RFHPC109: New Chip Architectures — Picking the Winners

In this podcast, the Radio Free HPC team welcomes Shahin Khan from OrionX to a discussion on chip architectures for HPC.

More and more new alternative architectures were in evidence at ISC in Germany this year, but what does it take for a chip architecture to be a winner? Looking back, chips like DEC Alpha had many advantages over the competition, but it did not survive.

Henry contends that a viable chip architecture needs a memory controller that has the muster to keep up with new memory hierarchies. Rich thinks it isn’t about features so much and that survival is all about the chip’s ecosystem.

Download the MP3 * Subscribe on iTunes * RSS Feed

RFHPC108: First Look at the Sunway TaihuLight 93 Petaflop Supercomputer

In this podcast, Shahin Khan from OrionX joins the Radio Free HPC team for a look at the new TOP500 list of the world’s fastest supercomputers.

As announced this morning at ISC 2016, the fastest supercomputer on the TOP500 is new Sunway TaihuLight System in Wuxi, China. Developed by the National Research Center of Parallel Computer Engineering & Technology (NRCPC), TaihuLight scored a whopping 93 Petaflops on the LINPACK benchmark. To put that in perspective, that is nearly three times faster than the previous #1 system, the Tianhe-2 supercomputer, which has moved to #2 after ruling the roost for some three years or so TaihuLight is also five times faster than Titan, the 17 Petaflop machine at ORNL, which is still the fastest machine in the USA.

Sunway in Wuxi, China

The Sunway TaihuLight Suercomputer in Wuxi, China is the world’s fastest supercomputer.

Here is the rundown:

  • Linpack: 93 Petaflops (Rmax)
  • Peak performance: 125.4 Petflops (Rpeak)
  • Processor: Sunway SW26010 1.4 GHz processor
  • Cores per socket: 260
  • Instruction Set: RISC instruction set developed by Sunway
  • Interconnect: their TOP500 submission says “Sunway design” but Mellanox supplied the Host Channel Adapter (HCA) and switch chips. Sunway may not call it InfiniBand, but that is exactly what it is. China has political reasons for characterizing the overall system domestic technology.
  • Cabinets: 40 Water-cooled cabinets, each with 3 Petaflops of peak performance
  • Power consumption: 15.27 Megawatts
  • Mflops/watt: 6051

Download the MP3 * Subscribe on iTunes * RSS Feed

Sign up for our insideHPC Newsletter

RFHPC107: HPC News Roundup for Friday the 13th

In this podcast, the Radio Free HPC team looks at the news highlights for the week leading up to Friday the 13th of May, 2016:

Download the MP3 * Subscribe on iTunes * RSS Feed

RFHPC105: The GTC’16 Run Down

In this podcast, the Radio Free HPC team recaps the GPU Technology Conference.

Since Rich is traveling around in some desert somewhere, Dan and Henry go it alone and discuss what happened at last week’s GTC’16 conference. They talk about the new Pascal (P1000) GPU, NVIDIA’s new server, and what happened at the concurrent OpenPOWER conference. A good time is had by all….”

Download the MP3 * Subscribe on iTunes * RSS Feed

RFHPC104: A Preview of GTC 2016

In this podcast, the Radio Free HPC team congratulates Dan Olds on becoming a Partner at OrionX. Then we go on to preview the GPU Technology Conference coming up April 4-7 in Silicon Valley.

GTC is the largest and most important event of the year for GPU developers. Join us this year as we showcase the most vital work in the computing industry today – Artificial Intelligence and Deep Learning, Virtual Reality and Self Driving Cars. GTC attracts developers, researchers, and technologists from some of the top companies, universities, research firms and government agencies from around the world.

Download the MP3 * Subscribe on iTunes * RSS Feed

RFHPC103: How Blockchain will Revolutionize Banking

In this podcast, the Radio Free HPC team looks at blockchain technology with Chris Skinner, author of ValueWeb – How FinTech firms are using mobile and blockchain technologies to create the Internet of Value.

The Internet of Things is all about machines trading with machines. Your fridge orders groceries; your car, fuel; your television, entertainment; and so on. However, machines cannot trade with machines if it’s expensive and slow. Would you really want your TV to order the next season of Game of Thrones, if the payment took ten days and cost $25 or more to process? Unfortunately with the four-pillar card scheme model and the SWIFT counterparty bank system, that is the problem we face today. As a result, we need an Internet of Value to work with the Internet of Things. The Internet of Value, or ValueWeb for short, allows machines to trade with machines and people with people, anywhere on this planet in real-time and for free. Using a combination of technologies from mobile devices and the bitcoin blockchain, fintech firms are building the ValueWeb. The question then is what this means for financial institutions, governments and citizens? This book provides the answers.

Download the MP3 * Subscribe on iTunes * RSS Feed

RFHPC101: The Case of the Encrypted iPhone

In this podcast, the Radio Free HPC team looks at Apple’s fight against a court order to decrypt an iPhone used by one of the San Bernardino shooters.

The government contends that a 1789 law called the All Writs Act compels Apple to honor a search warrant and assist the authorities in getting access to unlock and decrypt the iPhone 5C used by Syed Rizwan Farook in the San Bernardino shooting in December. The government contends that phone might contain crucial evidence in the case.

Apple CEO Tim Cook on Tuesday evening said the US government’s legal position on encryption backdoors was setting “a dangerous precedent.” If a back door is created to crack this particular phone, bad guys will be able to exploit it.

The Radio Free HPC is split as to what should happen next, but it seems likely that some kind of compromise will result. Is the government entitled to a back door to all devices? It would seem that no one wants such an important policy to be decided from a single case in California.

Download the MP3 * Subscribe on iTunes * RSS Feed

RFHPC100: The Top HPC Tech Stories from 2015

bubbleIn this podcast, the Radio Free HPC team looks at the Top Technology Stories for High Performance Computing in 2015.

  • Henry thinks new NVM Non-Volatile Memory (3D Xpoint) technologies will have the most dramatic impact on HPC architectures going forward. Rich says that the analytics for 3D XPoint indicate that many of his readers at insideHPC are eager to learn more.
  • Dan believes that the Coral Announcements made in the last 15 months or so will result in new levels of architectural diversity in the TOP500. In what he calls the “Rebel Alliance” the co-design approach from IBM, Nvidia, and Mellanox will be deployed at two of the three Coral systems in the 2017 timeframe. On the other side of the coin, the Aurora system at Argonne will use the Scalable System Framework architecture from Intel.
  • Rich sees tremendous potential in NVMe technologies, having seen his first demonstration at the Scalable Informatics booth at SC15. The NVM Express specification defines an optimized register interface, command set and feature set for PCI Express (PCIe)-based Solid-State Drives (SSDs). The goal of NVM Express is to unlock the potential of PCIe SSDs now and in the future, and standardize the PCIe SSD interface.

Download the MP3 * Subscribe on iTunes * RSS Feed