The Greening of HPC — A Conversation with Professor Wu Feng

By Caroline Connor, for HPCwire

November 18, 2010

Ever notice that everyone’s gone green these days? The increased awareness in the HPC community of the need to maximize energy efficiency in compute-intensive environments has never been greater. With The Green500 results coming out this week, my thoughts turned towards learning more about the man largely credited with the movement towards environmentally sustainable supercomputing, Professor Wu Feng from Virginia Tech.

HPCwire: Wu, you’re well known for your work establishing the need for green computing, starting with the “Green Destiny” system back in 2001 and more recently, establishing The Green500. What are the most significant changes you’ve observed in the direction of energy-efficient computing and its influence on supercomputer design?

Wu Feng: The single biggest change is simply the awareness that power and energy consumption is a problem in supercomputing. It’s like the four stages of recovery. The first step is recognizing you have a problem, then working to overcome it. It’s that simple.

HPCwire: The naming of “Green Destiny” seems self-explanatory. Now you’ve got a system called “HokieSpeed.” Where did you ever get a name like that for a supercomputer?

Wu: Unlike Green Destiny, where there were multitudes of meanings behind it, the name HokieSpeed is fairly transparent. I had to come up with a name quickly, kind of like when you talked to Thomas Sterling about his naming of Beowulf. For our project, we mainly have Virginia Tech “Hokie” investigators, who seek to accelerate their computational simulations to execute at high ‘speed’, so I just pushed two words together.

HPCwire: Everyone is talking about the Tianhe-1A supercomputer announcement. From what we know, does it look like it will rate well on The Green500?

Wu: We could see this coming around 18 months ago. China has made a strategic investment in HPC, and they seem to be putting their eggs into the GPU basket. I can’t comment right now on how the supercomputer rates on The Green500, but I will say that I would be surprised if it did not do well. From an energy efficiency perspective, we have discovered that GPU-based systems tend to be very energy efficient.

HPCwire: So, what are your thoughts on cloud computing with respect to energy efficiency?

Wu: To a large extent the jury is still out on this. It’s like “outsourcing” your IT support. Outsourcing has some benefits and some drawbacks.

With respect to energy efficiency, relative to an institution that is leveraging cloud computing, the advantage is they don’t have to worry about building the most energy-efficient machine room. That’s something that institutions are not necessarily experts at anyway, so why not just use a cloud?

I think of it as similar to being part of a timeshare. So, from the standpoint of energy use, timesharing on a cloud resource can be much more cost and energy efficient. Instead of owning private systems that are using only five percent of their capability, you can aggregate twenty users onto a single cloud resource that each uses five percent on a single resource instead of twenty. That ends up being more energy efficient from an aggregation standpoint. In fact, you’re increasing the efficiency of the whole ecosystem.

From a scientific computing standpoint, depending on how one defines scientific computing, it may not be as energy efficient for some users due to the potential necessity of first migrating large data sets up to the cloud. When work is completed it may then need to be brought down from the cloud for post-analysis, and moving data is very energy intensive. So while there isn’t a black-and-white solution to the problem, it’s the right solution for the right task at the right time.

HPCwire: Speaking of cloud, some of these huge Fortune 500s build their big computing sites near hydroelectric dams and wind farms. Do you study whether the energy used for supercomputing is from renewable sources, or perhaps non-carbon-emitting sources like nuclear? Do you envision a “LowCarbon500” as well as a “Green500” list?

Wu: I personally don’t do any research in the area of renewable resources, fuels or energy sources or what have you. I may be somewhat of a “Renaissance man” but not that much of one! (Laughing) I am already doing way too many things as it is!

I would hope there could be something like that, though I don’t know that The Green500 would ultimately be the resting place for it. I hope that what The Green500 does is raise awareness of the need for energy efficiency in the area of high-end computing. We are starting to do exploratory lists, like The Little Green500, and there have been discussions on creating additional exploratory lists that deal with other aspects of computation. For example, someone has suggested we do a cloud-based Green500 also. I think these are all wonderful ideas; but it’s more about trying to find the grassroots support and the mechanisms to move these projects forward.

HPCwire: So, how do you come up with your very best ideas?

Wu: A lot of my research is on building efficient systems, whether it’s efficiency with respect to performance, energy, cost or personnel. It permeates whatever I do. Since I am not quite as organized as I would like to be, I rely on using a variety of tricks or mechanisms to efficiently remember the ideas that are oftentimes the foundation for my research. Here’s an example:

During my time at Los Alamos National Laboratory, I used to road bike with a group of cyclists at lunchtime around a 25-mile loop. I discovered that cycling helped to free my inner consciousness and many of my deepest thoughts would simply “percolate to the top.” It was during these rides that I oftentimes had my best research ideas. My efficiency trick was to attach a tag to each idea and associate them with an acronym so I could remember them when I got back. Unfortunately my “physiological cache” was limited to only about eight ideas per ride. So, if I exceeded the eight (and remember, this is in the days before smart phones), I would often call my landline from my cell phone, while riding, and leave myself an “ideas message.”

HPCwire: Can you share where you grew up and some of your family background?

Wu: I had a rich and somewhat nomadic existence. I was born in Michigan and lived in maybe five to six places as a kid, 12 to 14 places in total. With all the moving that I did, everyone would say, “Oh you must be a military brat,” but that wasn’t exactly the case. In actuality, my dad was a professor of electrical and computer engineering. When he got the “right” overture from an institution, we would move and move frequently.

HPCwire: How do you believe that experience influenced the man you are today?

Wu: (Laughs) Ah, all of these Zen questions! Adaptability is certainly a very key element. When you’re exposed to as many different environments, cultures, ways of life, and points of view as I have, it enables you to understand different perspectives that are not necessarily in line with your own. It made me appreciate and respect different viewpoints, even if I did not agree with them. I learned to understand where people might be coming from, not to take anything too personally, and avoid making decisions that might be driven emotionally rather than logically. (Laughs) I am starting to feel like Spock on Star Trek now or something!

HPCwire: I discovered recently that you have a B.S. Honors degree in Music as an undergrad. Are you still a musician?

Wu: Yes. I was classically trained on the piano and picked up other instruments at school, the clarinet and the trumpet in particular. I think those were the sidelights that my parents encouraged, to keep me busy and out of trouble! (Laughing) My piano teacher was kind of bummed when I did not pursue music as my core major…though it did become a secondary major, an honors major. While I was good enough to place in national-level piano competitions as a teen, I felt that I wasn’t ever going to be good enough to make it on the international stage, which as a classical pianist, one would have to do to be successful. In retrospect, if I had been more disciplined I probably could have gone much farther. Hindsight is 20/20, but of course, I don’t have a crystal ball so I don’t really know what would have happened if I had chosen that path.

You know, it would be interesting to see how many of your column subjects are musically inclined, like John Gustafson and Michael Warren, for instance. I’ve met many such highly successful researchers who also have a musical background. Having such musical background exercises different parts of your brain and creates a holistic being. For example, in a study from the 1990s, researchers found that musical training and exposure strongly correlated to a substantial increase in size of the corpus callosum, the fibers that join the left and right hemispheres of the brain together. This in turn contributed to a larger amount of information relaying across different parts of the brain and pointed to music’s ability to aid in memory function. Anyway, enough of the geek talk…in short, I suspect you will find that those you view as being technically brilliant also possess a musical or otherwise creative background.

HPCwire: That’s an interesting observation. Wu, you mentioned earlier in this interview that you are “somewhat of a Renaissance man.” How do you think this came about?

Wu: It was around the time of Green Destiny and the huge amount of public exposure and interest the project generated, both inside and outside the HPC community. It created new collaborations and interdisciplinary research opportunities for me that expanded beyond my work in computer networking and influenced my exploring new areas of research. Someone said, “Oh, you’re a Renaissance man because you’re doing networking, green computing, now you’re doing bioinformatics.” And I said, “Yeah, that’s kind of the polite term for it.” (Laughing) From another perspective, one could say that I have a hard time focusing!

HPCwire: While researching for this interview, I came across your philanthropic project, MyVICE@VT, and your efforts to introduce computer science to rural and disadvantaged children at the Blacksburg New School. What was the catalyst that prompted you to take on yet another project when your plate is already pretty crowded?

Wu: I live in a neighborhood that has a lot of middle-schoolers, and being in a small community, you tend to get to know your neighbors both professionally and personally. I was seeing a trend with girls in particular that they were choosing not to go into what we call the STEM areas of education: Science, Technology, Engineering and Mathematics. We found that they were choosing not to go into these areas, not because they couldn’t do it, but because they perceived it as “not being cool.” What I tried to do with this project was to show them that it could be cool; you just have to package it in the right way. For example, at one rural school, the kids have an activity called Author’s Tea, where they write short stories, illustrate them, and bind them into books, which are then shared at an annual tea. I approached the kids with the idea that they could do their own movie adaptations of their short stories, like a Harry Potter movie. Before long, the kids were working with a system and programming with pictures without even realizing it. I wanted to show them that they could use these skills in whatever career path they chose to pursue without the fear of “not being cool.”

HPCwire: That brings me to ask, of all the diverse areas to which you have contributed your energy and talents, which do you find the most rewarding?

Wu: Succinctly speaking, the work I find most rewarding is that which crosses disciplinary boundaries. The work I’ve been doing in the bioinformatics area and work that builds bridges between computer science and biological/biomedical areas have been the most rewarding personally. I just wish I could spend more time on it. More broadly, the “motherhood and apple pie” answer is that what I find most rewarding is how what I do will ultimately benefit and contribute to society down the line. If I can influence change and help to make a difference that is more than rewarding enough for me.

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!

Musk’s Latest Startup Eyes Brain-Computer Links

April 21, 2017

Elon Musk, the auto and space entrepreneur and severe critic of artificial intelligence, is forming a new venture that reportedly will seek to develop an interface between the human brain and computers. Read more…

By George Leopold

MIT Mathematician Spins Up 220,000-Core Google Compute Cluster

April 21, 2017

On Thursday, Google announced that MIT math professor and computational number theorist Andrew V. Sutherland had set a record for the largest Google Compute Engine (GCE) job. Sutherland ran the massive mathematics workload on 220,000 GCE cores using preemptible virtual machine instances. Read more…

By Tiffany Trader

Nvidia P100 Shows 1.3-2.3x Speedup Over K80 GPU on Financial Apps

April 20, 2017

When it comes to the true performance of the latest silicon, every end user knows that the best processor is the one that works best for their application. Read more…

By Tiffany Trader

Quantum Adds Global Smarts to StorNext File System

April 20, 2017

Companies that use Quantum’s StorNext platform to store massive amounts of data this week got a glimpse of new storage capabilities that should make it easier to access their data horde from anywhere in the world. Read more…

By Alex Woodie

HPE Extreme Performance Solutions

HPC-Driven Weather Simulations Improving Forecasting Capabilities

In September of 1938, a massive hurricane traversed the Atlantic Ocean and made landfall in New England. Due to inadequate and incorrect forecasting, the storm struck farther north and with greater intensity than had been predicted, leaving residents and authorities with virtually no warning or time to properly prepare. Read more…

Scaling an HPC Career in Nepal Can Be a Steep Climb

April 20, 2017

Umesh Upadhyaya works as an IT Associate at the International Centre for Integrated Mountain Development (ICIMOD) in Nepal, which supports the country’s one and only HPC facility. He is directly involved in an initiative that focuses on climate change and atmosphere modeling Read more…

By Nages Sieslack

Hyperion (IDC) Paints a Bullish Picture of HPC Future

April 20, 2017

Hyperion Research – formerly IDC’s HPC group – yesterday painted a fascinating and complicated portrait of the HPC community’s health and prospects at the HPC User Forum held in Albuquerque, NM. HPC sales are up and growing ($22 billion, all HPC segments, 2016). Read more…

By John Russell

Intel Open Sources All Lustre Work, Brent Gorda Exits

April 19, 2017

In a letter to the Lustre community posted on the Intel website, Vice President of Intel's Data Center Group Trish Damkroger writes that effective immediately the company will be contributing all Lustre development to the open source community. Damkroger also announced that Brent Gorda, General Manager, High Performance Data Division at Intel is leaving the company. Read more…

By Tiffany Trader

Facebook Open Sources Caffe2; Nvidia, Intel Rush to Optimize

April 18, 2017

From its F8 developer conference in San Jose, Calif., today, Facebook announced Caffe2, a new open-source, cross-platform framework for deep learning. Caffe2 is the successor to Caffe, the deep learning framework developed by Berkeley AI Research and community contributors. Read more…

By Tiffany Trader

Hyperion (IDC) Paints a Bullish Picture of HPC Future

April 20, 2017

Hyperion Research – formerly IDC’s HPC group – yesterday painted a fascinating and complicated portrait of the HPC community’s health and prospects at the HPC User Forum held in Albuquerque, NM. HPC sales are up and growing ($22 billion, all HPC segments, 2016). Read more…

By John Russell

Knights Landing Processor with Omni-Path Makes Cloud Debut

April 18, 2017

HPC cloud specialist Rescale is partnering with Intel and HPC resource provider R Systems to offer first-ever cloud access to Xeon Phi "Knights Landing" processors. The infrastructure is based on the 68-core Intel Knights Landing processor with integrated Omni-Path fabric (the 7250F Xeon Phi). Read more…

By Tiffany Trader

CERN openlab Explores New CPU/FPGA Processing Solutions

April 14, 2017

Through a CERN openlab project known as the ‘High-Throughput Computing Collaboration,’ researchers are investigating the use of various Intel technologies in data filtering and data acquisition systems. Read more…

By Linda Barney

DOE Supercomputer Achieves Record 45-Qubit Quantum Simulation

April 13, 2017

In order to simulate larger and larger quantum systems and usher in an age of “quantum supremacy,” researchers are stretching the limits of today’s most advanced supercomputers. Read more…

By Tiffany Trader

Penguin Takes a Run at the Big Cloud Providers

April 12, 2017

HPC specialist Penguin Computing recently re-ran benchmarks from a study of its larger brethren and says the results show its ‘public cloud’ – Penguin on Demand (POD) – is among the leaders in cost and performance. 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

HPC and the Colocation Datacenter – a Bridge Too Far?

April 7, 2017

A more standardised HPC platform approach is making the running of HPC projects within increasing financial reach. Read more…

By Clive Longbottom, Quocirca

Google Pulls Back the Covers on Its First Machine Learning Chip

April 6, 2017

This week Google released a report detailing the design and performance characteristics of the Tensor Processing Unit (TPU), its custom ASIC for the inference phase of neural networks (NN). Read more…

By Tiffany Trader

Google Pulls Back the Covers on Its First Machine Learning Chip

April 6, 2017

This week Google released a report detailing the design and performance characteristics of the Tensor Processing Unit (TPU), its custom ASIC for the inference phase of neural networks (NN). Read more…

By Tiffany Trader

Quantum Bits: D-Wave and VW; Google Quantum Lab; IBM Expands Access

March 21, 2017

For a technology that’s usually characterized as far off and in a distant galaxy, quantum computing has been steadily picking up steam. Read more…

By John Russell

Trump Budget Targets NIH, DOE, and EPA; No Mention of NSF

March 16, 2017

President Trump’s proposed U.S. fiscal 2018 budget issued today sharply cuts science spending while bolstering military spending as he promised during the campaign. Read more…

By John Russell

HPC Compiler Company PathScale Seeks Life Raft

March 23, 2017

HPCwire has learned that HPC compiler company PathScale has fallen on difficult times and is asking the community for help or actively seeking a buyer for its assets. Read more…

By Tiffany Trader

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

For IBM/OpenPOWER: Success in 2017 = (Volume) Sales

January 11, 2017

To a large degree IBM and the OpenPOWER Foundation have done what they said they would – assembling a substantial and growing ecosystem and bringing Power-based products to market, all in about three years. Read more…

By John Russell

CPU-based Visualization Positions for Exascale Supercomputing

March 16, 2017

In this contributed perspective piece, Intel’s Jim Jeffers makes the case that CPU-based visualization is now widely adopted and as such is no longer a contrarian view, but is rather an exascale requirement. Read more…

By Jim Jeffers, Principal Engineer and Engineering Leader, Intel

TSUBAME3.0 Points to Future HPE Pascal-NVLink-OPA Server

February 17, 2017

Since our initial coverage of the TSUBAME3.0 supercomputer yesterday, more details have come to light on this innovative project. Of particular interest is a new board design for NVLink-equipped Pascal P100 GPUs that will create another entrant to the space currently occupied by Nvidia's DGX-1 system, IBM's "Minsky" platform and the Supermicro SuperServer (1028GQ-TXR). Read more…

By Tiffany Trader

Leading Solution Providers

Tokyo Tech’s TSUBAME3.0 Will Be First HPE-SGI Super

February 16, 2017

In a press event Friday afternoon local time in Japan, Tokyo Institute of Technology (Tokyo Tech) announced its plans for the TSUBAME3.0 supercomputer, which will be Japan’s “fastest AI supercomputer,” Read more…

By Tiffany Trader

IBM Wants to be “Red Hat” of Deep Learning

January 26, 2017

IBM today announced the addition of TensorFlow and Chainer deep learning frameworks to its PowerAI suite of deep learning tools, which already includes popular offerings such as Caffe, Theano, and Torch. Read more…

By John Russell

Is Liquid Cooling Ready to Go Mainstream?

February 13, 2017

Lost in the frenzy of SC16 was a substantial rise in the number of vendors showing server oriented liquid cooling technologies. Three decades ago liquid cooling was pretty much the exclusive realm of the Cray-2 and IBM mainframe class products. That’s changing. We are now seeing an emergence of x86 class server products with exotic plumbing technology ranging from Direct-to-Chip to servers and storage completely immersed in a dielectric fluid. Read more…

By Steve Campbell

BioTeam’s Berman Charts 2017 HPC Trends in Life Sciences

January 4, 2017

Twenty years ago high performance computing was nearly absent from life sciences. Today it’s used throughout life sciences and biomedical research. Genomics and the data deluge from modern lab instruments are the main drivers, but so is the longer-term desire to perform predictive simulation in support of Precision Medicine (PM). There’s even a specialized life sciences supercomputer, ‘Anton’ from D.E. Shaw Research, and the Pittsburgh Supercomputing Center is standing up its second Anton 2 and actively soliciting project proposals. There’s a lot going on. Read more…

By John Russell

HPC Startup Advances Auto-Parallelization’s Promise

January 23, 2017

The shift from single core to multicore hardware has made finding parallelism in codes more important than ever, but that hasn’t made the task of parallel programming any easier. Read more…

By Tiffany Trader

HPC Technique Propels Deep Learning at Scale

February 21, 2017

Researchers from Baidu’s Silicon Valley AI Lab (SVAIL) have adapted a well-known HPC communication technique to boost the speed and scale of their neural network training and now they are sharing their implementation with the larger deep learning community. Read more…

By Tiffany Trader

US Supercomputing Leaders Tackle the China Question

March 15, 2017

Joint DOE-NSA report responds to the increased global pressures impacting the competitiveness of U.S. supercomputing. Read more…

By Tiffany Trader

IDG to Be Bought by Chinese Investors; IDC to Spin Out HPC Group

January 19, 2017

US-based publishing and investment firm International Data Group, Inc. (IDG) will be acquired by a pair of Chinese investors, China Oceanwide Holdings Group Co., Ltd. Read more…

By Tiffany Trader

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