Monday 30 September 2013

MD hcNewsFlash APU13 – Bigger & Better Than Ever

hcNewsFlash - Learn about the latest hc news, tools, events, training opportunities, and job opportunities in the heterogeneous computing arena.\

Update
FacePlus 3D Character 
Put Your Expressions onto a 3D Character
With FacePlus in Mixamo All Access, you can capture facial expressions with standard webcams and transfer them in real time onto a 3D character. This real-time capture and animation capability is made possible by offloading Mixamo’s complex algorithms from the CPU onto GPU technology. Real-time motion capture of facial expressions has the potential to make its way into video games and video conferencing applications, giving end users the opportunity to animate avatars in real time.
Hot Chips 2013 Logo 
Did You Miss Hot Chips 2013? 
If so, don't despair! Check out these Hot Chips presentations about heterogeneous system architecture (HSA) & HSAIL:
  • HSA Queueing - Ian Bratt, ARM
  • HSA Memory Model - Ben Gaster, Qualcomm
  • HSA Overview - Phil Rogers, AMD
  • HSAIL: Portable Compiler for HSA - Ben Sanders, AMD
Download the Developer's Guide for Kabini Processors 
Developer's Guide for Kabini Processors 
If you are a platform designer or involved in the development of low-level BIOS functions, drivers and operating system kernel modules, check out the Preliminary BIOS and Kernel Developer’s Guide (BKDG) for AMD Family 16h Models 00h-0Fh (Kabini) Processors. In this guide, you’ll learn about the major architecture, instruction set and virtualization support changes relative to Family 14h Models 00h-0Fh (ON)
Gary Frost - HSA from a Software Developer's Perspective 
HSA from a Software Developer's Perspective
HSA enabled hardware and software improves the programmability of compatible GPUs and accelerators as well as the compute performance for programmers working in mainstream environments. Gary Frost will be exploring these topics on October 14, 2013 at Tsinghua University in Beijing. Gary is an AMD Software Fellow and co-lead of the OpenJDK Sumatra project which promises to bring accelerated GPU compute directly into the JVM. More information about this talk will be available here in the future.
Heterogeneous Computing and HSA in China 
Heterogeneous Computing and HSA in China
One Saturday a month, more than 100 developers gather at 3WCoffee in Beijing, China to discuss GPU computing topics such as HSA & GCN, parallelism of image processing and Sparse LU factorization. Check out some of the past presentations from GPU Saturdays here. And starting this month and running through December 2013, presentations about HSA will be given at various universities throughout China. Read this blog post to find the HSA university presentation closest to you.
HSA Platform Block Diagram 
Asymmetric Multiprocessing with Heterogeneous Architectures:
Kurt Shuler of Arteris, Inc. writes in his article titled “Asymmetric Multiprocessing with Heterogeneous Architectures: Use the Best Tool for the Job” about how asymmetric multiprocessing (AMP) architectures make more efficient use of silicon. Read the full article here.

Tricks and Tips

When an AMD Developer Forum user asked about support of templates in OpenCL (Linux), AMD recommended checking out the APP SDK Sample IntrostaticCPP Kernel, which demonstrates how to use templates in OpenCL kernels using AMD's static CPP Kernel extension that is supported in Linux.

Visit the AMD Developer Forumsfor other useful tips and tricks.

Submit your Tips&Tricks tohcNewsFlash@amd.com
Jobs
AMD is Hiring!

Featured Jobs:
Submit Heterogeneous Compute job listings to hcNewsFlash@amd.com





CALL FOR RESEARCH PAPERS DICTAP2014

CALL FOR RESEARCH PAPERS
--------------------------
Deadline: April 6, 2014

You are invited to offer papers for the conference. The DICTAP2014 welcomes submissions on any topic in the field of digital information, communications technology and any related topics.

The conference welcomes papers on the following (but not limited to) research topics:

 ** Algorithms, Architecture, and Infrastructures
 ** Artificial Intelligence and Decision Support Systems
 ** Case Studies on Data Management, Monitoring and Analysis
 ** Cloud Computing and Computer Networks
 ** Communication Protocols, Communication Systems
 ** Compression and Coding
 ** Computer Graphics
 ** Constraint Programming
 ** Data Exchange Issues and Supply Chain
 ** Data Grids, Data and Information Quality
 ** Data Life Cycle in Products and Processes
 ** Data Models for Production Systems and Services
 ** Data Warehouses and Data Mining
 ** Data, Text, and Web Content Mining
 ** Digital Rights Management
 ** Distributed Information Systems
 ** E-Learning, E-Commerce, E-Business and E-Government
 ** Enterprise Computing
 ** Human-Computer Interaction
 ** ICT for Social and Humanity
 ** Image Analysis and Image Processing
 ** Information Content Security
 ** Information Retrieval
 ** Information Theory, System, and Technology
 ** Information Visualization
 ** Intelligent and Robust System
 ** Interoperability
 ** Knowledge Management
 ** Management and Diffusion of Multimedia Applications
 ** Mobile Data Management
 ** Mobile, Ad Hoc and Sensor Network Security
 ** Modeling, Algorithm, and Optimization
 ** Multimedia and Interactive Multimedia
 ** Natural Language Processing
 ** Network Management Techniques
 ** Network Systems and Devices
 ** Networks Security, Encryption and Cryptography
 ** Peer to Peer Data Management
 ** Quality of Service Issues
 ** Scientific Computing and Multimedia Processing
 ** Security and Access Control
 ** Security in Information and Telecommunication System
 ** Semantic Web, Ontologies and Rules
 ** Sensor Networks and Embedded System
 ** Soft Computing
 ** Telecommunication Business & Regulation
 ** Temporal and Spatial Databases
 ** Transmission, Antenna & Propagation
 ** Ubiquitous Systems
 ** Video Search and Video Mining
 ** Web Metrics and its Applications
 ** Web Mining including Web Intelligence and Web 3.0
 ** Web Services, Web based Application
 ** Wireless and Optical Communications
 ** XML and other extensible languages

Papers should be submitted electronically as pdf format without author(s) name. You can submit your research paper at

http://sdiwc.net/conferences/2014/dictap2014/paper-submission/.

The papers should be prepared following the instructions specified here :

http://sdiwc.net/conferences/2014/dictap2014/camera-ready/.

If you have problems regarding on submitting your paper(s), you can email us at di2014@sdiwc.net. We will contact you shortly.

For further inquiries:
----------------------
Natalie Walker
The Society of Digital Information and Wireless Communications (SDIWC)
www.sdiwc.net
di2014@sdiwc.net

Friday 27 September 2013

IPDPS 2014 September 21, 2013 Release 28th IEEE International Parallel & Distributed Processing Symposium

IPDPS 2014 September 21, 2013 Release
----------------------------------------------
28th IEEE International Parallel & Distributed Processing Symposium
May 19-23, 2014
Arizona Grand Resort
PHOENIX (Arizona) USA
www.ipdps.org
---------------------------------------------
- October 11, 2013......Abstracts due
- October 18, 2013......Submission deadline
----------------------------------------------
IPDPS 2014 ALERTS
...Submission portal now open at http://www.ipdps.org/ipdps2014/2014_call_for_papers.html
...Due dates for most of 21 workshops are after December 09, 2013. See http://www.ipdps.org/ipdps2014/2014_workshops.html
----------------------------------------------
IPDPS 2014 CALL FOR PAPERS
----------------------------------------------
----------------------------------------------
SCOPE : Authors are invited to submit manuscripts that present original unpublished research in all areas of parallel and distributed processing, including the development of experimental or commercial systems. Work focusing on emerging technologies is especially welcome. Topics of interest include, but are not limited to:

- Parallel and distributed algorithms, focusing on topics such as: numerical, combinatorial, and data-intensive parallel algorithms, scalability of algorithms and data structures for parallel and distributed systems, communication and synchronization protocols, network algorithms, scheduling, and load balancing.

- Applications of parallel and distributed computing, including computational and data-enabled science and engineering, big data applications, parallel crowd sourcing, large-scale social network analysis, management of big data, cloud and grid computing, scientific and biomedical applications, and mobile computing. Papers focusing on applications using novel commercial or research architectures, big data approaches, or discussing scalability toward the exascale level are encouraged.

- Parallel and distributed architectures, including architectures for instruction-level and thread-level parallelism; petascale and exascale systems designs; novel big data architectures; special-purpose architectures, including graphics processors, signal processors, network processors, media accelerators, and other special purpose processors and accelerators; impact of technology on architecture; network and interconnect architectures; parallel I/O and storage systems; architecture of the memory hierarchy; power-efficient and green computing architectures; dependable architectures; and performance modeling and evaluation.

- Parallel and distributed software, including parallel and multicore programming languages and compilers, runtime systems, operating systems, resource management including green computing, middleware for grids, clouds, and data centers, libraries, performance modeling and evaluation, parallel programming paradigms, and programming environments and tools. Papers focusing on novel software systems for big data and exascale systems are encouraged.

WHAT/WHERE TO SUBMIT
More details on submissions and instructions for submitting manuscripts are available at www.ipdps.org. All submitted manuscripts will be reviewed. Submitted papers should NOT have appeared in or be under consideration for another conference, workshop or journal. Go to this page for instructions on submitting manuscripts: http://www.ipdps.org/ipdps2014/2014_call_for_papers.html

IMPORTANT DATES
- October 11, 2013......Abstracts due
- October 18, 2013......Submission deadline
- December 09, 2013...Author notification
- February 01, 2014.....Camera ready due
----------------------------------------------

IPDPS 2014 CALL FOR PARTICIPATION
---------------------------------------------------------
---------------------------------------------------------
The 28th IEEE International Parallel & Distributed Processing Symposium will be held 19-23 May 2014 in Phoenix at the Arizona Grand Resort, an all-suites family-friendly resort and meeting place. Phoenix has an international airport and is the hub for several US airlines. It is only a six hour drive from Los Angeles and Las Vegas and the starting point for one day tours of the Grand Canyon as well as other historic communities in the area. For those who come early or stay late, there are boundless Southwest tourist attractions and activities. For shorter trip times, AGR has a water-world, golf course, and hiking and riding trails on the premises and an indoor athletic club and spa for fitness training. Check the IPDPS Web pages for updates and information on workshops, the PhD Forum, and other events as the full program develops and see the full call for papers for details on submitting papers for 2014.

GENERAL CHAIR
Manish PARASHAR (Rutgers University, USA)

PROGRAM CHAIR
David A. BADER (Georgia Institute of Technology, USA)
PROGRAM VICE-CHAIRS
-Algorithms
Anne BENOIT (ENS Lyon, France)
-Applications
Padma RAGHAVAN (Pennsylvania State University, USA)
-Architecture
Yan SOLIHIN (North Carolina State University, USA)
-Software
Ron BRIGHTWELL (Sandia National Laboratories, USA)

WORKSHOPS CHAIR
?mit V. ?ATALY?REK  (Ohio State University, USA)
WORKSHOPS VICE-CHAIR
Yogesh SIMMHAN (University of Southern California, USA)
----------------------------------------------
IPDPS 2014 WORKSHOPS
IPDPS workshops, held on the first and last days of the symposium, provide attendees an opportunity to explore special topics. The 21 workshops planned for IPDPS 2014 in Phoenix are listed athttp://www.ipdps.org/ipdps2014/2014_workshops.html. That page has a link to the call for papers for each workshop. Note that most workshops have a due date for submissions later than the author notification date of December 9th for regular conference papers.

PhD FORUM CO-CHAIRS
Luc BOUG? (ENS Cachan, France)
Bo HONG (Georgia Institute of Technology, USA)
----------------------------------------------
ENHANCED STUDENT AUTHOR PROGRAM 2014
The PhD Forum & Student Author Program will provide added value to encourage advisors to bring their students to IPDPS, with an enhanced program providing a comprehensive venue for students to better prepare for their research and career path in parallel and distributed computing. Participating students will have the opportunity to both present their research work and interact with senior academic and industry people in an informal setting. In addition, there will be mentoring sessions to help students improve communication skills, obtain valuable information for career planning, get familiar with a few of the trendy research topics, and make valuable contacts ? all while enjoying the IPDPS main conference and many associated workshops. See details athttp://www.ipdps.org/ipdps2014/2014_phd_forum.html

28th IEEE International Parallel & Distributed Processing Symposium
----------------------------------------------------------------------------------------------
...Follow us on Facebook at https://www.facebook.com/IPDPS
...Follow us on Twitter at  https://twitter.com/IPDPS
----------------------------------------------------------------------------------------------
Sponsored by IEEE Computer Society Technical Committee on Parallel Processing
In cooperation with ACM SIGARCH, IEEE Computer Society Technical Committee on Computer Architecture, and IEEE Computer Society Technical Committee on Distributed Processing
----------------------------------------------

HLPGPU 2014: High-Level Programming for Heterogeneous and Hierarchical Parallel Systems

Call for Papers (CFP):

HLPGPU 2014:
    High-Level Programming for Heterogeneous and Hierarchical Parallel
    Systems
Vienna, Austria, Tuesday, Jan 21st 2014.
Co-Located with HiPEAC 2014
--------------------------------------------------------------------------------

AIMS AND SCOPE
HLPGPU aims to bring together researchers and practitioners to present new results and ongoing
work on those aspects of high-level programming relevant, or specific, to
GPGPUs and new architectures.

-   High-level parallel programming models, libraries and languages.
-   Adaptation to heterogeneous/hierarchical platforms: GPGPU, multicore,
    FPGA etc.
-   Adaptation of cluster- and grid- performance models to new platforms.
-   Programming experiments and applications of heterogeneous/hierarchical
    platforms with a view on high-level programming methods.
-   Algorithmic skeletons, design patterns for heterogeneous/hierarchical
    platforms.
-   Domain-specific parallel patterns
-   Efficient implementations of parallel patterns on multicore systems
-   Mapping patterns to heterogeneous multicore systems
-   Exploiting performance information to guide pattern Implementation
-   Pattern implementations using application-specific information
-   Refactoring tools and techniques for parallel patterns
-   Tools and systems to aid pattern-based parallel programming - structured
    parallel programming models
-   Heterogeneous computing
-   Feedback-directed compilation
-   Timing analysis tools and techniques
-   Statistical performance modelling and prediction


IMPORTANT DATES
-   Submission: 1st November 2013
-   Notification: 25th November
-   Final Version: 9th December
-   Workshop 21st January, 2014

ORGANISERS
    Kevin Hammond (kh@cs.st-andrews.ac.uk) and
    Chris Brown (cmb21@st-andrews.ac.uk) (University of St Andrews)

PROGRAMME COMMITTEE
-       Chris Brown (University of St Andrews) (PC Chair)
-       Murray Cole (University of Edinburgh)
-       Jose Gracia (HLRS, Stuttgart)
-       Clemens Grelck (Universiteit van Amsterdam)
-       Gaetan Hains (Universite Paris-Est Creteil)
-       Kevin Hammond (University of St Andrews)
-       Herbert Kuchen (University Muenster)
-       Sven-Bodo Scholz (University of Heriot-Watt)


SUBMISSION
Papers must be submitted online via EasyChair:
https://www.easychair.org/conferences/?conf=hlpgpu2014

Submitted papers should be in portable document format (PDF), formatted using
the ACM SIGPLAN style guidelines. The text should be in a 9pt font in two
columns; the length is restricted to 6-10 pages.

Proceedings will be available to all HiPEAC attendees.
A selection of the best papers may be considered for publication as a journal
special issue after the event.

WEBSITE
https://sites.google.com/site/hlpgpu2014/

Thursday 26 September 2013

WoNDP: 1st Workshop on Near-Data Processing in conjunction with MICRO-46

WoNDP: 1st Workshop on Near-Data Processing
in conjunction with MICRO-46
Sunday, December 8th, 2013
Davis, California, USA


Scope:
------
Computing in large-scale systems is shifting away from the traditional
compute-centric model successfully used for many decades into one that
is much more data-centric. This transition is driven by the evolving
nature of what computing comprises, no longer dominated by the
execution of arithmetic and logic calculations but instead becoming
dominated by large data volume and the cost of moving data to the
locations where computations are performed. Data movement impacts
performance, power efficiency and reliability, three fundamental
components of a system. These trends are leading to changes in the
computing paradigm, in particular the notion of moving computation to
the data in a so-called Near-Data Processing approach, which seeks to
perform computations in the most appropriate location depending on
where data resides and what needs to be extracted from that data.
Examples already exist in systems that perform some computations
closer to disk storage, leveraging the data streaming coming from the
disks, filtering the data so that only useful items are transferred
for processing in other parts of the system.  This workshop is
intended to bring together experts from academia and industry to share
advances in the development of Near-Data Processing systems
principles, with emphasis on large-scale systems.  The workshop will
consist of submitted papers and invited talks.

Topics of interest include but are not limited to:

  - Analysis of applications illustrating the potential for Near-Data
    Processing
  - System and software architectures for Near-Data Processing
  - Programming models for distributed and heterogeneous
    infrastructures, driven by location of the data
  - Processing/Memory/Storage architectures and microarchitectures for
    Near-Data Processing
  - Performance evaluation of Near-Data Processing systems and
    subsystems
  - Power-efficiency and reliability analysis and evaluation of
    Near-Data Processing

Call for Papers:
----------------
  Two kinds of papers are invited:
  - Technical papers (4-6 pages) with preliminary results.
  - Position papers (3 pages max) on directions for research
    and development.

Please submit an electronic copy of your paper (in PDF) in two
column format with at least 10pt font.

The selected papers will be made available online. However,
publication in WoNDP does not preclude later publication at regular
conferences or journals.

Important Dates:
----------------
Paper submissions due: Monday October 14, 2013
Notification: Monday November 4th, 2013
Final Paper Due: Monday December 2nd, 2013

Organizers:
-----------
Jaime Moreno, IBM TJ Watson Research Center
Ravi Nair, IBM TJ Watson Research Center
Rajeev Balasubramonian, University of Utah

Program Committee:
------------------
Rajeev Balasubramonian, University of Utah
Jichuan Chang, HP Labs
Jeff Draper, USC/ISI
David Lilja, University of Minnesota
Jaime Moreno, IBM TJ Watson Research Center
Richard Murphy, Micron
Ravi Nair, IBM TJ Watson Research Center