Sign up for our newsletter and get the latest HPC news and analysis.
Send me information from insideHPC:


Altair to boost UNLV Supercomputing

Today UNLV announced new Memorandum of Understanding (MOU) between the university and Altair Engineering. “Per the agreement, Altair’s technology will enable Cherry Creek II users to simplify access and utilization of the supercomputer’s capabilities and capacity. When deployed, PBS Works, Altair’s high-performance computing management suite, will securely manage all Cherry Creek II compute workload.”

Rigetti Computing Releases Forest 1.3 Quantum Software Platform

Rigetti Computing has released a new version of Forest, their quantum software platform. Forest 1.3 offers upgraded developer tools, improved stability, and faster execution. “Starting today, researchers using Forest will be upgraded to version 1.3, which provides better tools for optimizing and debugging quantum programs. The upgrade also provides greater stability in our quantum processor (QPU), which will let researchers run more powerful quantum programs. Forest is the easiest and most powerful way to build quantum applications today. We believe the combination of one of the most powerful gate-model quantum computers, cutting-edge classical hardware, and our unique hybrid classical/quantum architecture creates the clearest and shortest path toward the demonstration of unequivocal quantum advantage.”

D-Wave Completes Prototype of Next-Gen Quantum Processor

Today D-Wave Systems announced that the company has completed fabrication and testing of a working prototype next-generation processor, and the installation of a D-Wave 2000Q system for a customer. The prototype processor uses an advanced new architecture that will be the basis for D-Wave’s next-generation quantum processor. The D-Wave 2000Q system, the fourth generation of commercial products delivered by D-Wave, was installed at the Quantum Artificial Intelligence Lab run by Google, NASA, and Universities Space Research Association.

Highest Peformance and Scalability for HPC and AI

Scot Schultz from Mellanox gave this talk at the Stanford HPC Conference. “Today, many agree that the next wave of disruptive technology blurring the lines between the digital, physical and even the biological, will be the fourth industrial revolution of AI. The fusion of state-of-the-art computational capabilities, extensive automation and extreme connectivity is already affecting nearly every aspect of society, driving global economics and extending into every aspect of our daily life.”

Warm Water-Cooling enables a fanless design for new Lenovo ThinkSystem SD650

Today Lenovo unveiled the new ThinkSystem SD650 server Direct Water Cooling for energy-efficient, high-density computing. Already deployed at the Leibniz Supercomputing Centre in Germany, the ThinkSystem SD650 will save customers up to 40% on energy costs while delivering a 10-15% performance improvement over air-cooled systems. “The system utilizes warm water instead of air to cool the components, including the CPUs and memory. Water conducts heat more efficiently, allowing customers to run their processors in “turbo” mode continuously, resulting in a performance improvement. The SD650 HPC servers have no system fans, operate at lower temperatures when compared to standard air-cooled systems and have negligible datacenter chilled water requirements. The result – lower datacenter power consumption of 30-40% compared to traditional cooling methods.”

Lenovo ThinkSystem Servers Power 1.3 Petaflop Supercomputer at University of Southampton

OCF in the UK has deployed a new supercomputer at the University of Southampton. Named Iridis 5, the 1.3 Petaflop system will support research demanding traditional HPC as well as projects requiring large scale deep storage, big data analytics, web platforms for bioinformatics, and AI services. “We’ve had early access to Iridis 5 and it’s substantially bigger and faster than its previous iteration – it’s well ahead of any other in use at any University across the UK for the types of calculations we’re doing.”

Designing HPC, Deep Learning, and Cloud Middleware for Exascale Systems

DK Panda from Ohio State University gave this talk at the Stanford HPC Conference. “This talk will focus on challenges in designing HPC, Deep Learning, and HPC Cloud middleware for Exascale systems with millions of processors and accelerators. For the HPC domain, we will discuss the challenges in designing runtime environments for MPI+X (PGAS-OpenSHMEM/UPC/CAF/UPC++, OpenMP and Cuda) programming models by taking into account support for multi-core systems (KNL and OpenPower), high networks, GPGPUs (including GPUDirect RDMA) and energy awareness.”

Samsung Unveils 30.72TB Enterprise SSD

Today Samsung announced that it has begun mass producing the industry’s largest capacity SAS solid state drive – the PM1643 – for use in next-generation enterprise storage systems. Leveraging Samsung’s latest V-NAND technology with 64-layer, 3-bit 512-gigabit chips, the 30.72 terabyte drive delivers twice the capacity and performance of the previous 15.36TB high-capacity lineup introduced in March 2016. “With our launch of the 30.72TB SSD, we are once again shattering the enterprise storage capacity barrier, and in the process, opening up new horizons for ultra-high capacity storage systems worldwide,” said Jaesoo Han, executive vice president, Memory Sales & Marketing Team at Samsung Electronics. “Samsung will continue to move aggressively in meeting the shifting demand toward SSDs over 10TB and at the same time, accelerating adoption of our trail-blazing storage solutions in a new age of enterprise systems.”

WekaIO: Making Machine Learning Compute-Bound Again

We are going to present WekaIO, the lowest latency, highest throughput file system solution that scales to 100s of PB in a single namespace supporting the most challenging deep learning projects that run today. We will present real life benchmarks comparing WekaIO performance to a local SSD file system, showing that we are the only coherent shared storage that is even faster than the current caching solutions, while allowing customers to linearly scale performance by adding more GPU servers.”

HPE wins $57 Million Supercomputing Contract for DoD Modernization Program

Today HPE announced it has been selected to provide new supercomputers for the DoD High Performance Computing Modernization Program (HPCMP) to accelerate the development and acquisition of advanced national security capabilities. “The DoD’s continuous investment in supercomputing innovation is a clear testament to this development and an important contribution to U.S. national security. HPE has been a strategic partner with the HPCMP for two decades, and we are proud that the DoD now significantly extends this partnership, acknowledging HPE’s sustained leadership in high performance computing.”