Back to Table of contents

Primeur weekly 2016-08-08

Focus

OpenSoC Fabric to create Open Source Network-on-Chip systems for demonstration purposes ...

ExaNoDe project is looking for chiplet solutions stacked on an active silicon interposer ...

Quantum computing

New quantum computer module sets stage for general-purpose quantum computers ...

Diamond-based light sources will lay a foundation for quantum communications of the future ...

Focus on Europe

IBM scientists imitate the functionality of neurons with a phase-change device ...

European Commission issues booklet on e-Infrastructures as the foundation of the European Open Science Cloud ...

Middleware

Bright Computing releases Version 7.3 of Bright Cluster Manager and Bright OpenStack ...

Hardware

HiPEAC community delivers video processing with up to eight times faster edge detection and 50 times faster motion detection ...

AMD open sources professional GPU-optimized photorealistic renderer ...

Curtiss-Wright collaborates with Dolphin Interconnect Solutions to dramatically increase HPEC system fabric speed ...

New UK consortium to explore use of magnetic skyrmions in data storage ...

Smallest photodetector worldwide for optical data transmission ...

Cray reports second quarter 2016 financial results and updates 2016 outlook ...

Panasas introduces ActiveStor 20 ...

World's Highest Density Deep Learning Supercomputer in a Box by Joint Creators Orange and CoCoLink Korea ...

Applications

Rail researchers select liquid cooled computing for Big Data risk analysis ...

SC16 selects industry veteran Katharine Frase as keynote speaker ...

University of Kentucky biology graduate student wins prestigious Blue Waters Fellowship ...

Partnership between University of Maryland and U.S. Army Research Laboratory harnesses the power of defense supercomputing to create opportunities for scientific discovery ...

Personalized virtual brains: Big data - big theory ...

Analysis of metastatic prostate cancers suggests treatment options ...

Penn researchers improve computer modeling for designing drug-delivery nanocarriers ...

The Cloud

5.3 million euro HNSciCloud tender for Hybrid Cloud Platform released ...

IBM captures leadership position in hybrid Cloud environment adoption, according to research firm ...

IBM named leader in private Cloud adoption by market research firm ...

World's Highest Density Deep Learning Supercomputer in a Box by Joint Creators Orange and CoCoLink Korea


20 modified NVIDIA Tesla K40 GPUs in 4U Chassis
2 Aug 2016 Silicon Valley, Paris, Seoul - Orange Silicon Valley, a Silicon Valley Business Innovation Center for global telecom operator Orange, and CocoLink Corp, a spin-off of Seoul National University, have built a functional prototype of one of the world's highest density Deep Learning Supercomputer in a box using CoCoLink's KLIMAX 210, a server designed for Exascale. They were able to load 20 Functional GPUs in a single 4 Rack Unit Sized server. With 20 NVIDIA K40 GPUs set at overclock (GPU boost 2) mode, the system is capable of delivering a screaming 100 TeraFLOPS in a single box with 57,600 cores. With specially engineered high performance heat sinks, this pushes the limit of computational density in any server without resorting to liquid cooling.

The A.I. researchers of Orange in France were also able to use Caffe, the popular deep learning framework to test the system for scalability. They were able to scale the training job to 16 GPUs. This endeavour is continuing with various partners to adapt the framework to its full potential to exploit all the 20 GPUs in the system. The next step would be to scale to a cluster.

The team - Orange Silicon Valley and CoCoLink Korea - has also upgraded the system with the latest commercially available NVIDIA GPUs - GeForce GTX 1080 based on Pascal architecture. They were the first to validate a GTX 1080 for Deep Learning and identified that these consumer grade GPUs capable of achieving the same task of running GoogleNet on Caffe with 3.5 times faster speed in reaching a certain level of accuracy of image recognition during training than the NVIDIA Tesla K40 enterprise grade GPUs, which were unveiled in 2014.

This gives us a sense of how efficiency in deep learning systems is increasing over years in a beyond linear fashion.

Having identified this disruptive price/performance value proposition, the team loaded the KLIMAX system with 10 GTX 1080 GPUs.

They were able to fire up all Pascal GPUs on overclock (Boost) mode with a theoretical aggregate computation capability of 106 TeraFLOPS (Single Precision). So far the A.I. research team of Orange France were able to scale Caffe (NVIDIA fork) to 8 GPUs with beta release of CUDA 8.0 and CuDNN 5 and CuDNN4. The eventual objective is to scale the server capability with 20 Pascal GPUs with a computational horsepower in the excess of 200+ TeraFLOPS - a feat that has never been accomplished before with consumer grade graphics card.

A particular training job on ImageNet data which used to take Orange researchers one and a half days (36 hours) with a single NVIDIA K40 can now be accomplished in 3.5 hours using 8 NVIDIA GTX 1080 cards. This is more than 10x increase in speed in regard to training performance.

As the world transitions towards Exascale and A.I. turns out to be a global race, this particular experiment is a partnership between researchers of 3 countries - USA, France and South Korea - working together to accelerate Artificial Intelligence by building a supercomputer in a single server by pushing the limits of thermodynamics, geometry and price vs. performance efficiency.

This currently remains as a research project for Orange and there are no plans at present to implement or develop this as a commercial offering. Detailed benchmark data based on this research will be published by the team in the near future as they make more progress towards optimization of the Deep Learning framework in collaboration with the open source community, academia and industry partners.

Source: Orange Silicon Valley

Back to Table of contents

Primeur weekly 2016-08-08

Focus

OpenSoC Fabric to create Open Source Network-on-Chip systems for demonstration purposes ...

ExaNoDe project is looking for chiplet solutions stacked on an active silicon interposer ...

Quantum computing

New quantum computer module sets stage for general-purpose quantum computers ...

Diamond-based light sources will lay a foundation for quantum communications of the future ...

Focus on Europe

IBM scientists imitate the functionality of neurons with a phase-change device ...

European Commission issues booklet on e-Infrastructures as the foundation of the European Open Science Cloud ...

Middleware

Bright Computing releases Version 7.3 of Bright Cluster Manager and Bright OpenStack ...

Hardware

HiPEAC community delivers video processing with up to eight times faster edge detection and 50 times faster motion detection ...

AMD open sources professional GPU-optimized photorealistic renderer ...

Curtiss-Wright collaborates with Dolphin Interconnect Solutions to dramatically increase HPEC system fabric speed ...

New UK consortium to explore use of magnetic skyrmions in data storage ...

Smallest photodetector worldwide for optical data transmission ...

Cray reports second quarter 2016 financial results and updates 2016 outlook ...

Panasas introduces ActiveStor 20 ...

World's Highest Density Deep Learning Supercomputer in a Box by Joint Creators Orange and CoCoLink Korea ...

Applications

Rail researchers select liquid cooled computing for Big Data risk analysis ...

SC16 selects industry veteran Katharine Frase as keynote speaker ...

University of Kentucky biology graduate student wins prestigious Blue Waters Fellowship ...

Partnership between University of Maryland and U.S. Army Research Laboratory harnesses the power of defense supercomputing to create opportunities for scientific discovery ...

Personalized virtual brains: Big data - big theory ...

Analysis of metastatic prostate cancers suggests treatment options ...

Penn researchers improve computer modeling for designing drug-delivery nanocarriers ...

The Cloud

5.3 million euro HNSciCloud tender for Hybrid Cloud Platform released ...

IBM captures leadership position in hybrid Cloud environment adoption, according to research firm ...

IBM named leader in private Cloud adoption by market research firm ...