffany Trader

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

Cray Moves to Acquire the Seagate ClusterStor Line

July 28, 2017

This week Cray announced that it is picking up Seagate's ClusterStor HPC storage array business for an undisclosed sum. "In short we're effectively transitioning the bulk of the ClusterStor product line to Cray," said CEO Peter Ungaro. Read more…

By Tiffany Trader

Intel Launches Software Tools to Ease FPGA Programming

September 5, 2017

Field Programmable Gate Arrays (FPGAs) have a reputation for being difficult to program, requiring expertise in specialty languages, like Verilog or VHDL. Easin Read more…

By Tiffany Trader

IBM Advances Web-based Quantum Programming

September 5, 2017

IBM Research is pairing its Jupyter-based Data Science Experience notebook environment with its cloud-based quantum computer, IBM Q, in hopes of encouraging a new class of entrepreneurial user to solve intractable problems that even exceed the capabilities of the best AI systems. Read more…

By Alex Woodie

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

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