Mellanox, ORNL to Deliver UCX Progress Report at SC15

By John Russell

November 16, 2015

At ISC2015 Mellanox introduced a new open-source network communication framework – United Communication X Framework (UCX) – for high-performance and data-centric applications.

At the time Gilad Shainer of Mellanox said, “By providing our advancements in shared memory, MPI and underlying network transport technologies, we can continue to advance open standards-based networking and programming models. UCX will provide optimizations for lower software overhead in communication paths that will allow cross platform near native-level interconnect performance. The framework interface will expose semantics that target not only HPC programming models, but data-centric applications as well. It will also enable vendor independent development of the library.”

These are big goals. Promoting co-design methodology is at the heart of the effort. UCX alliance members hope the effort will not only provide a vehicle for production quality software, but also a low-level research infrastructure for more flexible and portable support for exascale-ready programming models. Other UCX founding members were present at the launch and included DOE’s Oak Ridge National Laboratory, NVIDIA, IBM, the University of Tennessee the group, and NVIDIA.

The UCX key UCX components include:

  • UC-S for Services. Basic infrastructure for component based programming, memory management, and useful system utilities. Functionality: platform abstractions and data structures.
  • UC-T for Transport. Low-level API that expose basic network operations supported by underlying hardware. Functionality: work request setup and instantiation of operations.
  • UC-P for Protocols. High-level API uses UCT framework to construct protocols commonly found in applications Functionality: multi-rail, device selection, pending queue, rendezvous, tag-matching, software-atomics, etc.

Shainer insists UCX is the framework for future systems. At SC15 this week, he and Pavel Shamis (ORNL) will provide UCX update at a BOF on Tuesday. As a prelude, HPCwire asked Shainer to review the purpose of UCX and its early activities and progress. Here is that interview.

HPCwire: I was at the ISC introduction of UCX and several of the gathered attendees were impressed by the founding members by confused about the goals and the problem it was attacking. Perhaps it would be worthwhile to review how UCX originated and what it seeks to accomplish.

Gilad1Shainer: Today there are multiple HPC libraries (MPI, SHMEM, PGAS languages) and emerging HPC programming models (libraries and languages) that face a substantial challenge because they require a re-implementation (or maintenance) of complex network codes within the code-bases.

This often leads to code duplication and long term maintenance issues. As a side effect these duplicated efforts frequently result in performance issues because developers don’t have the time, or the vendor-level expertise in some cases, required to optimize network. In addition, emerging hardware technologies are now focusing primarily on a limited range of HPC libraries or programming models (mostly MPI) due to time and resource constraints. At the end of the day, resources are desperately needed to optimize both software and hardware with emerging HPC programming models.

By providing a unified, standardized, performance-portable and hardware agnostic interface these issues are resolved. HPC libraries and programming models can now target a single API that enables optimal execution of the libraries on a broad variety of hardware architectures. At the same time, hardware vendors can focus on the development of a single layer, which enables functionality across multiple programming models.

Another important aspect of the challenge is the exascale programming environment has yet to be defined and it is a topic of ongoing HPC research. In order to address this challenge UCX was designed as a framework – a collection of building blocks that enables fast and flexible access to various utilities and communication directives. This approach provides fine grain flexibility that allows HPC researches to customize and adjust UCX for their unique and specific needs. This is exactly the part where the co-design component of the effort is critical. Through the UCX framework researchers can (and already do) influence hardware architecture through the offloading of some of the capabilities onto the hardware. Simultaneously researchers are able to learn about new features and capabilities of the hardware, enabling those for exascale programming models.

This is truly the kind of project where researchers and industry work together on co-design and transition from the bleeding edge of research to the production environment.

UCX diagram 2015-07-13HPCwire: You’ve described ambitious goals. How do you practically make that happen? Who are the primary supporters UCX has and needs and what are the key technical hurdles confronting progress?

Shainer: UCX is truly open source and community driven effort. The base code of UCX was contributed by industry, academic and government labs, and today the organizations involved are Oak Ridge National laboratory, Mellanox, IBM, NVIDIA, Lawrence Livermore national laboratory, Argonne National laboratory, University of Tennessee, Houston University and Pathscale.

In terms of technical hurdles confronting progress, UCX is vastly different from other frameworks. The base of UCX required years of development from its members, and now the effort is being unified. Users, labs, academic institutes and commercial vendors are all working together to create synergies between the software and the hardware. The intention is to deliver the most advanced high-performance software framework that will be used on standard solutions, such as InfiniBand and Ethernet, as well on custom made products.

HPCwire: Does UCX effort to fit into OpenPOWER?

Shainer: No, UCX is not part of OpenPOWER. UCX supports any compute platform including Power, GPUs and x86. We believe many future systems, including the CORAL system (but not limited to CORAL), will use UCX as the software framework between the infrastructure and the applications.

HPCwire: What are some of the milestones you’ll look for to that indicate UCX is gaining traction in the HPC community?

Shainer: The number of contributors and developers on UCX continues to grow and we are seeing more and more organizations looking to incorporate UCX into their HPC platforms. UCX has already been integrated with upstream of Open MPI project and OpenSHMEM. Upcoming version of OpenMPI 2.0 will have full support for UCX. Also, the upcoming year will reveal more software solutions using HPC, including the highly popular MPICH MPI developed by researches from Argonne National Laboratories, as well as increased support for emerging exascale runtimes like ParSec developed by University of Knoxville, Tennessee. Clearly there is a need for a co-designed, open and eco-system driven framework out there, and UCX is filling this need.

HPCwire: The original announcement noted UCX will incorporate elements of MXM (Mellanox), UCCS (ORNL), and PAMI (IBM) technology. This seems like a powerful combination. How will this work be done and what are the strengths of each the UCX wishes to capture?

Shainer: Yes, this is a powerful combination. With UCX we consolidate decades of experience in development of HPC software by variety of industry and academy organization into an open source framework. It unites elements that were designed for the fastest networks, large infrastructures, accelerators, MPI, SHMEM/PGAS and UPC. We have successfully created synergies between the software and the hardware, and it is full open source. We’ll do several demonstrations at SC15, and will host a BoF session on Tuesday, November 17, 3:30PM – 5:00PM, Room 15. All are invited to join us there and learn more on UCX, its mission, the current development status and our future plans.

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!

African Supercomputing Center Inaugurates ‘Toubkal,’ Most Powerful Supercomputer on the Continent

February 25, 2021

Historically, Africa hasn’t exactly been synonymous with supercomputing. There are only a handful of supercomputers on the continent, with few ranking on the global stage. Now, the Mohammed VI Polytechnic University (U Read more…

By Oliver Peckham

Supercomputer-Powered Machine Learning Supports Fusion Energy Reactor Design

February 25, 2021

Energy researchers have been reaching for the stars for decades in their attempt to artificially recreate a stable fusion energy reactor. If successful, such a reactor would revolutionize the world’s energy supply over Read more…

By Oliver Peckham

Japan to Debut Integrated Fujitsu HPC/AI Supercomputer This Spring

February 25, 2021

The integrated Fujitsu HPC/AI Supercomputer, Wisteria, is coming to Japan this spring. The University of Tokyo is preparing to deploy a heterogeneous computing system, called "Wisteria/BDEC-01," that will tackle simulati Read more…

By Tiffany Trader

President Biden Signs Executive Order to Review Chip, Other Supply Chains

February 24, 2021

U.S. President Biden signed an executive order late today calling for a 100-day review of key supply chains including semiconductors, large capacity batteries, pharmaceuticals, and rare-earth elements. The scarcity of ch Read more…

By John Russell

Xilinx Launches Alveo SN1000 SmartNIC

February 24, 2021

FPGA vendor Xilinx has debuted its latest SmartNIC model, the Alveo SN1000, with integrated “composability” features that allow enterprise users to add their own custom networking functions to supplement its built-in networking. By providing deep flexibility... Read more…

By Todd R. Weiss

AWS Solution Channel

Introducing AWS HPC Tech Shorts

Amazon Web Services (AWS) is excited to announce a new videos series focused on running HPC workloads on AWS. This new video series will cover HPC workloads from genomics, computational chemistry, to computational fluid dynamics (CFD) and more. Read more…

ASF Keynotes Showcase How HPC and Big Data Have Pervaded the Pandemic

February 24, 2021

Last Thursday, a range of experts joined the Advanced Scale Forum (ASF) in a rapid-fire roundtable to discuss how advanced technologies have transformed the way humanity responded to the COVID-19 pandemic in indelible ways. The roundtable, held near the one-year mark of the first... Read more…

By Oliver Peckham

Japan to Debut Integrated Fujitsu HPC/AI Supercomputer This Spring

February 25, 2021

The integrated Fujitsu HPC/AI Supercomputer, Wisteria, is coming to Japan this spring. The University of Tokyo is preparing to deploy a heterogeneous computing Read more…

By Tiffany Trader

Xilinx Launches Alveo SN1000 SmartNIC

February 24, 2021

FPGA vendor Xilinx has debuted its latest SmartNIC model, the Alveo SN1000, with integrated “composability” features that allow enterprise users to add their own custom networking functions to supplement its built-in networking. By providing deep flexibility... Read more…

By Todd R. Weiss

ASF Keynotes Showcase How HPC and Big Data Have Pervaded the Pandemic

February 24, 2021

Last Thursday, a range of experts joined the Advanced Scale Forum (ASF) in a rapid-fire roundtable to discuss how advanced technologies have transformed the way humanity responded to the COVID-19 pandemic in indelible ways. The roundtable, held near the one-year mark of the first... Read more…

By Oliver Peckham

IBM’s Prototype Low-Power 7nm AI Chip Offers ‘Precision Scaling’

February 23, 2021

IBM has released details of a prototype AI chip geared toward low-precision training and inference across different AI model types while retaining model quality within AI applications. In a paper delivered during this year’s International Solid-State Circuits Virtual Conference, IBM... Read more…

By George Leopold

IBM Continues Mainstreaming Power Systems and Integrating Red Hat in Pivot to Cloud

February 23, 2021

As IBM continues its massive pivot to the cloud, its Power-microprocessor-based products are being mainstreamed and realigned with the corporate-wide strategy. Read more…

By John Russell

Livermore’s El Capitan Supercomputer to Debut HPE ‘Rabbit’ Near Node Local Storage

February 18, 2021

A near node local storage innovation called Rabbit factored heavily into Lawrence Livermore National Laboratory’s decision to select Cray’s proposal for its CORAL-2 machine, the lab’s first exascale-class supercomputer, El Capitan. Details of this new storage technology were revealed... Read more…

By Tiffany Trader

ENIAC at 75: Celebrating the World’s First Supercomputer

February 15, 2021

With little fanfare, today’s computer revolution was arguably born and announced through a small, innocuous, two-column story at the bottom of the front page of The New York Times on Feb. 15, 1946. In that story and others, the previously classified project, ENIAC... Read more…

By Todd R. Weiss

Microsoft, HPE Bringing AI, Edge, Cloud to Earth Orbit in Preparation for Mars Missions

February 12, 2021

The International Space Station will soon get a delivery of powerful AI, edge and cloud computing tools from HPE and Microsoft Azure to expand technology experi Read more…

By Todd R. Weiss

Julia Update: Adoption Keeps Climbing; Is It a Python Challenger?

January 13, 2021

The rapid adoption of Julia, the open source, high level programing language with roots at MIT, shows no sign of slowing according to data from Julialang.org. I Read more…

By John Russell

Esperanto Unveils ML Chip with Nearly 1,100 RISC-V Cores

December 8, 2020

At the RISC-V Summit today, Art Swift, CEO of Esperanto Technologies, announced a new, RISC-V based chip aimed at machine learning and containing nearly 1,100 low-power cores based on the open-source RISC-V architecture. Esperanto Technologies, headquartered in... Read more…

By Oliver Peckham

Azure Scaled to Record 86,400 Cores for Molecular Dynamics

November 20, 2020

A new record for HPC scaling on the public cloud has been achieved on Microsoft Azure. Led by Dr. Jer-Ming Chia, the cloud provider partnered with the Beckman I Read more…

By Oliver Peckham

NICS Unleashes ‘Kraken’ Supercomputer

April 4, 2008

A Cray XT4 supercomputer, dubbed Kraken, is scheduled to come online in mid-summer at the National Institute for Computational Sciences (NICS). The soon-to-be petascale system, and the resulting NICS organization, are the result of an NSF Track II award of $65 million to the University of Tennessee and its partners to provide next-generation supercomputing for the nation's science community. Read more…

Programming the Soon-to-Be World’s Fastest Supercomputer, Frontier

January 5, 2021

What’s it like designing an app for the world’s fastest supercomputer, set to come online in the United States in 2021? The University of Delaware’s Sunita Chandrasekaran is leading an elite international team in just that task. Chandrasekaran, assistant professor of computer and information sciences, recently was named... Read more…

By Tracey Bryant

10nm, 7nm, 5nm…. Should the Chip Nanometer Metric Be Replaced?

June 1, 2020

The biggest cool factor in server chips is the nanometer. AMD beating Intel to a CPU built on a 7nm process node* – with 5nm and 3nm on the way – has been i Read more…

By Doug Black

Top500: Fugaku Keeps Crown, Nvidia’s Selene Climbs to #5

November 16, 2020

With the publication of the 56th Top500 list today from SC20's virtual proceedings, Japan's Fugaku supercomputer – now fully deployed – notches another win, Read more…

By Tiffany Trader

Gordon Bell Special Prize Goes to Massive SARS-CoV-2 Simulations

November 19, 2020

2020 has proven a harrowing year – but it has produced remarkable heroes. To that end, this year, the Association for Computing Machinery (ACM) introduced the Read more…

By Oliver Peckham

Leading Solution Providers

Contributors

Texas A&M Announces Flagship ‘Grace’ Supercomputer

November 9, 2020

Texas A&M University has announced its next flagship system: Grace. The new supercomputer, named for legendary programming pioneer Grace Hopper, is replacing the Ada system (itself named for mathematician Ada Lovelace) as the primary workhorse for Texas A&M’s High Performance Research Computing (HPRC). Read more…

By Oliver Peckham

At Oak Ridge, ‘End of Life’ Sometimes Isn’t

October 31, 2020

Sometimes, the old dog actually does go live on a farm. HPC systems are often cursed with short lifespans, as they are continually supplanted by the latest and Read more…

By Oliver Peckham

Saudi Aramco Unveils Dammam 7, Its New Top Ten Supercomputer

January 21, 2021

By revenue, oil and gas giant Saudi Aramco is one of the largest companies in the world, and it has historically employed commensurate amounts of supercomputing Read more…

By Oliver Peckham

Intel Xe-HP GPU Deployed for Aurora Exascale Development

November 17, 2020

At SC20, Intel announced that it is making its Xe-HP high performance discrete GPUs available to early access developers. Notably, the new chips have been deplo Read more…

By Tiffany Trader

Intel Teases Ice Lake-SP, Shows Competitive Benchmarking

November 17, 2020

At SC20 this week, Intel teased its forthcoming third-generation Xeon "Ice Lake-SP" server processor, claiming competitive benchmarking results against AMD's second-generation Epyc "Rome" processor. Ice Lake-SP, Intel's first server processor with 10nm technology... Read more…

By Tiffany Trader

New Deep Learning Algorithm Solves Rubik’s Cube

July 25, 2018

Solving (and attempting to solve) Rubik’s Cube has delighted millions of puzzle lovers since 1974 when the cube was invented by Hungarian sculptor and archite Read more…

By John Russell

It’s Fugaku vs. COVID-19: How the World’s Top Supercomputer Is Shaping Our New Normal

November 9, 2020

Fugaku is currently the most powerful publicly ranked supercomputer in the world – but we weren’t supposed to have it yet. The supercomputer, situated at Japan’s Riken scientific research institute, was scheduled to come online in 2021. When the pandemic struck... Read more…

By Oliver Peckham

MIT Makes a Big Breakthrough in Nonsilicon Transistors

December 10, 2020

What if Silicon Valley moved beyond silicon? In the 80’s, Seymour Cray was asking the same question, delivering at Supercomputing 1988 a talk titled “What’s All This About Gallium Arsenide?” The supercomputing legend intended to make gallium arsenide (GaA) the material of the future... Read more…

By Oliver Peckham

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire