IBM Dials Up Density for HPC and Hyperscale

By Nicole Hemsoth

September 11, 2013

IBM is casting an ever-widening net to cover a broader range of workloads starting with today’s announcement of its NextScale system, which is designed to use a stripped-down x86 lure to reel in everything from the cloudy heights to high performance computing.

That lure is surprisingly simple–and all by design. Server buyers on all sides of the compute spectrum are being pulled into the swift current of stripped-down, purpose-driven and cost-conscious hardware. IBM has remained one of the few that continued to swim upstream of this raw-box approach–but it’s catching up–and throwing some performance awareness into the mix.

Adding to their x86 drive, the star of NextScale is the Ivy Bridge processor (one or two) which are nestled within a half-width NextScale nX360 server. These snap snugly into the host n1200 enclosure (a 6U, 12-bay chassis) that can double up to host 84 of these pared-down boxes—or 2,016 cores–in a standard 19-inchrack.

And “standard rack” is the key word here, at least for those who bit the iDataPlex line but were scared off by the strange manipulations of space and time necessary to maneuver around its (useful but) non-standard design. In other words, IBM has taken a “best of all worlds” approach with the NextScale system, pulling the MVP features from iDataPlex and Flex alike to create something that might be able to go head-to-head with the wave of hyperscale (and hypercheap) solutions that are flooding the market.

This new server strain puts IBM in a much larger petri dish with competitive offerings from HP (namely the SL6500 series and the half-width SL390S) as well as similar lines from Dell (the C8000 series, in particular). But the difference here, says System X Product Manager, Gaurav Chaudhry , is that they’re able to offer integration with some of IBM’s key initiatives and products, including their recently acquired workload management tools from Platform Computing, full GPFS support and for the cloudy side, ready-made APIs and binaries for xCAT which, while free to begin with, is being actively supported by IBM.

Dubbed the “economical addition to the System X family” IBM says that this approach offers the density, performance and flexibility to support the diverse targeted workloads. For the HPC crowd, there are certainly some features worth noting—but generally speaking, this is a pared-down approach that lets users build what they need at a price point that’s relative to other bare-bones boxes from competitors. But there are still some things that are off in the future—enough so that we might not see many of these finding their way into the Top 500 before next ISC.

The NextScale announcement is really about possibility and the future, at least for HPC buyers. So far, this is an Intel-only offering, with support for GPUs and Xeon Phi coming in early 2014. While there were no timeframes stated for other additions, including Power, ARM or other processors, it stands to reason that IBM wouldn’t want to be left behind as others march to the beat of customer demand.

With that said, to snap in spicy elements like GPUs or Phi means a need for more sophisticated cooling. One notable missing element with NextScale is the direct water cooling. The version announced today is air-cooled with the possibility of passive water cooling. Chaudhry says that direct water is coming right in line with other acceleration/co-processor capabilities.

That omission aside, there are some other notable elements that will appeal to the HPC set. For instance, IBM will offer well-rounded support for Infiniband, including FDR and QDR. There is no integrated I/O or switching, no chassis-level management, and the attractive part of iDataPlex, namely its front access capabilities to almost all components, was carried over.

For the cloud and general datacenter users, there will be two standard gigabit Ethernet ports, although they’ll be glad to sell additional capability to add 10GbE as an option as well. While HPC is all about the IOPS, latency and general performance, Chadhury says that the cloud customers simply want to get up and running as soon as possible—it’s all about time to delivery, he says

As IBM’s David Watts noted of the new nx360 server addition:

The IBM NeXtScale nx360 M4 compute node contains only the essential components in the base architecture…

  • 1 or 2 Intel Xeon E5-2600 v2 series processors
  • Up to 8 ECC DIMMs operating up to 1866 MHz providing a total memory capacity of up to 128 GB
  • 2 on-board 1Gb Ethernet ports
  • Integrated management with the IMM2 supporting IPMI and UEFI industry standards
  • PCI Express 3.0 I/O expansion capabilities through a 16x riser cage
  • Additional mezzanine slot for FDR InfiniBand or 10Gb Ethernet without consuming a PCIe slot

IBM  took their cues from the positive responses around offering front accessibility (as with the iDataPlex systems) and carried that over to NextScale. Chaudhry freely admits that while iDataPlex was made for its own configuration and offered little flexibility, the idea with NextScale was to “keep all the things we liked and get rid of other things, like the full-width server versus this 8.5 inch wide but deep (versus shallow) approach.”

On that “best of all worlds” note touched on earlier, Chaudhry highlights the difference between the Flex versus NextScalelines s in the increased ability to go as “vanity-free” as one wishes. “So say if a customer isn’t looking for the integrated switching built into the chassis, they have the flexibility to pick their own,”

The key concepts behind this launch are around flexibility, simplicity and scale—in short, a move away from the tricky design and implementation details of their iDataPlex but with more room to grow than Flex might offer for some users. IBM Product Marketing Manager for the System X line, Gaurav Chaudhry says that this isn’t the immediate end of the line for iDataPlex. It simply marks an evolution toward flexible systems that can meet the low latency, high performance, and I/O demands of HPC while remaining lightweight and simple enough for cloud users to hop into without a great deal of effort. The company still has a number of iDataPlex systems to support, which will continue for at least 18 months, but the hyperscale, low-cost NextScale is the real battlefield for IBM’s push—and the shove will come down to price.

As a side note, it seems a shame that the Flex line was named “Flex” versus NextScale—seems the true meaning of these are flip-flopped, with the Flexes emphasizing scalability and NextScale pushing flexibility.

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!

The New MLPerf Storage Benchmark Runs Without ML Accelerators

October 3, 2024

MLCommons is known for its independent Machine Learning (ML) benchmarks.  These benchmarks have focused on mathematical ML operations and accelerators (e.g., Nvidia GPUs). Recently, MLCommons introduced the results of i Read more…

DataPelago Unveils Universal Engine to Unite Big Data, Advanced Analytics, HPC, and AI Workloads

October 3, 2024

DataPelago today emerged from stealth with a new virtualization layer that it says will allow users to move AI, data analytics, and ETL workloads to whatever physical processor they want, without making code changes, the Read more…

IBM Quantum Summit Evolves into Developer Conference

October 2, 2024

Instead of its usual quantum summit this year, IBM will hold its first IBM Quantum Developer Conference which the company is calling, “an exclusive, first-of-its-kind.” It’s planned as an in-person conference at th Read more…

Stayin’ Alive: Intel’s Falcon Shores GPU Will Survive Restructuring

October 2, 2024

Intel's upcoming Falcon Shores GPU will survive the brutal cost-cutting measures as part of its "next phase of transformation." An Intel spokeswoman confirmed that the company will release Falcon Shores as a GPU. The com Read more…

Texas A&M HPRC at PEARC24: Building the National CI Workforce

October 1, 2024

Texas A&M High-Performance Research Computing (HPRC) significantly contributed to the PEARC24 (Practice & Experience in Advanced Research Computing 2024) conference. Eleven HPRC and ACES’ (Accelerating Computin Read more…

A Q&A with Quantum Systems Accelerator Director Bert de Jong

September 30, 2024

Quantum technologies may still be in development, but these systems are evolving rapidly and existing prototypes are already making a big impact on science and industry. One of the major hubs of quantum R&D is the Q Read more…

The New MLPerf Storage Benchmark Runs Without ML Accelerators

October 3, 2024

MLCommons is known for its independent Machine Learning (ML) benchmarks.  These benchmarks have focused on mathematical ML operations and accelerators (e.g., N Read more…

DataPelago Unveils Universal Engine to Unite Big Data, Advanced Analytics, HPC, and AI Workloads

October 3, 2024

DataPelago today emerged from stealth with a new virtualization layer that it says will allow users to move AI, data analytics, and ETL workloads to whatever ph Read more…

Stayin’ Alive: Intel’s Falcon Shores GPU Will Survive Restructuring

October 2, 2024

Intel's upcoming Falcon Shores GPU will survive the brutal cost-cutting measures as part of its "next phase of transformation." An Intel spokeswoman confirmed t Read more…

How GenAI Will Impact Jobs In the Real World

September 30, 2024

There’s been a lot of fear, uncertainty, and doubt (FUD) about the potential for generative AI to take people’s jobs. The capability of large language model Read more…

IBM and NASA Launch Open-Source AI Model for Advanced Climate and Weather Research

September 25, 2024

IBM and NASA have developed a new AI foundation model for a wide range of climate and weather applications, with contributions from the Department of Energy’s Read more…

Intel Customizing Granite Rapids Server Chips for Nvidia GPUs

September 25, 2024

Intel is now customizing its latest Xeon 6 server chips for use with Nvidia's GPUs that dominate the AI landscape. The chipmaker's new Xeon 6 chips, also called Read more…

Building the Quantum Economy — Chicago Style

September 24, 2024

Will there be regional winner in the global quantum economy sweepstakes? With visions of Silicon Valley’s iconic success in electronics and Boston/Cambridge� Read more…

How GPUs Are Embedded in the HPC Landscape

September 23, 2024

Grasping the basics of Graphics Processing Unit (GPU) architecture is crucial for understanding how these powerful processors function, particularly in high-per Read more…

Shutterstock_2176157037

Intel’s Falcon Shores Future Looks Bleak as It Concedes AI Training to GPU Rivals

September 17, 2024

Intel's Falcon Shores future looks bleak as it concedes AI training to GPU rivals On Monday, Intel sent a letter to employees detailing its comeback plan after 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…

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…

Granite Rapids HPC Benchmarks: I’m Thinking Intel Is Back (Updated)

September 25, 2024

Waiting is the hardest part. In the fall of 2023, HPCwire wrote about the new diverging Xeon processor strategy from Intel. Instead of a on-size-fits all approa Read more…

Ansys Fluent® Adds AMD Instinct™ MI200 and MI300 Acceleration to Power CFD Simulations

September 23, 2024

Ansys Fluent® is well-known in the commercial computational fluid dynamics (CFD) space and is praised for its versatility as a general-purpose solver. Its impr 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…

Shutterstock 1024337068

Researchers Benchmark Nvidia’s GH200 Supercomputing Chips

September 4, 2024

Nvidia is putting its GH200 chips in European supercomputers, and researchers are getting their hands on those systems and releasing research papers with perfor 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…

Leading Solution Providers

Contributors

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…

Quantum and AI: Navigating the Resource Challenge

September 18, 2024

Rapid advancements in quantum computing are bringing a new era of technological possibilities. However, as quantum technology progresses, there are growing conc Read more…

IBM Develops New Quantum Benchmarking Tool — Benchpress

September 26, 2024

Benchmarking is an important topic in quantum computing. There’s consensus it’s needed but opinions vary widely on how to go about it. Last week, IBM introd Read more…

Google’s DataGemma Tackles AI Hallucination

September 18, 2024

The rapid evolution of large language models (LLMs) has fueled significant advancement in AI, enabling these systems to analyze text, generate summaries, sugges Read more…

Microsoft, Quantinuum Use Hybrid Workflow to Simulate Catalyst

September 13, 2024

Microsoft and Quantinuum reported the ability to create 12 logical qubits on Quantinuum's H2 trapped ion system this week and also reported using two logical qu 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…

Intel Customizing Granite Rapids Server Chips for Nvidia GPUs

September 25, 2024

Intel is now customizing its latest Xeon 6 server chips for use with Nvidia's GPUs that dominate the AI landscape. The chipmaker's new Xeon 6 chips, also called Read more…

US Implements Controls on Quantum Computing and other Technologies

September 27, 2024

Yesterday the Commerce Department announced  export controls on quantum computing technologies as well as new controls for advanced semiconductors and additiv Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire