RFHPC152: AI, Ethics, and Self-Driving Cars

In this podcast, the Radio Free HPC team learns about Henry’s first exploit as an Ethical Superhero.

“After witnessing a hit-and-run fender bender, Henry confronted the culprit and ensured that the miscreant left a note on the victim’s windshield. And while we applaud Henry for his heroism, we are also very grateful that he was not shot in the process. This tale leads us into a discussion of AI ethics and how we won’t have this problem in the coming era of self-driving cars.”

After that, we do our Catch of the Week:

Download the MP3 * Subscribe on iTunes * RSS Feed

RFHPC151: Cray Urika-GX Brings Graph Computing to Alan Turing Institute

In this podcast, the Radio Free HPC team looks at why the Alan Turing Institute is focusing on Graph Computing with their acquisition of a Cray Urika-GX supercomputer.

‘Hosted at the University of Edinburgh in the Edinburgh Parallel Computing Centre (EPCC), the Cray Urika-GX system will provide researchers at the Alan Turing Institute with a dedicated analytics hardware platform, enabling the development of advanced applications across a number of scientific fields including engineering and technology, defense and security, smart cities, financial services and life sciences.”

After that, we do our Catch of the Week:

Download the MP3 * Subscribe on iTunes * RSS Feed

RFHPC150: Why Drive Writes Per Day matter for SSDs

In this podcast, the Radio Free HPC team looks at why Drive Writes Per Day are such an important metric for acquiring the right kind of SSD for your particular workload.

Drive writes per day (DWPD) is an endurance rating that manufacturers of NAND flash storage provide their customers. … DWPD will vary, depending upon whether the storage is intended for consumer or enterprise use. Consumer use solid state drives (SSDs) have a fixed endurance rating and capacity.

After that, we do our Catch of the Week:

  • Shahin likes a new BBC documentary on the #1 Sunway TaihuLight supercomputer in China.

Download the MP3 * Subscribe on iTunes * RSS Feed

RFHPC149: A Rundown of ISC 2017 Student Cluster Competition Results

In this podcast, the Radio Free HPC team looks back at the recent ISC 2017 conference and summarizes results from Student Cluster Competition.

Eleven student teams were on the show floor this year, vying against each other for the top honors in the sixth annual ISC Student Cluster Competition. Tsinghua University from China emerged as the Overall Competition Winner, thus marking their third win in the contest. They had the honor of receiving their trophy from Wednesday keynote speaker, Professor Thomas Sterling.

The second place was captured by the South African team hosted by CHPC, and the third place went to Beihang University, also from China. The Fan Favorite Award went to Universitat Politècnica De Catalunya from Barcelona, who garnered over 2,100 ISC 2017 participant votes to win the title for the second year in a row. The High Linpack award went to competitors from the Friedrich-Alexander University Erlangen in Nuremberg.

The three-day competition was co-organized with the HPC Advisory Council. If you are interested in applying for the 2018 competition, please contact the organizers at scc@isc-events.com.

Brent Gorda with his red Motoguzzi and Rich Brueckner with his bike dubbed “The Mighty One.”

After that, we do our Catch of the Week:

  • Shahin likes our recent insideHPC post on IBM’s TrueNorth AI chip coming to ARL. IBM is collaborating with the U.S. Air Force Research Laboratory (AFRL) on a first-of-a-kind brain-inspired supercomputing system powered by a 64-chip array of the IBM TrueNorth Neurosynaptic System. The scalable platform IBM is building for AFRL will feature an end-to-end software ecosystem designed to enable deep neural-network learning and information discovery.
  • Dan reminisces on his youth where he bought an entire minivan full of fireworks for the 4th of July.
  • Rich tells the tale of his Lustre Motorcycle Tour through the Alps. The GoPro camera footage from the trip is amazing. He followed that trip up with three days at the PASC17 conference.

Download the MP3 * Subscribe on iTunes * RSS Feed

RFHPC147: A Look at the Latest TOP500

In this podcast, the Radio Free HPC team looks at the latest TOP500 list of the world’s fastest supercomputers. It’s Day 1 here at the ISC 2017 conference, and we’ll be keeping you posted on all the news as the show goes June 18-22 in Frankfurt, Germany.

 

After that, we do our Catch of the Week:

  • Student Cluster Competition Update: The student team from NUDT in China has Visa troubles, so they will not be able to participate this week in Frankfurt. That reduces the field to 11 international teams.
  • What’s up with the Aurora supercomputer that was supposed to come to Argonne next year? Rich has the scoop.

Download the MP3 * Subscribe on iTunes * RSS Feed

RFHPC145: Touring the 100 Megawatt SuperNAP Datacenter

In this podcast, Rich gives us the lowdown on his recent tour of the SuperNAP datacenter in Las Vegas. Run by Switch, the campus has over up to 2.4 million sqare feet of Tier IV Gold data center space with 315 Megawatts of datacenter capacity.

“Founded in 2000 and headquartered in Las Vegas, Nevada, Switch is built on the intelligent and sustainable growth of the Internet. Its Founder and CEO, Rob Roy, developed more than 260 patent and patent-pending claims covering data center designs that manifested into their world-renowned data centers and their technology solution ecosystems.”

After that, we do our Catch of the Week:

  • Shahin is impressed with ARM’s new Cortex A75 chips. “This is the first set of processing components designed specifically to tackle the challenges of onboard AI and machine learning.”
  • Dan notes that Google is possibly facing a $9 Billion fine from EU antitrust regulators for allegedly manipulating search results on its shopping service.
  • Dan also points us to a story on how the Bank of Canada is not sold on the concept of underpinning payment systems
    using Blockchain technology.

Download the MP3 * Subscribe on iTunes * RSS Feed

RFHPC143: A Look at Google’s TPU Tensor Processing Unit

In this podcast, the Radio Free HPC team looks at the announcements coming from Google IO conference. Of particular interest was their second-generation TensorFlow Processing Unit (TPU2).

After that, we do our Catch of the Week:

  • Shahin discusses some details about the new prototype of HPE’s The Machine“The prototype unveiled today contains 160 terabytes (TB) of memory, capable of simultaneously working with the data held in every book in the Library of Congress five times over—or approximately 160 million books. It has never been possible to hold and manipulate whole data sets of this size in a single-memory system, and this is just a glimpse of the immense potential of Memory-Driven Computing.”
  • Rich points us to the launch of the new Emerging Woman Leader in Technical Computing Award. Sponsored by SIGHPC, the award will be presented every two years, with the first presentation in November during SC17.
  • Dan is excited by the rebirth of the OS/2 operating system. The Arca OS 5.0 operating system lets you run OS/2 applications today on modern hardware.
  • Quantum Computing vendor D-Wave Systems announced a $50 Million round of new funding.

Download the MP3 * Subscribe on iTunes * RSS Feed

RFHPC141: Results from the ASC17 Student Cluster Competition

In this podcast, the Radio Free HPC team reviews the results from the ASC17 Student Cluster Competition finals in Wuxi, China. In the end, Tsinghua University won the overall competition, beating 20 teams from around the world.

“As the world’s largest supercomputing competition, ASC17 received applications from 230 universities around the world, 20 of which got through to the final round held this week at the National Supercomputing Center in Wuxi after the qualifying rounds. During the final round, the university student teams were required to independently design a supercomputing system under the precondition of a limited 3000W power consumption. They also had to operate and optimize standard international benchmark tests and a variety of cutting-edge scientific and engineering applications including AI-based transport prediction, genetic assembly, and material science. Moreover, they were required to complete high-resolution maritime simulation on the world’s fastest supercomputer, Sunway TaihuLight.

The grand champion, team Tsinghua University, completed deep parallel optimization of the high-resolution maritime data simulation mode MASNUM on TaihuLight, expanding the original program up to 10,000 cores and speeding up the program by 392 times. This helped the Tsinghua University team win the e Prize award. MASNUM was nominated in 2016 for the Gordon Bell Prize, the top international prize in the supercomputing applications field.

After that, we do our Catch of the Week:

  • Henry points us to the Google Docs security breach. They claim they have fixed the problem, but don’t open those shared docs!
  • Shahin likes a new story about AI-enhanced justice in the court systems where they look at setting bail and the risks associated with the defendant.
  • Dan was having trouble with slow internet and two-factor authentication, which sounds like a vicious circle.
  • Rich notes that Andrew Klein from Backblaze will present at MSST on what they’ve learned about hard drives over the years including failure rates by model, and the ability to predict drive failure before it happens.

Download the MP3 * Subscribe on iTunes * RSS Feed

RFHPC139: A Preview of the 2017 MSST Mass Storage Conference

Matthew O’Keefe is the Program Chair of the MSST Conference

In this podcast, the Radio Free HPC team discusses the upcoming MSST Mass Storage Conference with Program Chair Matthew O’Keefe from Oracle. The conference takes place May 15-19 in Santa Clara, California.

Since the conference was founded by the leading national laboratories, MSST has been a venue for massive-scale storage system designers and implementers, storage architects, researchers, and vendors to share best practices and discuss building and securing the world’s largest storage systems for high-performance computing, web-scale systems, and enterprises.

Download the MP3 * Subscribe on iTunes * RSS Feed

RFHPC138: A Look at Quantum Startup Rigetti Computing

In this podcast, the Radio Free HPC team looks at the week’s top stories:

Download the MP3 * Subscribe on iTunes * RSS Feed