Since 1986 - Covering the Fastest Computers
in the World and the People Who Run Them
Visit additional Tabor Communication Publications
August 18, 2010
AMD Still Playing Catchup in GPU Computing Race
AMD's acquisition of ATI in 2006, by chance or by design, coincided with the meteoric rise of general-purpose GPU (GPGPU) computing, especially in HPC. As AMD struggled to bring the two entities under one roof, NVIDIA, undistracted by a merger, was able to capture the GPGPU high ground and has never looked back.
But AMD is still in the hunt. To counter NVIDIA's latest Fermi GPUs, AMD is about to release its new FireStream cards, which match the Fermis in overall performance, if not capability. In a nutshell, both of the chipmakers' hardware now offer about a half a teraflop (double precision) per chip. But that's mostly where the comparison ends. NVIDIA hardware has the advantage in of ECC memory support, local cache, asynchronous transfers, and a generally more sophisticated architecture geared for general purpose computing. AMD's offerings have the advantage of better performance per watt, at least for the 150 watt FireStream 9350 product.
NVIDIA also has big advantage in its CUDA programming environment, which has become the premier software platform for GPGPU development. AMD, on the other hand, is sticking with the open standard OpenCL, which is generally considered less capable and certainly much less mature than CUDA.
A recent article penned by Lawrence Latif of The Inquirer this week does a nice job of matching up the GPGPU competition and he makes a particularly interesting point about CUDA's long-term prospects:
CUDA might not be open, or even a standard, but history tells us that such technicalities never stopped other languages from attaining widespread popularity. Being policed by IBM didn't stop Fortran from still being the numerical language, half a century after it first appeared. Even with Sun Microsystems' best efforts to create a cumbersome 'framework' and employ licensing peculiarities, Java's popularity has managed to surpass C. It has happened before and it's looking like history will repeat itself.
Much of the rest of Latif's report is based on conversations with NVIDIA's Tesla product line manager Sumit Gupta and AMD's director of stream computing Patricia Harrell. And while there's certainly a lot of he-said-she-said in the text, the whole article is quite illuminating and worth reading in its entirety.
Full story at The Inquirer
Discussion
There are 0 discussion items posted.
|
Join the Discussion |
Sponsored Links
Accelerate your computational research and engineering applications with Exxact’s Tesla K20 GPU workstations and servers, maximized for supercomputing professionals.
- Unified profiling and debugging lowers costs and boosts productivity
- White Paper: Building a Data-Intensive Cluster Supercomputer
- Enterprise HPC software platforms engineering & software acceleration services
- Unmasking the Concealed Costs & Challenges of Open Source Tools
- PGI 2013: OpenMP 1.5X faster than GCC, new GNU-compatible OpenACC C++ compiler, CUDA 5 and Tesla K20 support, and more.
- Revolution R Enterprise Delivers Big Data Predictive Analytics
- PGI 2013: Industry-leading Performance, OpenACC and More
- Progress in Parallel: the Bull Parallel Programming Center
- The Cray CS300™ – Flexibility. Performance. Manageability. Results.
- TotalView release supports Intel® Xeon Phi™ coprocessor and more
RSS Feeds
Feeds by Topic
- Applications
- Developer Tools
- Interconnects
- Middleware
- Networks
- Processors
- Storage
- Systems
- Visualization
Feeds by Industry
Feeds by Content Type
- Features
- Blogs
- Short Takes
- Off the Wire
- Whitepapers
- Multimedia
- HPC Soundbite Podcasts
- HPCwire Job Bank
Subscribe to All Content
June 18, 2013
- AMD Unveils Server Strategy and Roadmap
- 2013 International Supercomputing Conference Opens in Leipzig
- HPC Advisory Council Announces 2nd Annual Spain Supercomputing Conference
- EADS Announces 'Join the Spirit' Award Winners
- AMAX ClusterMax Cluster and ServMax Server Solutions Updated
- IDC Announces New Winners of HPC Innovation Excellence Awards
- Xyratex Enhances ClusterStor Operating System, Unlocks More Value for Scale-Out HPC Storage
- Researchers Deploy GPUs to Build World's Largest Artificial Neural Network
- Cray Launches Complete Lustre Storage Solution Across HPC and Big Data Computing Markets
- Azul Systems and Solarflare Partner to Eliminate Java Application Jitter for Capital Markets
- Mellanox Technologies Names Board Chairman
June 17, 2013
- Cirrascale Announces Expanded Support for Intel Xeon Phi Coprocessor Product Family
- AMD's SeaMicro SM15000 Powers Rubicon Project
- World Premiere for Turbocharged Data Speed
- Mellanox's FDR InfiniBand Solution with NVIDIA GPUDirect RDMA Technology Provides Superior Performance
- Purdue Builds Nation's Fastest Campus Supercomputer - Again
- Colfax Announces New Line of Servers and Workstations Supporting Intel Xeon Phi Coprocessors
- Cray CS300 Cluster Supercomputers to Feature New Intel Xeon Phi Coprocessors x100 Family
- Intel Powers the World's Fastest Supercomputer, Reveals HPC Technologies
- Supermicro Announces Support for New Intel Xeon Phi x100 Product Family
- IDT RapidIO 20 Gbps-Per-Port Switches Provide High Performance Interconnect for Supercomputer
- Colorado State University Engineering Professors Receive Award to Design Green Supercomputers
- IDC Market Study Shows Strong Gains for Co-Processors and Big Data at HPC Sites
- Altair's PBS Professional Deployed on Cray XC30 Supercomputer at JAIST
- Mellanox FDR 56Gb/s InfiniBand Solutions Deliver Leading Application Performance and Scalability
- MilkyWay-2 Wins #1 Supercomputer in the World According to Top500.org
- Acceleware Showcases High Performance Optimization Techniques at ISC'13
- Penguin Computing, Calxeda, and Inktank Partner to Deliver Large-Scale Storage on ARM-based Servers
- SGI and DoD Launch Supercomputer Spirit, the Fastest System in the Department
- Mellanox Demonstrates World's First InfiniBand Connectivity With NVIDIA Tegra ARM Processor
- e2v Adds the P2041 and P3041 Quad-Core Processors to its Portfolio of QorIQ Products
- Adaptive Computing to Manage Computing Workloads for HPC
- Xyratex to Showcase New HPC Storage Offerings and Value at ISC'13
- NAG Showcases New Parallelized Numerical Solvers at ISC'13
- Tabor Communications and EMI Partner to Publish HPCwire Japan
June 14, 2013
- Samplify APAX Storage Library Accelerates Disk Throughput and Expands Storage Capacity
- Silicon Mechanics Announces Availability of Seagate Constellation ES.3 Hard Drive
- ESI Opens Offices on the Ter@tec Campus Dedicated to Simulation and High Performance Computing
June 13, 2013
- Ace Computers' Massive Military Build Shows Custom Computers Reign
- Worldwide High Performance Computing 2012 Total Market Model and 2013-17 Forecast
- ISC Big Data and Cloud Newsletter
- Silicon Mechanics Partners with Acellera on Biomolecular Simulation Hardware-Software Appliance
- Army Supercomputing Center Signals Growth in Soldier Protection Solutions
- OpenSFS to Highlight Lustre in New Markets at ISC13 by Hosting Participatory Community Events
- HPCAC and ISC to Showcase HPC Coders and Cluster Administrators
- Cray Launches New Hadoop Solution on Cray CS300 Line of Cluster Supercomputers
- AMD's SeaMicro Servers Accelerate Biomolecular Research to Provide HPC
- Lawrence Livermore's Vulcan Available for Collaborations With Industry and Academia
- Acceleware Releases AxRTM 6.0
June 12, 2013
- BSC Building First Supercomputer to Combine ARM CPUs, GPU Accelerators, and InfiniBand
- First Open Source Release of E-iRODS Announced by RENCI
- Cycle Computing CEO to Speak on Utility HPC at Cloud Slam and LiveStream Event
- NAG Library for Intel Xeon Phi Launches at ISC13
- NAG HPC Applications Performance and Scalability Expertise Acknowledged
- Titan Completes Acceptance Testing
- Silicon Mechanics Announces Intel SSD Data Center S3500 Series High Performance Hard Disk Drives
- Bright Cluster Manager 6.1 Delivers Full Support for the Intel Xeon Phi and Amazon VPC
- RAID Launches Ultra-Dense, High Performance 4U 60-Bay Dual Server Node Solution
- Adaptive Computing Launches Workload Optimization Pack for Cluster Platforms
- IBM Expands Support for Linux on Power Systems Servers
- TotalView Offers Debugging Support for Intel Xeon Phi Coprocessor
June 11, 2013
- Scalable Informatics siFlash Dominates STAC-M3 Benchmarks
- Netlist to Present the Advantages of HyperCloud Memory at IBM's Edge2013 Conference
- Panasas Launches High Performance File Transfer Software
- CoolIT Selected to Host Birds of a Feather Session at ISC13
- Calxeda and Inktank Team to Deliver Transformative Ceph-Based Storage Platform
- MEGWARE and Chemnitz University of Technology in International Battle for Supercomputing Title
- Ingram Micro's Artizen Portfolio Simplifies High Performance Solutions
- Intel Introducing New Lustre Solution
- Europe and US Exascale Thought Leaders to Join US DOE X-Stack Members at ISC
- Innodisk Exhibits at International SuperComputing 2013
- Asetek Showcases Latest Datacenter Efficiency Solutions at ISC
- UC San Diego Launches New Research Computing Program
- Tabor Communications Further Strengthens its Digital Marketing Strategy
- Solarflare to Speak at STAC Summits in Chicago, New York, and London
- Seneca Expands its Presence in the Digital Broadcast Market by Joining the Sports Video Group
June 10, 2013
- IBM Unveils Big Data, Cloud Enhancements Throughout Systems Portfolio
- Altera Announces Breakthrough Advantages with Generation 10 FPGAs and SoCs
- Supermicro Appoints StorIT As Value Added Distributor For MENA Region
- Beacon Shines for Intel Xeon Phi Coprocessor Developers With Allinea Tools
- Hack Reactor Programming Students Attempt World Record, Produce Supercomputer
- IIT-Madras Ties Up With IBM
- sTec Highlights Growth Strategy Progress
June 07, 2013
- Computational Models Highlight Bacterial Growth
- Governor, Massachusetts Life Sciences Center Announce Over $100 Million in Capital Grant Funding
June 06, 2013
- PRACE Scientific Conference 2013, Success Stories and Strategies
- Dell Introduces New Solutions Designed for Data-Intensive Workloads
- Vello Systems and Accton Strike OEM Agreement for OpenFlow-Based Network Equipment
- Inspur Supports Tsinghua and HUST Teams in Upcoming ISC'13
- Adaptive Computing Attributes Sales Velocity and Success to Act-On
June 05, 2013
- Temporal Cloaking Could Bring More Secure Optical Communications
- Translational Research Institute Implements SGI Super Computing Solutions
- Altair Finalizes Global Partnership with Fujitsu
- Texas Instruments Transforms the Economics of Small Cells
- Cirrascale Announces Support for 4th Generation Intel Core and Intel Xeon E3-1200 v3 Processors
- Leadtek Releases Entry-Level WinFast WS700 Equipped With Haswell
- AMAX Launches New Server Platforms
Most Read Features
- Details Emerge About China's 50+ Petaflop Chart-Topper
- Full Details Uncovered on Chinese Top Supercomputer
- Is China Set to Unveil Record-Shattering Supercomputer?
- "No Exascale for You!" An Interview with Berkeley Lab's Horst Simon
- Saddling Phi for TACC’s Stampede
- Supercomputing Vet Champions Quantum Cause
- Exascale Advocates Stand on Nuclear Stockpiles
- CERN, Google Drive Future of Global Science Initiatives
- Xyratex Targets Missing Middle with Scaled-Down ClusterStor 1500
- Blue Waters Seals Off with Tape
Most Read Around the Web
- Building Supercomputers with Raspberries
- Running Computational Fluid Dynamics in the Cloud
- Speaking Many Languages into the MIC
- HPC and the True Cost of Cloud
- Floating Funding to Exascale Island
- NASA Builds 'Climate in a Box'
- TACC's Hadoop Cluster Breaks New Ground
- GASPI Targets Exascale Programming Limits
- Computing the Physics of Bubbles
- World's Smallest Movie Has Big (Data) Implications
Most Read This Just In
- D-Wave Two Quantum Computer Selected for New AI Initiative
- Mines' Powerful New Supercomputer to Focus on Energy Research
- AMD Targets Server Performance with Open 3.0 Release
- Mellanox Technologies Ltd. Announces Definitive Agreement to Acquire Kotura, Inc.
- New IBM Center in Beijing to Speed Linux Applications on Power Systems
- Two Virginia Tech Teams Named Finalists in DARPA Spectrum Challenge
- Supermicro Announces X10 Server Building Blocks Supporting Intel Haswell Processors
- Ireland Sprouts Native Top Supercomputer List
- Kitware Develops Customizable Simulation Framework to Provide HPC for Mid-Sized Manufacturers
- Next HPC Installation Step Initiated at High Performance Computing Center Stuttgart
Feature Articles
My Supercomputer is Bigger Than Yours!
Contributing commentator, Andrew Jones, offers a break in the news cycle with an assessment of what the national "size matters" contest means for the U.S. and other nations...
Read more...
Alternatives Emerge as Linpack Loses Ground
Today at the International Supercomputing Conference in Leipzing, Germany, Jack Dongarra presented on a proposed benchmark that could carry a bit more weight than its older Linpack companion. The high performance conjugate gradient (HPCG) concept takes into account new architectures for new applications, while shedding the floating point....
Read more...
Intel Snaps New Grips to HPC Hook
Not content to let the Tianhe-2 announcement ride alone, Intel rolled out a series of announcements around its Knights Corner and Xeon Phi products--all of which are aimed at adding some options and variety for a wider base of potential users across the HPC spectrum. Today at the International Supercomputing Conference, the company's Raj....
Read more...
Sponsored Whitepapers
Best Practices in Big Data Storage
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
Progress in Parallel: the Bull Parallel Programming Center
04/15/2013 | Bull | “50% of HPC users say their largest jobs scale to 120 cores or less.” How about yours? Are your codes ready to take advantage of today’s and tomorrow’s ultra-parallel HPC systems? Download this White Paper by Analysts Intersect360 Research to see what Bull and Intel’s Center for Excellence in Parallel Programming can do for your codes.
Sponsored Multimedia
HPCwire Live! Atlanta's Big Data Kick Off Week Meets HPC
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?
Webinar: Mellanox Virtual Modular Switch, the Most Efficient 40GbE Aggregation Switch Solution
Join our webinar to learn how IT managers can migrate to a more resilient, flexible and scalable solution that grows with the data center. Mellanox VMS is future-proof, efficient and brings significant CAPEX and OPEX savings. The VMS is available today.
HPC Job Bank
Featured Events
- June 20, 2013
- June 21, 2013
CIO North America
Marina Del Rey, CA
United States
- June 24, 2013
- June 25, 2013
The Trading Show Chicago
Chicago, IL
United States
- June 24, 2013
- June 28, 2013
2013 Federated Conferences Week (FCW '13)
San Jose, CA
United States
- June 25, 2013
- June 26, 2013
TERATEC 2013 Forum
Paris,
France
- July 22, 2013
- July 25, 2013
XSEDE13: Gateway to Discovery
San Diego, CA
United States
- November 17, 2013
- November 22, 2013
SC'13
Denver, CO
United States
