Massively Scalable AI that Seamlessly Works with Your Existing Infrastructures, Power Availability, and Budget

February 22, 2021

Artificial intelligence (AI) applications need a highly scalable hardware assist to execute fast enough for their output to be used in decision-making. Help is on the way. Graphcore’s IPU-POD systems offer massive scalable potential to thousands of IPU-M2000 machines while allowing users to ‘dial-up’ IPU resources and their regular compute resources in set increments to match their needs. Such capabilities satisfy the compute requirements of the most demanding AI applications with the additional benefit of being economically easier to manage and more ‘tuned for purpose’. IPU-PODs are configured in a range of scale-out options and capacity can be adjusted to accommodate the power budgets available in your racks.

An AI acceleration solution for production environments

At the heart of the solution is the Colossus GC200 MK2 IPU, a massively parallel 59.4 billion transistor processor. It delivers 250 Trillion Operations per Second (TOPS) across 1,472 independent cores with 900MB of In-Processor Memory and an internal IPU memory bandwidth at a blazingly fast 47TBs. The IPU-M2000s are interconnected across a 2.8Tbps low-latency fabric.

The IPU-M2000 integrates four of these processors in a 1U shelf, offering one petaflop of mixed-precision compute. This is the core building block for a family of IPU-POD systems that are designed to fit different AI workloads and datacenter power provisioning. Four IPU-M2000’s and a direct attach server are offered as an IPU-POD16, eight IPU-M2000’s with server and switches make up the IPU-POD32, while sixteen IPU-M2000’s make up an IPU-POD64. Such a solution provides a core building block to further scale-out the solution into the exascale domain.

The scale-out capacity is complemented with Graphcore’s unique IPU-Fabric™ interconnect technology. IPU-Fabric is a collection of technologies that ultimately accelerate the speed at which the AI workload can be processed. It covers communication between the IPUs in an IPU-M2000, intra-rack IPU-M2000 to IPU-M2000 interconnect, and inter-rack IPU-M2000 to IPU-M2000 communication. IPU-Fabric is ultra-low latency, deterministic, and jitter-free.

Comfortable fit into existing environments

Getting workloads to run on new acceleration processors is often an arduous task. Graphcore addresses this issue with its Poplar® SDK, which is a complete software stack co-designed with the IPU. Poplar is fully integrated with standard machine learning frameworks, like TensorFlow and PyTorch so developers can work in a familiar environment. Additionally, Poplar minimises complexities when scaling to more systems. These features help developers easily use the IPU system’s processing power for any existing or new compute-intensive AI application.

As well as building AI graphs in the Poplar compiler, all the communication events that will happen during the job are calculated and allotted during the compilation process. This, together with the guaranteed very tight timing of packet delivery in IPU-Fabric, means you get a super-efficient and performant system without contention, collisions, or losses.

Ola Tørudbakken, SVP at Graphcore, states “The IPU-POD architecture is designed specifically to accommodate scale-out at a massive level. A combination of innovations has been introduced to make this possible. Three that are of particular note are the deterministic compiled in communications that happen in the Poplar software stack, our very fast, low-latency IPU-Fabric that allows all-to-all IPU communication, and our comprehensive communications library to support the massive number of collective operations that happen in deep learning workloads. All of these work in concert to achieve ground-breaking performance at scale”.

From an IT management perspective, Graphcore uses the most popular industry standard tools such as OpenBMC, RedFish, and IPMI over LAN. The management software is deliberately a flexible modular solution with a rich collection of open APIs for integration into existing systems.

Once an application can run on the system, Graphcore offers help deploying and maintaining the apps into a production environment. The IPU-POD uses common orchestration solutions like Kubernetes and Slurm. As a result, DevOps teams have the tools to ensure applications operate efficiently and deliver the expected performance and reliability needed in a production environment.

The IPU Systems are designed for virtualized datacenters. They offer virtualized hardware resource allocation and provisioning with Virtual IPU and containerized Poplar AI graph workloads using industry-standard tools such as Docker and Kubernetes.

The 1U IPU-M2000 is accessed over 100GbE RoCEv2 (RDMA over Converged Ethernet) for low-latency access. Using Ethernet avoids the bottlenecks and costs of PCIe connectors and enables a flexible CPU to accelerator ratio.

Additionally, the IPU-M2000 includes integrated scale-out networking, enabling the user to easily scale from a small system for development to massive rack deployments, all networked over standard networking at a lower cost, and with larger scale-out possibilities than using InfiniBand. The IPU-Fabric connects  IPUs by tunneling over Ethernet, maintaining the same programming model,  regardless of the size of the deployment.

“We use a standard 100-gigabit ethernet fabric for rack-to-rack connectivity. The integrated networking lets an organization start very small and go very big”, continues Tørudbakken.

Takeaways

IPU-POD systems are architected to seamlessly fit into an existing data center network and offer multiple ways of scaling up. A company can start with a single IPU-M2000 attached directly to a server providing one petaflop of compute, although many companies choose an IPU-POD16  made of four IPU-M2000’s directly attached to a server, for their experimentation and pilot work. From there they can scale out to IPU-POD64 IPU-POD128 and larger systems, connected to host servers through a standard ethernet-switched fabric.

Simply put, the Graphcore IPU-POD delivers the performance at scale for AI workloads with minimal training or adjustments and without disrupting production environments and operations.

Graphcloud is available now for evaluating the unique advantages of the IPU and IPU-POD Systems: https://www.graphcore.ai/graphcloud

To learn more about scalable machine intelligence with IPU-POD Systems in the datacenter watch our webinar: //play.vidyard.com/aEe1y5aGDBSHcfUEBLB3Pk.jpg?

 

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