MPI: Maturing, Evolving, and Becoming More Pervasive

By Salvatore Salamone

August 6, 2018

Have you kept pace with the changes in the message passing interface (MPI) specification? Most likely not, if you’re like most people, even though it is very likely your high-performance computing (HPC) workloads are benefiting from the most recent updates and enhancements done to MPI.

MPI was conceived and developed by academic and industry researchers in the early 1990s and was designed to be a portable message-passing middleware to function on a wide variety of parallel computing architectures.

Today, MPI is widely considered as the de facto parallel programming standard for the most demanding HPC environments. MPI over InfiniBand is used to accelerate workloads on the most powerful supercomputers, including the top three Top500 HPC systems, and four of the top five systems. Additionally, MPI continues to be the dominant middleware for HPC systems and is pervasive across distributed AI/ML applications.

The latest updates and enhancements are being driven by the demands of new application areas such as AI, distributed machine learning (ML), and the increased use of GPUs in HPC environments.

Introducing the MVAPICH project

The MVAPICH project, led by Network-Based Computing Laboratory (NBCL) of The Ohio State University, is developing MPI enhancements to meet the performance demands of these new application areas.

The MVAPICH2 software, based on MPI 3.1 standard, delivers the best performance, scalability, and fault tolerance for high-end computing systems and servers using a wide range of interconnect technologies, including InfiniBand and RoCE networking technologies. The MVAPICH2 software family is also ABI (application binary interface) compatible with various other MPI libraries such as MPICH, IntelMPI, CrayMPI, and others.

The software is now being used by more than 2,925 organizations in 86 countries worldwide to extract the potential of the latest emerging networking technologies, such as in-network computing. As of July, more than 482,000 downloads have taken place from the project’s site, and many vendors, including Mellanox are also distributing this software as part of their own software distributions.

The MVAPICH project is optimizing its implementation of MPI to keep pace with the changing demands in technology and all while keeping faithful to the MPI standard.

Currently, MVAPICH2 2.3 is the latest version and provides many enhancements and new features including MPI-3.1 standards compliance, single copy intra-node communication using Linux supported CMA (Cross Memory Attach), Checkpoint/Restart using LLNL’s Scalable Checkpoint/Restart Library (SCR), high-performance and scalable InfiniBand hardware multicast-based collectives, enhanced shared-memory-aware and intra-node collectives, support for Mellanox SHARP technology for optimized collectives, high-performance communication support for NVIDIA GPU with IPC, collective and non-contiguous datatype support, MPI_T support, and integrated hybrid UD-RC/XRC design, and support for UD only mode. A complete set of features and supported platforms can be found here.

The MVAPICH project’s most recently released libraries are designed to address compute demands and performance requirements of newer HPC workloads and environments.

The libraries deliver specific benefits for different applications or computing needs. They include:

  • MVAPICH2: This library offers support for InfiniBand, RoCE, Ethernet and other interconnect technologies.
  • MVAPICH2-X: A library that includes advanced MPI features (exploiting UMR, ODP and Core-Direct features of InfiniBand), OSU INAM for Network Analysis and Monitoring, PGAS (OpenSHMEM, UPC, UPC++, and CAF), and MPI+PGAS programming models with unified communication runtime
  • MVAPICH2-GDR: This delivers optimized MPI for clusters with NVIDIA GPUs. This library is also designed to deliver high-performance and scalability for the emerging deep-learning applications
  • MVAPICH2-Virt: This library offers high-performance and scalable MPI for hypervisor and container-based HPC cloud applications
  • MVAPICH2-EA: A library for energy aware and High-performance MPI

Selecting a technology partner

When implementing MPI to improve the performance of your HPC environment, it is not done independently, but rather by partnering with technology companies that have expertise in the area.

Mellanox is a leader in the field and offers high-speed interconnect solutions which based on open standards. They work closely with the MVAPICH project to ensure the benefits provided by the project’s latest libraries take full advantage of the improvements and additional offload engines from its latest 100Gb/s EDR and 200Gb/s HDR InfiniBand. Additionally, Mellanox uses the project’s benchmarks to validate performance claims.

At the heart of the Mellanox HPC software offering is its HPC-X™. This is a comprehensive software package that includes MPI, SHMEM, and UPC communications libraries. HPC-X also includes various acceleration packages to improve both the performance and scalability of applications running on top of these libraries, including support for MXM (Mellanox Messaging) which accelerates the underlying send/receive (or put/get) messages, and FCA (Fabric Collectives Accelerations) which accelerates the underlying collective operations used by the MPI/PGAS languages.

Mellanox HPC-X takes full advantage of the Mellanox hardware-based acceleration engines to maximize MPI, SHMEM/PGAS and UPC based applications. These acceleration engines are part of the Mellanox adapter (CORE-Direct engine) and switch (Mellanox SHARP engine) solutions. Mellanox Scalable Hierarchical Aggregation and Reduction Protocol (SHARP)™ technology improves upon the performance of MPI operations by offloading collective operations from the CPU to the switch network, and by eliminating the need to send data multiple times between endpoints. This innovative approach decreases the amount of data traversing the network as aggregation nodes are reached which dramatically reduces the MPI operations time.

Implementing collective communication algorithms in the network also has additional benefits, such as freeing up valuable CPU resources for computation rather than using them to process communication.

Mellanox HPC-X allows OEM’s and System Integrators to meet the needs of their end-users by deploying the latest available software that takes advantage of the features and capabilities available in the most recent hardware and firmware changes.

Summary

New HPC application areas including AI and ML, along with the growing use of GPUs to accelerate compute-intensive applications requires robust and feature-rich message passing.

The MVAPICH project is producing new MPI libraries to enhance the performance of HPC systems and speed the execution of the most demanding workloads.

Today, MPI is supported on virtually all HPC platforms. It is highly portable. There is little or no need to modify your source code when you port your application to a different platform that supports the MPI standard.

Moreover, vendor implementations, such as Mellanox HPC-X, can further exploit native hardware features to optimize performance.

For more information about the MVAPICH project, visit: http://mvapich.cse.ohio-state.edu/

For more details about implementing MPI in today’s demanding HPC environments, visit: http://www.mellanox.com/page/hpcx_overview

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industry updates delivered to you every week!

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion XL — were added to the benchmark suite as MLPerf continues Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing power it brings to artificial intelligence.  Nvidia's DGX Read more…

Call for Participation in Workshop on Potential NSF CISE Quantum Initiative

March 26, 2024

Editor’s Note: Next month there will be a workshop to discuss what a quantum initiative led by NSF’s Computer, Information Science and Engineering (CISE) directorate could entail. The details are posted below in a Ca Read more…

Waseda U. Researchers Reports New Quantum Algorithm for Speeding Optimization

March 25, 2024

Optimization problems cover a wide range of applications and are often cited as good candidates for quantum computing. However, the execution time for constrained combinatorial optimization applications on quantum device Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at the network layer threatens to make bigger and brawnier pro Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HBM3E memory as well as the the ability to train 1 trillion pa Read more…

MLPerf Inference 4.0 Results Showcase GenAI; Nvidia Still Dominates

March 28, 2024

There were no startling surprises in the latest MLPerf Inference benchmark (4.0) results released yesterday. Two new workloads — Llama 2 and Stable Diffusion Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

NVLink: Faster Interconnects and Switches to Help Relieve Data Bottlenecks

March 25, 2024

Nvidia’s new Blackwell architecture may have stolen the show this week at the GPU Technology Conference in San Jose, California. But an emerging bottleneck at Read more…

Who is David Blackwell?

March 22, 2024

During GTC24, co-founder and president of NVIDIA Jensen Huang unveiled the Blackwell GPU. This GPU itself is heavily optimized for AI work, boasting 192GB of HB Read more…

Nvidia Looks to Accelerate GenAI Adoption with NIM

March 19, 2024

Today at the GPU Technology Conference, Nvidia launched a new offering aimed at helping customers quickly deploy their generative AI applications in a secure, s Read more…

The Generative AI Future Is Now, Nvidia’s Huang Says

March 19, 2024

We are in the early days of a transformative shift in how business gets done thanks to the advent of generative AI, according to Nvidia CEO and cofounder Jensen Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

Nvidia Showcases Quantum Cloud, Expanding Quantum Portfolio at GTC24

March 18, 2024

Nvidia’s barrage of quantum news at GTC24 this week includes new products, signature collaborations, and a new Nvidia Quantum Cloud for quantum developers. Wh Read more…

Alibaba Shuts Down its Quantum Computing Effort

November 30, 2023

In case you missed it, China’s e-commerce giant Alibaba has shut down its quantum computing research effort. It’s not entirely clear what drove the change. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

DoD Takes a Long View of Quantum Computing

December 19, 2023

Given the large sums tied to expensive weapon systems – think $100-million-plus per F-35 fighter – it’s easy to forget the U.S. Department of Defense is a Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Intel’s Server and PC Chip Development Will Blur After 2025

January 15, 2024

Intel's dealing with much more than chip rivals breathing down its neck; it is simultaneously integrating a bevy of new technologies such as chiplets, artificia Read more…

Baidu Exits Quantum, Closely Following Alibaba’s Earlier Move

January 5, 2024

Reuters reported this week that Baidu, China’s giant e-commerce and services provider, is exiting the quantum computing development arena. Reuters reported � Read more…

Leading Solution Providers

Contributors

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Shutterstock 1179408610

Google Addresses the Mysteries of Its Hypercomputer 

December 28, 2023

When Google launched its Hypercomputer earlier this month (December 2023), the first reaction was, "Say what?" It turns out that the Hypercomputer is Google's t Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Shutterstock 1606064203

Meta’s Zuckerberg Puts Its AI Future in the Hands of 600,000 GPUs

January 25, 2024

In under two minutes, Meta's CEO, Mark Zuckerberg, laid out the company's AI plans, which included a plan to build an artificial intelligence system with the eq Read more…

Google Introduces ‘Hypercomputer’ to Its AI Infrastructure

December 11, 2023

Google ran out of monikers to describe its new AI system released on December 7. Supercomputer perhaps wasn't an apt description, so it settled on Hypercomputer Read more…

China Is All In on a RISC-V Future

January 8, 2024

The state of RISC-V in China was discussed in a recent report released by the Jamestown Foundation, a Washington, D.C.-based think tank. The report, entitled "E Read more…

Intel Won’t Have a Xeon Max Chip with New Emerald Rapids CPU

December 14, 2023

As expected, Intel officially announced its 5th generation Xeon server chips codenamed Emerald Rapids at an event in New York City, where the focus was really o Read more…

IBM Quantum Summit: Two New QPUs, Upgraded Qiskit, 10-year Roadmap and More

December 4, 2023

IBM kicks off its annual Quantum Summit today and will announce a broad range of advances including its much-anticipated 1121-qubit Condor QPU, a smaller 133-qu Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire