New Dimensions in HPC

By Tabor Research

April 29, 2008

Within the computing industry, the traditional High Productivity Computing (tHPC) market has acted and continues to act as a generative edge for new technologies and applications. This market area has traditionally been the point where users are pushing advances in system performance and architectures to address problems that range from standard engineering simulations to problems that have hitherto been intractable. In addition, tHPC has acted as a test bed for the IT industry as a whole, where new concepts and technologies are developed and proven and then introduced into larger mainstream markets.

Tabor Research believes that new technologies, methodologies and applications are emerging outside of the traditional HPC market that have the essential characteristics of high productivity computing (requirements for leading edge capabilities, incorporating, testing, and perfecting of new technologies and methodologies, and market creation and expansion.) This new area, which we cleverly call Edge HPC (or eHPC), leverages the experience and technology of the Traditional HPC market, while introducing new areas for innovation. Most importantly we believe that eHPC is at the cusp of significant market generation and growth.

eHPC Drivers

Factors driving the Edge HPC market include:

  • Data source explosion – Over the last decade several technologies for acquiring and entering data directly into computer networks have become ubiquitous. For example, internet access allows anyone with a PC to become a data entry source; barcode scanners can provide detailed information on product sales and movement, RFID provides the capability to automatically gather data on the location and movement of anything with a tag; GPS systems actively generate location data which can be stored and transferred, and so on. This list is being expanded as new technologies come on line.
  • Processing new data types – The information technology industry has been built around the processing of four basic data types – integer number, floating point number, strings, and logical values. In the final analysis, the entire industry and the trillions of dollars of revenue it has generated is based on our ability to manipulate these four abstracts. Over the last few decades new media data types (e.g., images, audio streams, video streams) have entered and helped to propel the market. However with the exception of some filtering and “photo shop” type processing on images, these new data types have largely been treated as basic large objects (BLOBs) which are only read and written with other data types linked to the BLOB for processing purposes, e.g., searching, sorting, etc. As additional processing techniques continue to evolve we expect that the expanded ability to manipulate these data types will lead to new applications and green field market opportunities.
  • Merging of communications and computing – Computing and communications have been connected since the development of the first I/O device. Over time the balance between computational and communications functions associated with computers has steadily shifted towards the communications side. This shift saw major inflection points during the introduction of the World Wide Web and the move to high-bandwidth internet services. This shift combined with continuing increases in the performance and ubiquity of computing/communications networks has created classes of applications ranging from virtualized economies (e.g., eBay), to new social structures (e.g., Facebook, MySpace), to new forms of mass entertainment (i.e. on-line gaming), and so on.
  • Complex event architectures – New data sources and faster data communications have combined to enable a new generation of complex event driven applications. These applications accept streaming data from multiple independent sources which are driven by real world events. Data can be generated at irregular intervals, with varying volumes and from geographically dispersed sources. Applications must respond to the incoming data in near-real time. Responses can range from recording data in step with streaming rates, to evaluating system conditions and issuing warning reports and/or system control commands, to recalibrating/reanalyzing external system conditions. In addition to the communications based applications mentioned above, near-real time applications can take the form of in-flight product distributions and logistics, financial tracking, analysis, and trading, national security threat analysis and warning systems, and so on.

None of these factors are new or have gone unnoticed. However, they have combined to create new sets of computational/data and visualization requirements that can be addressed by high productivity computing technologies. Tabor Research believes that a significant “Edge HPC” market currently exists and that this market has strong growth potential over the next five plus years.

High Productivity Computing Definition

Tabor Research defines HPC as the use of servers, clusters, supercomputers, and networked systems – plus associated software, tools, components, storage, and services – for tasks that are particularly intensive in computation, analysis, memory usage, or data management. Within industry, HPC can frequently be distinguished from general business computing in that companies generally will use HPC applications to gain advantage in their core endeavors – e.g., finding oil, designing automobile parts, or protecting clients’ investments – as opposed to non-core endeavors, such as payroll management or resource planning. 

At the highest level, Tabor Research divides the HPC market into “Traditional HPC” and “Edge HPC” segments, as follows:

  • Traditional HPC – HPC systems used by scientists and engineers in research, development, and production across industry, government, and academia.
  • Edge HPC – HPC systems used to address applications that have essential “high productivity computing” characteristics but which lie outside the traditional bounds of scientific and engineering computing. Characteristics of this class of applications include (but are not limited to):

o  requirements for leading edge systems performance, or ability to address the most demanding problems.
o  requirements for ultra or extreme levels of scalability.
o  tendency to incorporate, test, and perfect new technologies and methodologies.
o  associated with market creation and expansion.

Classifying Edge HPC Applications

The eHPC market represents a diverse set of users with application requirements for high productivity solutions. These requirements can range from relatively straightforward extensions of traditional HPC applications or workflows into new fields to more abstract requirements for system architectural innovations and/or highly specialization systems configurations or infrastructures. Given this diversity of top level requirements, we believe that the market is best segmented based on the physical and/or logical features that define and drive the applications.

Tabor thus divides the Edge HPC market into four major segments: Complex Event and Business Processing, Process Optimization, Virtual Infrastructure and Environments, and Ultra-scale Computing.

Complex Event Processing

Complex event processing (CEP) applications are driven by continuous data feeds generated by real world events such as: electronic trading on stock markets, security monitoring systems, sensor based inventory tracking systems, and so on. Data may be streamed into the system from multiple independent sources, and data may dramatically decrease in value over time. Data volumes can vary significantly from moment to moment. CEP solutions often involve networks of: sensors, multiple communicating servers, and control devices. Applications operate in near real-time, with events initiated from real world occurrence often setting off a chain of response and control events throughout the system network.

CEP applications fall into the eHPC realm when:

  • Requirements to maintain low response latencies in the face of growing data volumes exceed the capabilities of standard systems.
  • eHPC system capabilities allow for the expansion of CEP based applications into new market domains.
  • System scale requirements exceed the capabilities of standard systems.

Tables 1 provides examples of CEP domains and applications.

Table 1
Examples of Complex Event Processing Applications

Domain Applications Type
Civil Infrastructure/Utilities  Delivery network monitoring
  Pipeline monitoring
Computer Systems Intrusion detection
  Network monitoring
Financial Services Event alert
  Market pricing
  Digital trading
General Business Environmental monitoring
  In store monitoring
  Real time supply chain
Health Informatics Disease tracking
  Patient monitoring
Military Operations Battlefield monitoring
  Shared battle space awareness
  Target detection
National/Civil Security Environmental monitoring
  Signal intelligence
  Area surveillance
Telecom Network traffic routing
Transportation “In-flight” asset tracking

Process Optimization

The Process Optimization (PO) application profiles mirror traditional HPC workflows. These applications make use of technology above and beyond standard enterprise solutions, either in architecture, software, or system management. PO applications have one or more of the following properties:

  • Data intensive – The majority of the applications’ time may be spent streaming data from disk to memory to processor and back to disk for database centric applications, or from data source to processor to disk for event centric applications. In addition, both data transfers and total database volumes may be significantly larger that those found in common business applications.
  • Computationally intensive – The majority of the applications’ time may be spent performing arithmetic or logical operations in such areas as: statistical analysis and modeling, process simulations, pattern matching, and so on.
  • Operational time processing – Applications are operating in synchronization with the operational timing of the organization.

Table 2 presents a list of example applications and domains that we see as fitting into the Process Optimization segment at this time.

Table 2
Examples of Process Optimization Applications

Domain Applications Type
Military Operations “Sense and Respond” logistics
Business Intelligence Data mining, database search
Civil Infrastructure/Utilities Anomaly management
Computer Systems Anomaly management
Financial Services Capital budgeting
  Combinatorial auctions
  Derivatives pricing
  Legal compliance
General Business Distribution resource planning
  Facility location planning
  Resource scheduling
  Vehicle routing
Military Operations Asset tracking
  Distribution resource planning
  Facility location planning
  Spares management
National/Civil Security Seismic activity monitoring
  Weapons and delivery systems planning
Telecom Anomaly management
Transportation Real time route planning/rerouting
Other Complex text and image matching
  Text classification and filtering

Virtual Infrastructure and Environments

Virtual Infrastructure and Environments (VIE) applications implement computer network based business and social structures. They also hold the promise of extending these structures through synthetic realities ala Second Life . These structures range from on-line gaming environments, to multi-person/system training environments, to virtual economies, to virtual social environments. The applications fall into the eHPC market based on:

  • Requirements for real time or near real time response rates.
  • High productivity computing requirements to address continually expanding message rates and data volumes.
  • The ability to expand the VIE application domain based on advances in computer system capabilities.

Table 3 provides a list of example VIE domains and applications.

Table 3
Examples of Infrastructure and Environments Applications

Domain Applications Type
Virtual Civil Infrastructure Internet commerce
Consumer products On-line gaming
  Social networks
B to B and B to C Virtual economies
B to B Virtual offices

Ultra-Scale

One eHPC feature that appears across multiple application spaces is the requirement for “Ultra-scale Computing capabilities.” Ultra-scale computing systems are specially designed and/or configured to effectively manage node counts that significantly exceed those provided by industry standard products.

Currently ultra-scale applications generally appear as service layers to the internet. The primary example of this application is internet search engines. Applications can be both data intensive (e.g., map and satellite photo applications) and/or compute intensive (e.g., search applications). This segment is currently represented by a small number of very large sites.

Table 4 provides a list of example Ultra-scale domains and applications.

Table 4
Examples of Ultra-scale Applications

Domain Applications Type
Internet data processing Data aggregation
  Data dissemination
  Search
Other Other

Conclusions

Tabor Research believes that over the last few years a number of technology and market factors have combined to create new market opportunities outside the boundaries of the traditional HPC market. We believe this “Edge HPC” market is currently generating significant revenues and has strong growth potential. Over time, we expect it to exceed the tHPC market due to the scope of domains it will impact.

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!

Hyperion: AI-driven HPC Industry Continues to Push Growth Projections

November 21, 2019

Three major forces – AI, cloud and exascale – are combining to raise the HPC industry to heights exceeding expectations. According to market study results released this week by Hyperion Research at SC19 in Denver, Read more…

By Doug Black

At SC19: Bespoke Supercomputing for Climate and Weather

November 20, 2019

Weather and climate applications are some of the most important uses of HPC – a good model can save lives, as well as billions of dollars. But many weather and climate models struggle to run efficiently in their HPC en Read more…

By Oliver Peckham

Microsoft, Nvidia Launch Cloud HPC Service

November 20, 2019

Nvidia and Microsoft have joined forces to offer a cloud HPC capability based on the GPU vendor’s V100 Tensor Core chips linked via an InfiniBand network scaling up to 800 graphics processors. The partners announced Read more…

By George Leopold

Hazra Retiring from Intel Data Center Group, Successor Not Known

November 20, 2019

Rajeeb Hazra, corporate VP of Intel’s Data Center Group and GM for the Enterprise and Government Group, is retiring after more than 24 years at the company. At this writing, his successor is unknown. An earlier story on... Read more…

By Doug Black

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-accelerated computing. In recent years, AI has joined the s Read more…

By John Russell

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

Data Management – The Key to a Successful AI Project

 

Five characteristics of an awesome AI data infrastructure

[Attend the IBM LSF & HPC User Group Meeting at SC19 in Denver on November 19!]

AI is powered by data

While neural networks seem to get all the glory, data is the unsung hero of AI projects – data lies at the heart of everything from model training to tuning to selection to validation. Read more…

SC19 Student Cluster Competition: Know Your Teams

November 19, 2019

I’m typing this live from Denver, the location of the 2019 Student Cluster Competition… and, oh yeah, the annual SC conference too. The attendance this year should be north of 13,000 people, with the majority attende Read more…

By Dan Olds

Hyperion: AI-driven HPC Industry Continues to Push Growth Projections

November 21, 2019

Three major forces – AI, cloud and exascale – are combining to raise the HPC industry to heights exceeding expectations. According to market study results r Read more…

By Doug Black

At SC19: Bespoke Supercomputing for Climate and Weather

November 20, 2019

Weather and climate applications are some of the most important uses of HPC – a good model can save lives, as well as billions of dollars. But many weather an Read more…

By Oliver Peckham

Hazra Retiring from Intel Data Center Group, Successor Not Known

November 20, 2019

Rajeeb Hazra, corporate VP of Intel’s Data Center Group and GM for the Enterprise and Government Group, is retiring after more than 24 years at the company. At this writing, his successor is unknown. An earlier story on... Read more…

By Doug Black

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

Top500: US Maintains Performance Lead; Arm Tops Green500

November 18, 2019

The 54th Top500, revealed today at SC19, is a familiar list: the U.S. Summit (ORNL) and Sierra (LLNL) machines, offering 148.6 and 94.6 petaflops respectively, Read more…

By Tiffany Trader

ScaleMatrix and Nvidia Launch ‘Deploy Anywhere’ DGX HPC and AI in a Controlled Enclosure

November 18, 2019

HPC and AI in a phone booth: ScaleMatrix and Nvidia announced today at the SC19 conference in Denver a joint offering that puts up to 13 petaflops of Nvidia DGX Read more…

By Doug Black

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

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

Supercomputer-Powered AI Tackles a Key Fusion Energy Challenge

August 7, 2019

Fusion energy is the Holy Grail of the energy world: low-radioactivity, low-waste, zero-carbon, high-output nuclear power that can run on hydrogen or lithium. T Read more…

By Oliver Peckham

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

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

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

AMD Launches Epyc Rome, First 7nm CPU

August 8, 2019

From a gala event at the Palace of Fine Arts in San Francisco yesterday (Aug. 7), AMD launched its second-generation Epyc Rome x86 chips, based on its 7nm proce Read more…

By Tiffany Trader

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

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

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

Leading Solution Providers

ISC 2019 Virtual Booth Video Tour

CRAY
CRAY
DDN
DDN
DELL EMC
DELL EMC
GOOGLE
GOOGLE
ONE STOP SYSTEMS
ONE STOP SYSTEMS
PANASAS
PANASAS
VERNE GLOBAL
VERNE GLOBAL

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

Intel Confirms Retreat on Omni-Path

August 1, 2019

Intel Corp.’s plans to make a big splash in the network fabric market for linking HPC and other workloads has apparently belly-flopped. The chipmaker confirmed to us the outlines of an earlier report by the website CRN that it has jettisoned plans for a second-generation version of its Omni-Path interconnect... Read more…

By Staff report

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

Rise of NIH’s Biowulf Mirrors the Rise of Computational Biology

July 29, 2019

The story of NIH’s supercomputer Biowulf is fascinating, important, and in many ways representative of the transformation of life sciences and biomedical res Read more…

By John Russell

Xilinx vs. Intel: FPGA Market Leaders Launch Server Accelerator Cards

August 6, 2019

The two FPGA market leaders, Intel and Xilinx, both announced new accelerator cards this week designed to handle specialized, compute-intensive workloads and un Read more…

By Doug Black

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

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

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