It Is About Latency

By Gilad Shainer, Mellanox Technologies

December 2, 2019

Data latency or bandwidth (latency of large data messages) is one of the key elements responsible for applications performance and scalability as we all know. The lower the latency, the better the performance we can gain. Latency can be measured on a non-loaded (aka empty) cluster system or on a loaded system. This article addresses latency measurements of the first case, since it is important for understanding the latency an application will incur with a single job running. The second case of multiple applications sharing the same cluster simultaneously will be addressed in a future article.

The challenge of reducing data transfer latency has been going through multiple technology development phases – from reducing network latency to reducing complex data operations latencies. InfiniBand, the leading interconnect for high performance and data intensive applications, demonstrates extremely low latency today, with switch latencies close to 100ns, and an end-to-end latency of less than 1usec (end-point to end-point). The effort of reducing the latency of complex data operations involves adding new hardware and software technologies.

These hardware enhancements are referred to as In-Network Computing, reflecting additional dedicated or configurable computation engines embedded in the network devices. Two examples include the Mellanox Scalable Hierarchical Aggregation and Reduction Protocol (SHARP)™ and Mellanox MPI hardware Tag Matching technologies. Mellanox SHARP is based on dedicated compute engines located on the InfiniBand switch data path dedicated for performing data reduction and aggregation operations; and the hardware-based MPI matching engines are part of the InfiniBand adapters. These two technologies enable dramatic reduction in the latency of  MPI, SHMEM/PGAS and other programming models operations, and to maintain low latencies regardless of clusters sizes.

Figure 1 below shows a comparison of MPI latency (OSU MPI benchmark) and MPI Random Ring latency between EDR InfiniBand, Aries and Slingshot, demonstrating the InfiniBand latency advantage over previous and next generations of competitive proprietary networks.

Figure 1: Comparison of MPI latency (OSU MPI benchmark) and MPI Random Ring latency between Mellanox EDR InfiniBand, Cray Aries and Cray Slingshot, demonstrating the InfiniBand latency advantage (Source: “Characterizing full system network performance”, Cray User Group 2019 Proceedings)

Figure 2 shows MPI latency based on the OSU MPI benchmark, demonstrating the latency advantage gained through Mellanox MPI Tag Matching technology (HW-TM in the figure) – a 35% reduction in MPI latency.

Figure 2: MPI latency based on OSU benchmark improves by 35% using Mellanox MPI Tag Matching technology (Source: Ohio State University MVAPICH team presentation at Supercomputing 2019)

Beyond the latency reduction that is obtained by performing MPI Tag Matching operations at the network level, it is also possible to increase communication-to-computation overlap. Communication-computation-overlap refers to the ability for computation to progress asynchronously as the CPU is being used for application computational tasks.. The higher the overlap the better the system utilization. Figure 3 demonstrates close to 100% overlap between communication and computations of the MPI_lscatterv operations, leveraging Mellanox Tag Matching technology (HW-TM in the figure). The test was conducted on the Frontera supercomputer at Texas Advanced Computing Center.

Figure 3: Communication and computations overlap percentage with MPI_Iscatterv operations leveraging Mellanox Tag Matching technology to reach almost 100% overlap, as tested on Texas Advanced Computing Center’s Frontera supercomputer (source: Ohio State University MVAPICH team presentation at Supercomputing 2019). “HW-TM” means Mellanox hardware MPI Tag Matching).

There are multiple publications regarding ’Mellanox’s SHARP In-Network Computing technology and its performance advantages for high performance and deep learning applications. Mellanox SHARP supports both low-latency data reductions and large data reductions, also referred to as streaming data aggregation. Figure 4 provides a clear demonstration of Mellanox SHARP In-Network Computing technology advantage. Compared to software-based implementations, Mellanox SHARP technology not only yields lower latency, but also maintains a nearly flat latency profile across cluster sizes.

Figure 4: MPI AllReduce latency comparison between Mellanox SHARP In-Network Computing technology and all-software-based MPI implementations. Using Mellanox SHARP yields lower latency which remains nearly flat across different cluster sizes.

Figure 5 demonstrates another of Mellanox SHARP advantages. A GNMT MLPerf benchmark for neural machine translation was run using NVIDIA Collective Communications Library (NCCL) version 2.4 with and without Mellanox SHARP, over 24 NVIDIA DGX systems and Mellanox InfiniBand interconnect. As can be seen in the figure, leveraging Mellanox SHARP results in a nearly 20% performance gain.

Figure 5: GNMT MLPerf benchmark (Neural Machina Translation) gains nearly 20% in performance by leveraging Mellanox SHARP with NVIDIA NCCL v2.4, run over 24 NVIDIA DGX1 systems and Mellanox InfiniBand.

One of the main factors influencing performance of compute and data intensive parallel applications is the latency of network transfer operations. InfiniBand addresses the latency challenge in a two-fold approach: on the one hand it provides extremely low network latency, and on the other hand introduces smart In-Network Computing engines to improve the latency of complex data operations, such as those used by high performance or deep learning communication frameworks. These advantages set InfiniBand apart as the leading interconnect solution for today’s and future supercomputing platforms.

 

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!

Focused on ‘Silicon TAM,’ Intel Puts Gary Patton, Former GlobalFoundries CTO, in Charge of Design Enablement

December 12, 2019

Change within Intel’s upper management – and to its company mission – has continued as a published report has disclosed that chip technology heavyweight Gary Patton, GlobalFoundries’ CTO and R&D SVP as well a Read more…

By Doug Black

Quantum Bits: Rigetti Debuts New Gates, D-Wave Cuts NEC Deal, AWS Jumps into the Quantum Pool

December 12, 2019

There’s been flurry of significant news in the quantum computing world. Yesterday, Rigetti introduced a new family of gates that reduces circuit depth required on some problems and D-Wave struck a deal with NEC to coll Read more…

By John Russell

How Formula 1 Used Cloud HPC to Build the Next Generation of Racing

December 12, 2019

Formula 1, Rob Smedley explained, is maybe the biggest racing spectacle in the world, with five hundred million fans tuning in for every race. Smedley, a chief engineer with Formula 1’s performance engineering and anal Read more…

By Oliver Peckham

RPI Powers Up ‘AiMOS’ AI Supercomputer

December 11, 2019

Designed to push the frontiers of computing chip and systems performance optimized for AI workloads, an 8 petaflops (Linpack) IBM Power9-based supercomputer has been unveiled in upstate New York that will be used by IBM Read more…

By Doug Black

At SC19: Developing a Digital Twin

December 11, 2019

In the not too distant future, we can expect to see our skies filled with unmanned aerial vehicles (UAVs) delivering packages, maybe even people, from location to location. In such a world, there will also be a digital twin for each UAV in the fleet: a virtual model that will follow the UAV through its existence, evolving with time. Read more…

By Aaron Dubrow

AWS Solution Channel

Making High Performance Computing Affordable and Accessible for Small and Medium Businesses with HPC on AWS

High performance computing (HPC) brings a powerful set of tools to a broad range of industries, helping to drive innovation and boost revenue in finance, genomics, oil and gas extraction, and other fields. Read more…

IBM Accelerated Insights

GPU Scheduling and Resource Accounting: The Key to an Efficient AI Data Center

[Connect with LSF users and learn new skills in the IBM Spectrum LSF User Community!]

GPUs are the new CPUs

GPUs have become a staple technology in modern HPC and AI data centers. Read more…

Supercomputers Help Predict Carbon Dioxide Levels

December 10, 2019

The Earth’s terrestrial ecosystems – its lands, forests, jungles and so on – are crucial “sinks” for atmospheric carbon, holding nearly 30 percent of our annual CO2 emissions as they breathe in the carbon-rich Read more…

By Oliver Peckham

Focused on ‘Silicon TAM,’ Intel Puts Gary Patton, Former GlobalFoundries CTO, in Charge of Design Enablement

December 12, 2019

Change within Intel’s upper management – and to its company mission – has continued as a published report has disclosed that chip technology heavyweight G Read more…

By Doug Black

RPI Powers Up ‘AiMOS’ AI Supercomputer

December 11, 2019

Designed to push the frontiers of computing chip and systems performance optimized for AI workloads, an 8 petaflops (Linpack) IBM Power9-based supercomputer has Read more…

By Doug Black

At SC19: Developing a Digital Twin

December 11, 2019

In the not too distant future, we can expect to see our skies filled with unmanned aerial vehicles (UAVs) delivering packages, maybe even people, from location to location. In such a world, there will also be a digital twin for each UAV in the fleet: a virtual model that will follow the UAV through its existence, evolving with time. Read more…

By Aaron Dubrow

Intel’s Jim Clarke on its New Cryo-controller and why Intel isn’t Late to the Quantum Party

December 9, 2019

Intel today introduced the ‘first-of-its-kind’ cryo-controller chip for quantum computing and previewed a cryo-prober tool for characterizing quantum proces Read more…

By John Russell

On the Spack Track @SC19

December 5, 2019

At the annual supercomputing conference, SC19 in Denver, Colorado, there were Spack events each day of the conference. As a reflection of its grassroots heritage, nine sessions were planned by more than a dozen thought leaders from seven organizations, including three U.S. national Department of Energy (DOE) laboratories and Sylabs... Read more…

By Elizabeth Leake

Intel’s New Hyderabad Design Center Targets Exascale Era Technologies

December 3, 2019

Intel's Raja Koduri was in India this week to help launch a new 300,000 square foot design and engineering center in Hyderabad, which will focus on advanced com Read more…

By Tiffany Trader

AWS Debuts 7nm 2nd-Gen Graviton Arm Processor

December 3, 2019

The “x86 Big Bang,” in which market dominance of the venerable Intel CPU has exploded into fragments of processor options suited to varying workloads, has n Read more…

By Doug Black

Ride on the Wild Side – Squyres SC19 Mars Rovers Keynote

December 2, 2019

Reminding us of the deep and enabling connection between HPC and modern science is an important part of the SC Conference mission. And yes, HPC is a science its Read more…

By John Russell

Using AI to Solve One of the Most Prevailing Problems in CFD

October 17, 2019

How can artificial intelligence (AI) and high-performance computing (HPC) solve mesh generation, one of the most commonly referenced problems in computational engineering? A new study has set out to answer this question and create an industry-first AI-mesh application... Read more…

By James Sharpe

D-Wave’s Path to 5000 Qubits; Google’s Quantum Supremacy Claim

September 24, 2019

On the heels of IBM’s quantum news last week come two more quantum items. D-Wave Systems today announced the name of its forthcoming 5000-qubit system, Advantage (yes the name choice isn’t serendipity), at its user conference being held this week in Newport, RI. Read more…

By John Russell

DARPA Looks to Propel Parallelism

September 4, 2019

As Moore’s law runs out of steam, new programming approaches are being pursued with the goal of greater hardware performance with less coding. The Defense Advanced Projects Research Agency is launching a new programming effort aimed at leveraging the benefits of massive distributed parallelism with less sweat. Read more…

By George Leopold

Ayar Labs to Demo Photonics Chiplet in FPGA Package at Hot Chips

August 19, 2019

Silicon startup Ayar Labs continues to gain momentum with its DARPA-backed optical chiplet technology that puts advanced electronics and optics on the same chip Read more…

By Tiffany Trader

SC19: IBM Changes Its HPC-AI Game Plan

November 25, 2019

It’s probably fair to say IBM is known for big bets. Summit supercomputer – a big win. Red Hat acquisition – looking like a big win. OpenPOWER and Power processors – jury’s out? At SC19, long-time IBMer Dave Turek sketched out a different kind of bet for Big Blue – a small ball strategy, if you’ll forgive the baseball analogy... Read more…

By John Russell

Cray, Fujitsu Both Bringing Fujitsu A64FX-based Supercomputers to Market in 2020

November 12, 2019

The number of top-tier HPC systems makers has shrunk due to a steady march of M&A activity, but there is increased diversity and choice of processing compon Read more…

By Tiffany Trader

Crystal Ball Gazing: IBM’s Vision for the Future of Computing

October 14, 2019

Dario Gil, IBM’s relatively new director of research, painted a intriguing portrait of the future of computing along with a rough idea of how IBM thinks we’ Read more…

By John Russell

Intel Debuts New GPU – Ponte Vecchio – and Outlines Aspirations for oneAPI

November 17, 2019

Intel today revealed a few more details about its forthcoming Xe line of GPUs – the top SKU is named Ponte Vecchio and will be used in Aurora, the first plann Read more…

By John Russell

Leading Solution Providers

SC 2019 Virtual Booth Video Tour

AMD
AMD
CEJN
CJEN
ONE STOP SYSTEMS
ONE STOP SYSTEMS
PANASAS
PANASAS
SIX NINES IT
SIX NINES IT
VERNE GLOBAL
VERNE GLOBAL
WEKAIO
WEKAIO

Kubernetes, Containers and HPC

September 19, 2019

Software containers and Kubernetes are important tools for building, deploying, running and managing modern enterprise applications at scale and delivering enterprise software faster and more reliably to the end user — while using resources more efficiently and reducing costs. Read more…

By Daniel Gruber, Burak Yenier and Wolfgang Gentzsch, UberCloud

Dell Ramps Up HPC Testing of AMD Rome Processors

October 21, 2019

Dell Technologies is wading deeper into the AMD-based systems market with a growing evaluation program for the latest Epyc (Rome) microprocessors from AMD. In a Read more…

By John Russell

Cray Wins NNSA-Livermore ‘El Capitan’ Exascale Contract

August 13, 2019

Cray has won the bid to build the first exascale supercomputer for the National Nuclear Security Administration (NNSA) and Lawrence Livermore National Laborator Read more…

By Tiffany Trader

SC19: Welcome to Denver

November 17, 2019

A significant swath of the HPC community has come to Denver for SC19, which began today (Sunday) with a rich technical program. As is customary, the ribbon cutt Read more…

By Tiffany Trader

When Dense Matrix Representations Beat Sparse

September 9, 2019

In our world filled with unintended consequences, it turns out that saving memory space to help deal with GPU limitations, knowing it introduces performance pen Read more…

By James Reinders

Cerebras to Supply DOE with Wafer-Scale AI Supercomputing Technology

September 17, 2019

Cerebras Systems, which debuted its wafer-scale AI silicon at Hot Chips last month, has entered into a multi-year partnership with Argonne National Laboratory and Lawrence Livermore National Laboratory as part of a larger collaboration with the U.S. Department of Energy... Read more…

By Tiffany Trader

With the Help of HPC, Astronomers Prepare to Deflect a Real Asteroid

September 26, 2019

For years, NASA has been running simulations of asteroid impacts to understand the risks (and likelihoods) of asteroids colliding with Earth. Now, NASA and the European Space Agency (ESA) are preparing for the next, crucial step in planetary defense against asteroid impacts: physically deflecting a real asteroid. Read more…

By Oliver Peckham

Jensen Huang’s SC19 – Fast Cars, a Strong Arm, and Aiming for the Cloud(s)

November 20, 2019

We’ve come to expect Nvidia CEO Jensen Huang’s annual SC keynote to contain stunning graphics and lively bravado (with plenty of examples) in support of GPU Read more…

By John Russell

  • arrow
  • Click Here for More Headlines
  • arrow
Do NOT follow this link or you will be banned from the site!
Share This