Point and Click HPC: High-Performance Desktops

By Doug Eadline

July 3, 2024

Recently, an interesting paper appeared on Arvix called Use Cases for High-Performance Research Desktops. To be clear, the term desktop in this context does not refer to a machine but rather a computing desktop environment.

At first blush, this concept of an HPC desktop may seem to run counter to large datacenter HPC clusters. However, when considering the actual workflow of HPC users, the high-performance desktop is a natural evolution of current HPC methods.

In general, HPC users experience two types of environments. The first is a batch environment (e.g., Slurm) that allows jobs to be submitted to larger computing systems. The batch request requires the user to specify resources (e.g., the number of CPU cores, GPUs, memory, software licenses, etc.) and submit an application (job) to the larger systems. Once the batch job is submitted, the user is free to do other things (this wait time often includes waiting for their job to move through the work queue before it even runs). The second environment presents a more local experience with interactive possibilities, including workbooks or visualization tools. (e.g., running interactive graphical applications like MATLAB, RStudio, or VMD.) Indeed, once you have folded the protein, how will you look at it?

As the paper states, “The unifying concept behind all implementations of an HPC Desktop is that users have access to a persistent Linux Desktop and can use all the built-in tools of a desktop to organize and conduct their research.” In addition, the paper describes the guiding principle behind the HPC Desktop as “to lower the barrier of entry to HPC systems by providing users with a convenient and stable environment that performs comparably to their laptops or desktops (in this case desktop computers).

In contrast to the managed and scheduled HPC environment, HPC Desktops exist as a shared resource, with multiple users sharing the same compute, storage, and software environment, which adds constraints to the usage policies. As mentioned in the paper, several HPC centers and research computing organizations deploy HPC desktops. Again, to be clear, these are remote desktops running on cluster servers.

Several remote access solutions are used to implement HPC Desktops, such as ThinLinc, NoMachine, and FastX  Using one of these tools, the HPC Desktop provides users with a persistent Linux Desktop with access to all the built-in tools. For instance, tools such as a graphical file browser, a graphical editor, and access to a graphical menu make it easy to launch applications. In contrast, a more traditional HPC environment often requires application and file management to be accomplished using the command line (ssh connection).

Another advantage to implementing HPC Desktops with a remote software tool is the ability for the user to disconnect and reconnect to an HPC Desktop over days and weeks. This feature makes it easy to run an application for a long time, which may be difficult to accomplish on a laptop.

The hardware environment is depicted in the figure. Users connect with the HPC Desktop servers via the local LAN or internet. As part of the cluster, the Desktop servers are typically connected to the cluster storage and network. In addition, certain cluster nodes are partitioned as “interactive” and used as Application Servers to run interactive applications. Typically, the batch scheduler manages these and offers no waiting for the jobs to run, but limits can be applied to the number of interactive sessions. The bulk of the cluster nodes are still partitioned and used for HPC batch jobs.

Because many clusters consist of generic servers, creating the HPC Desktop environment can be as easy as reassigning server roles and configuring software. Indeed, older cluster nodes could be used for this purpose after a cluster refresh or upgrade.

Location of the HPC Desktop relative to High Performance compute and storage systems. (Source: https://arxiv.org/pdf/2404.03298)

Helping New Users

The Linux command line can present a “barrier to entry” for many HPC users. The ability to use a graphical file manager in a Linux and HPC environment presents a less steep learning curve. While not the same as MacOS Finder or Windows File Explorer, new users can quickly transfer “GUI” concepts to the Linux desktop environment. The paper describes how many “difficult” command line operations can be accomplished using a graphical file manager.

  • Easy unpacking of archive files by selecting a file with the mouse and selecting “Extract here” from the file’s context menu.
  • Create an archive from a directory tree by selecting “Compress” from the directory’s context menu.
  • Look up how much storage an entire directory tree consumes by looking at directory properties or using a disk usage analyzer tool.
  • Moving files from one storage location to another by using “Copy and Paste” or “Drag and Drop” (for example, from HOME to SCRATCH).
  • File deletion is done by either moving the file(s) to the “Trash” or right-clicking to choose “Delete” from a pop-up menu. Having a” Trash” facility that makes it easy for users to undelete a file.
  • Bookmarking directories in the file manager allows users to easily remember the mount points for different file systems, for example, HOME, SCRATCH, PROJECT, etc.
  • Connect to an “outside” storage location using the “Connect to Server” functionality. This feature allows easy data movement from Windows file shares and connecting to cloud storage providers.

HPC Job Management

In addition to file management, an HPC desktop offers an easier path to HPC job management. As the paper lists, many activities are much better suited to a graphical environment.

  • Easy movement of files between a user’s machine and the HPC Desktop.
  • Download software and data sets straight to an HPC file system using a web browser on the HPC Desktop, especially for downloads that require web authentication.
  • Long-running data movement operations like rsync or moving files to a tape archive.
  • Using GfxLauncher with interactive applications, such as post processors, visualization packages, and notebooks.
  • Using a graphical debugger from an interactive job with X-Forwarding to the HPC Desktop.
  • Using a graphical IDE to write, test, and debug code in an environment that mimics the destination HPC environment.
  • Running graphical HPC performance analysis tools like Vampir, MAP, the gprofng GUI, or NVIDIA Nsight.
  • Graphical editors to create and edit HPC batch scripts.
  • Quickly look at visualizations created by HPC jobs using an image viewer.

Beyond HPC Work

The HPC Desktop provides a convenient environment for running graphical applications for long periods (and even bookmark the session and return to it later). This capability is especially useful if those applications are long-running serial or modestly parallel so that they run well in a shared environment. These applications can access data on large central file systems without having to copy the data.

In terms of licensed software, the HPC Desktop allows centralized sharing for a limited number of licenses without having to install and license the software on individual systems. The paper also mentioned the following non-HPC advantages.

  • Long-running Jupyter Notebooks or R-Studio sessions.
  • Access to statistical software like SPSS, SAS, and STATA (support long-running stats scripts that are not parallel but need to run for a long period).
  • Run applications that are only licensed on a central system. (shared license model for MATLAB, SPSS, Photoscan, or other vendor software packages)
  • Visualization Software, with local or remote use of GPUs using VirtualGL.
  • Run applications that operate on large data but do not require intensive CPU or excessive memory usage.

The paper mentions many more aspects of HPC Desktops, including Teaching and Learning, Client-Server Applications, and Secure Enclaves.

The paper concludes by pointing out that HPC Desktops have successfully attracted new users to HPC systems and broadened the user base for many institutions beyond traditional “ssh-only” HPC systems. HPC Desktop’s unique contribution to the HPC ecosystem provides users with a single environment to perform all their computation research. As HPC moves further into the mainstream, creating a vibrant community around HPC Desktops will be instrumental in sharing best practices, innovations, and experiences and ensuring that HPC Desktops continue to serve as an enabler of scientific discovery and innovation.

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!

Weekly Wire Roundup: July 8-July 12, 2024

July 12, 2024

HPC news can get pretty sleepy in June and July, but this week saw a bump in activity midweek as Americans realized they still had work to do after the previous holiday weekend. The world outside the United States also s Read more…

Nvidia, Intel not Welcomed in New Apple AI and HPC Development Tools

July 12, 2024

New Mac developer tools will leverage Apple's homegrown chips, limiting HPC users' ability to use parallel programming frameworks from Intel or Nvidia. Apple's latest programming framework, Xcode 16, was introduced at Read more…

Virga: Australia’s New HPC and AI Powerhouse

July 11, 2024

Australia has officially added another supercomputer to the TOP500 list with the implementation of Virga. Officially coming online in June 2024, Virga is the newest HPC system to come out of the Australian Commonwealth S Read more…

NSF Issues Next Solicitation and More Detail on National Quantum Virtual Laboratory

July 10, 2024

After percolating for roughly a year, NSF has issued the next solicitation for the National Quantum Virtual Lab program — this one focused on design and implementation phases of the Quantum Quantum Science and Technolo Read more…

NCSA’s SEAS Team Keeps APACE of AlphaFold2

July 9, 2024

High-performance computing (HPC) can often be challenging for researchers to use because it requires expertise in working with large datasets, scaling the software, and selecting the best user interface. The National Read more…

Anders Jensen on Europe’s Plan for AI-optimized Supercomputers, Welcoming the UK, and More

July 8, 2024

The recent ISC24 conference in Hamburg showcased LUMI and other leadership-class supercomputers co-funded by the EuroHPC Joint Undertaking (JU), including three of the 10 highest-ranking Top500 systems, but some other ne Read more…

Shutterstock 2203611339

NSF Issues Next Solicitation and More Detail on National Quantum Virtual Laboratory

July 10, 2024

After percolating for roughly a year, NSF has issued the next solicitation for the National Quantum Virtual Lab program — this one focused on design and imple Read more…

NCSA’s SEAS Team Keeps APACE of AlphaFold2

July 9, 2024

High-performance computing (HPC) can often be challenging for researchers to use because it requires expertise in working with large datasets, scaling the softw Read more…

Anders Jensen on Europe’s Plan for AI-optimized Supercomputers, Welcoming the UK, and More

July 8, 2024

The recent ISC24 conference in Hamburg showcased LUMI and other leadership-class supercomputers co-funded by the EuroHPC Joint Undertaking (JU), including three Read more…

Generative AI to Account for 1.5% of World’s Power Consumption by 2029

July 8, 2024

Generative AI will take on a larger chunk of the world's power consumption to keep up with the hefty hardware requirements to run applications. "AI chips repres Read more…

US Senators Propose $32 Billion in Annual AI Spending, but Critics Remain Unconvinced

July 5, 2024

Senate leader, Chuck Schumer, and three colleagues want the US government to spend at least $32 billion annually by 2026 for non-defense related AI systems.  T Read more…

Point and Click HPC: High-Performance Desktops

July 3, 2024

Recently, an interesting paper appeared on Arvix called Use Cases for High-Performance Research Desktops. To be clear, the term desktop in this context does not Read more…

IonQ Plots Path to Commercial (Quantum) Advantage

July 2, 2024

IonQ, the trapped ion quantum computing specialist, delivered a progress report last week firming up 2024/25 product goals and reviewing its technology roadmap. Read more…

Shutterstock_1687123447

Nvidia Economics: Make $5-$7 for Every $1 Spent on GPUs

June 30, 2024

Nvidia is saying that companies could make $5 to $7 for every $1 invested in GPUs over a four-year period. Customers are investing billions in new Nvidia hardwa Read more…

Atos Outlines Plans to Get Acquired, and a Path Forward

May 21, 2024

Atos – via its subsidiary Eviden – is the second major supercomputer maker outside of HPE, while others have largely dropped out. The lack of integrators and Atos' financial turmoil have the HPC market worried. If Atos goes under, HPE will be the only major option for building large-scale systems. Read more…

Everyone Except Nvidia Forms Ultra Accelerator Link (UALink) Consortium

May 30, 2024

Consider the GPU. An island of SIMD greatness that makes light work of matrix math. Originally designed to rapidly paint dots on a computer monitor, it was then Read more…

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…

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…

Shutterstock_1687123447

Nvidia Economics: Make $5-$7 for Every $1 Spent on GPUs

June 30, 2024

Nvidia is saying that companies could make $5 to $7 for every $1 invested in GPUs over a four-year period. Customers are investing billions in new Nvidia hardwa Read more…

Nvidia Shipped 3.76 Million Data-center GPUs in 2023, According to Study

June 10, 2024

Nvidia had an explosive 2023 in data-center GPU shipments, which totaled roughly 3.76 million units, according to a study conducted by semiconductor analyst fir Read more…

Some Reasons Why Aurora Didn’t Take First Place in the Top500 List

May 15, 2024

The makers of the Aurora supercomputer, which is housed at the Argonne National Laboratory, gave some reasons why the system didn't make the top spot on the Top 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…

Leading Solution Providers

Contributors

AMD Clears Up Messy GPU Roadmap, Upgrades Chips Annually

June 3, 2024

In the world of AI, there's a desperate search for an alternative to Nvidia's GPUs, and AMD is stepping up to the plate. AMD detailed its updated GPU roadmap, w Read more…

Intel’s Next-gen Falcon Shores Coming Out in Late 2025 

April 30, 2024

It's a long wait for customers hanging on for Intel's next-generation GPU, Falcon Shores, which will be released in late 2025.  "Then we have a rich, a very Read more…

Google Announces Sixth-generation AI Chip, a TPU Called Trillium

May 17, 2024

On Tuesday May 14th, Google announced its sixth-generation TPU (tensor processing unit) called Trillium.  The chip, essentially a TPU v6, is the company's l 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…

IonQ Plots Path to Commercial (Quantum) Advantage

July 2, 2024

IonQ, the trapped ion quantum computing specialist, delivered a progress report last week firming up 2024/25 product goals and reviewing its technology roadmap. Read more…

The NASA Black Hole Plunge

May 7, 2024

We have all thought about it. No one has done it, but now, thanks to HPC, we see what it looks like. Hold on to your feet because NASA has released videos of wh 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…

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…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire