News and Announcements

Dongarra Named to Committee for Square Kilometer Array

Jack Dongarra has been named to the Scientific and Engineering Advisory Committee for the Square Kilometer Array (SKA), an international effort to build the world’s largest radio telescope, eventually reaching over a square kilometer of collection area.

To accomplish this, SKA is not a single telescope but a collection of antennas to be spread over long distances that will use arrays at two primary sites—one in Australia and one in South Africa. The Australian site will have 130,000 antennas spread over 65 kilometers, while the South African site will have 200 antennas spread over 150 kilometers.

As one might imagine, this array will generate tremendous amounts of data that will need to be processed and stored, making it the quintessential “Big Data” endeavor. As Jack says, “It will generate data at a rate more than ten times today’s global Internet traffic. […] This is a mega-science project, which will test the limits of engineering and scientific endeavor over the coming decades.”

The SKA effort includes organizations from 10 countries—Australia, Canada, China, India, Italy, New Zealand, South Africa, Sweden, The Netherlands, and the United Kingdom—and is headquartered at the Jodrell Bank Observatory in Manchester, UK.

Read more from Tennessee Today.

SC15

ACM/IEEE’s Supercomputing Conference (SC15) is rapidly approaching. This year’s conference will be held on November 15 – 20 in Austin, TX. As usual, ICL will have a considerable presence at the conference with BoFs, papers, posters, and tutorials. Additionally, the University of Tennessee will again have its own booth where ICL’s research will be featured alongside other UT research centers. For an entire list of activities, visit the SC15 schedule page.

Conference Reports

Jack visits KAUST

kaust

On October 23 – 27, ICL’s Jack Dongarra visited the King Abdullah University of Science & Technology. While there, Jack met up with ICL alumni Hatem Ltaief, Mathieu Faverge, and Bilel Hadri.

KAUST is home to Shaheen II, a Cray XC40 supercomputer that currently sits at #7 on the TOP500 at 5.536 PetaFlop/s—making it the highest ranked Middle East system in the history of the TOP500 and the first to make the top 10.

SIAM Conference on Applied Linear Algebra

  • 001
  • 002
  • 003
  • 004
  • 005
  • 006
  • 007
  • 008
  • 009
  • 010

 

Knowing a little something about linear algebra, it is no surprise that a large contingent of ICLers attended the 2015 SIAM Conference on Applied Linear Algebra (SIAM LA) in Atlanta, GA on October 25 – 30. SIAM LA is organized by the Society of Industrial and Applied Mathematics (SIAM) and held every 3 years. The workshop is billed as the premier international conference in the field and brings together a diverse collection of researchers and practitioners from academia, laboratories, and industry to discuss the latest in applied linear algebra.

For our part, ICL attendance included Hartwig Anzt, Mark Gates, Piotr Luszczek, Stan Tomov, Mike Tsai, and Ichi Yamazaki. Hartwig acted as chair of the session on Mathematical Software and High Performance Computing and gave a talk on, “Random-Order Alternating Schwarz for Sparse Triangular Solves.” Mark Gates gave a talk, “Comparing Hybrid and Native GPU Acceleration for Linear Algebra.” Stan gave two talks, the first on “Efficient Eigensolver Algorithm on Accelerator Based Architecture,” and the second on, “Batched Matrix Computations on Hardware Accelerators Based on GPUs.” Mike Tsai presented a poster called, “Towards Batched Linear Solvers on Accelerated Hardware Platforms,” which will soon be hanging up in Stan’s office. Finally, Ichi presented ICL’s work on, “Mixed-Precision Orthogonalization Processes.”

As with every SIAM conference lately, and in part due to the proximity of Atlanta to Knoxville, the ICL team brought home a few visitors to the lab following SIAM LA, including ICL alum Marc Baboulin (INRIA) along with Takeshi Fukaya (Hokkaido University) and Toshiyuki Imamura (RIKEN).

Interview

Moritz Kreutzer Then

Moritz Kreutzer

Where are you from, originally?

I am from Sonneberg, Germany but I’ve been living in or close to Nuremberg for the last nine years.

Can you summarize your educational background?

I earned my BS in Computational Engineering in Erlangen, Germany. Afterwards, I spent one year of my MS studies in Erlangen (Computational Engineering as well) and the other one in Stockholm, Sweden (Scientific Computing) before I started my PhD studies in Erlangen.

Tell us how you first learned about ICL.

To be honest, I cannot recall the exact moment. However, as ICL is very well-known and highly renowned in the HPC community, learning about it is just a matter of time if you work in this field.

What made you want to visit ICL?

At one point, we had contact with Hartwig Anzt from ICL due to a certain overlap of interest and work. We figured it would be a great opportunity to stay in Knoxville and work with ICL for some time during my PhD studies. Fortunately, it worked out and now I am here.

What are your research interests?

I am working on building blocks for sparse linear algebra on heterogeneous systems. My work involves high-performance implementations for CPUs and accelerators guided by performance models in close collaboration with experts from the application side.

What are you working on during your visit with ICL?

During my visit with ICL, we are planning to conduct a heterogeneous implementation of the block Jacobi-Davidson method, a sparse eigenvalue solver.

What are your interests/hobbies outside work?

I really enjoy doing sports (especially rock climbing) and I am a passionate amateur chef. Besides, I also like travelling and reading.

Tell us something about yourself that might surprise people.

I can make the best pizza far and wide.

Recent Papers

  1. Haidar, A., A. Abdelfattah, S. Tomov, and J. Dongarra, Batched Matrix Computations on Hardware Accelerators Based on GPUs,” 2015 SIAM Conference on Applied Linear Algebra (SIAM LA), Atlanta, GA, SIAM, October 2015.  (9.36 MB)
  2. Gates, M., S. Tomov, and A. Haidar, Comparing Hybrid CPU-GPU and Native GPU-only Acceleration for Linear Algebra,” 2015 SIAM Conference on Applied Linear Algebra, Atlanta, GA, SIAM, October 2015.  (4.7 MB)
  3. Haidar, A., P. Luszczek, S. Tomov, and J. Dongarra, Efficient Eigensolver Algorithms on Accelerator Based Architectures,” 2015 SIAM Conference on Applied Linear Algebra (SIAM LA), Atlanta, GA, SIAM, October 2015.  (6.98 MB)
  4. Yamazaki, I., J. Barlow, S. Tomov, J. Kurzak, and J. Dongarra, Mixed-precision orthogonalization process Performance on multicore CPUs with GPUs,” 2015 SIAM Conference on Applied Linear Algebra, Atlanta, GA, SIAM, October 2015.  (301.01 KB)
  5. Abalenkovs, M., A. Abdelfattah, J. Dongarra, M. Gates, A. Haidar, J. Kurzak, P. Luszczek, S. Tomov, I. Yamazaki, and A. YarKhan, Parallel Programming Models for Dense Linear Algebra on Heterogeneous Systems,” Supercomputing Frontiers and Innovations, vol. 2, no. 4, October 2015. DOI: 10.14529/jsfi1504  (3.68 MB)
  6. Anzt, H., E. Chow, D. Szyld, and J. Dongarra, Random-Order Alternating Schwarz for Sparse Triangular Solves,” 2015 SIAM Conference on Applied Linear Algebra (SIAM LA), Atlanta, GA, SIAM, October 2015.  (1.53 MB)
  7. Gates, M., H. Anzt, J. Kurzak, and J. Dongarra, Accelerating Collaborative Filtering for Implicit Feedback Datasets using GPUs,” 2015 IEEE International Conference on Big Data (IEEE BigData 2015), Santa Clara, CA, IEEE, November 2015.  (1.02 MB)
  8. Anzt, H., J. Dongarra, and E. S. Quintana-Orti, Adaptive Precision Solvers for Sparse Linear Systems,” 3rd International Workshop on Energy Efficient Supercomputing (E2SC '15), Austin, TX, ACM, November 2015.
  9. Solcà, R., A. Kozhevnikov, A. Haidar, S. Tomov, T. C. Schulthess, and J. Dongarra, Efficient Implementation Of Quantum Materials Simulations On Distributed CPU-GPU Systems,” The International Conference for High Performance Computing, Networking, Storage and Analysis (SC15), Austin, TX, ACM, November 2015.  (1.09 MB)
  10. Anzt, H., E. Ponce, G. D. Peterson, and J. Dongarra, GPU-accelerated Co-design of Induced Dimension Reduction: Algorithmic Fusion and Kernel Overlap,” 2nd International Workshop on Hardware-Software Co-Design for High Performance Computing, Austin, TX, ACM, November 2015.  (1.46 MB)
  11. Kurzak, J., H. Anzt, M. Gates, and J. Dongarra, Implementation and Tuning of Batched Cholesky Factorization and Solve for NVIDIA GPUs,” IEEE Transactions on Parallel and Distributed Systems, no. 1045-9219, November 2015.
  12. Yamazaki, I., S. Tomov, J. Kurzak, J. Dongarra, and J. Barlow, Mixed-precision Block Gram Schmidt Orthogonalization,” 6th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems, Austin, TX, ACM, November 2015.  (235.69 KB)
  13. Faverge, M., J. Herrmann, J. Langou, B. Lowery, Y. Robert, and J. Dongarra, Mixing LU-QR Factorization Algorithms to Design High-Performance Dense Linear Algebra Solvers,” Journal of Parallel and Distributed Computing, vol. 85, pp. 32-46, November 2015. DOI: doi:10.1016/j.jpdc.2015.06.007  (5.06 MB)
  14. Mary, T., I. Yamazaki, J. Kurzak, P. Luszczek, S. Tomov, and J. Dongarra, Performance of Random Sampling for Computing Low-rank Approximations of a Dense Matrix on GPUs,” The International Conference for High Performance Computing, Networking, Storage and Analysis (SC15), Austin, TX, ACM, November 2015.
  15. Herault, T., A. Bouteiller, G. Bosilca, M. Gamell, K. Teranishi, M. Parashar, and J. Dongarra, Practical Scalable Consensus for Pseudo-Synchronous Distributed Systems,” The International Conference for High Performance Computing, Networking, Storage and Analysis (SC15), Austin, TX, ACM, November 2015.  (550.96 KB)
  16. Yamazaki, I., J. Kurzak, P. Luszczek, and J. Dongarra, Randomized Algorithms to Update Partial Singular Value Decomposition on a Hybrid CPU/GPU Cluster,” The International Conference for High Performance Computing, Networking, Storage and Analysis (SC15), Austin, TX, ACM, November 2015.
  17. Strohmaier, E., H. Meuer, J. Dongarra, and H. D. Simon, The TOP500 List and Progress in High-Performance Computing,” IEEE Computer, vol. 48, issue 11, pp. 42-49, November 2015. DOI: doi:10.1109/MC.2015.338
  18. Anzt, H., J. Dongarra, and E. S. Quintana-Orti, Tuning Stationary Iterative Solvers for Fault Resilience,” 6th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems (ScalA15), Austin, TX, ACM, November 2015.  (1.28 MB)
  19. Haugen, B., S. Richmond, J. Kurzak, C. A. Steed, and J. Dongarra, Visualizing Execution Traces with Task Dependencies,” 2nd Workshop on Visual Performance Analysis (VPA '15), Austin, TX, ACM, November 2015.  (927.5 KB)
  20. Haidar, A., Y. Jia, P. Luszczek, S. Tomov, A. YarKhan, and J. Dongarra, Weighted Dynamic Scheduling with Many Parallelism Grains for Offloading of Numerical Workloads to Multiple Varied Accelerators,” Proceedings of the 6th Workshop on Latest Advances in Scalable Algorithms for Large-Scale Systems (ScalA'15), vol. No. 5, Austin, TX, ACM, November 2015.  (347.6 KB)

Recent Conferences

  1. OCT
    Argo Members Meeting Argonne, Illinois
    Damien Genet
    Damien
    George Bosilca
    George
    Thomas Herault
    Thomas
    Damien Genet, George Bosilca, Thomas Herault
  2. OCT
    IWACOM-III Tokyo, Japan
    Ichitaro Yamazaki
    Ichitaro
    Ichitaro Yamazaki
  3. OCT
    -
    Jack Dongarra
    Jack
    Jack Dongarra
  4. OCT
    -
    White House Workshop on the National Strategic Computing Initiative (NSCI) Washington, District of Columbia
    Jack Dongarra
    Jack
    Jack Dongarra
  5. OCT
    -
    SIAM LA Atlanta, Georgia
    Azzam Haidar
    Azzam
    Hartwig Anzt
    Hartwig
    Ichitaro Yamazaki
    Ichitaro
    Mark Gates
    Mark
    Piotr Luszczek
    Piotr
    Stanimire Tomov
    Stan
    Yaohung
    Mike
    Azzam Haidar, Hartwig Anzt, Ichitaro Yamazaki, Mark Gates, Piotr Luszczek, Stanimire Tomov, Yaohung "Mike" Tsai
  6. NOV
    -
    SC15 Austin, Texas
    Aurelien Bouteiller
    Aurelien
    George Bosilca
    George
    Hartwig Anzt
    Hartwig
    Ichitaro Yamazaki
    Ichitaro
    Jack Dongarra
    Jack
    Jakub Kurzak
    Jakub
    Phil Mucci
    Phil
    Piotr Luszczek
    Piotr
    Terry Moore
    Terry
    Thomas Herault
    Thomas
    Tracy Rafferty
    Tracy
    Aurelien Bouteiller, George Bosilca, Hartwig Anzt, Ichitaro Yamazaki, Jack Dongarra, Jakub Kurzak, Phil Mucci, Piotr Luszczek, Terry Moore, Thomas Herault, Tracy Rafferty
  7. NOV
    Blake Haugen
    Blake
    Blake Haugen

Upcoming Conferences

  1. DEC
    MPI Forum San Jose, California
    Aurelien Bouteiller
    Aurelien
    Aurelien Bouteiller
  2. DEC
    TESSE Meeting Blacksburg, Virginia
    Amina Guermouche
    Amina
    George Bosilca
    George
    Thomas Herault
    Thomas
    Amina Guermouche, George Bosilca, Thomas Herault

Recent Lunch Talks

  1. OCT
    2
    Mike Guidry
    Mike Guidry
    ORNL
    Fast New Methods for Solving Large Sets of Coupled Differential Equations at Scale in Scientific Applications PDF
  2. OCT
    9
    Mike Jantz
    Mike Jantz
    EECS
    Cross-Layer Memory Management to Achieve Power and Performance Goals PDF
  3. OCT
    12
    Edmond Chow
    Edmond Chow
    Georgia Tech
    Very Fine-grained Parallelization of Sparse Linear Algebra Computations PDF
  4. OCT
    16
    Pierre Sens
    Pierre Sens
    LIP6
    Probabilistic Byzantine Tolerance for Cloud Computing PDF
  5. OCT
    23
    Bob Muenchen
    Bob Muenchen
    UTK
    Monitoring Trends in Tools for Data Science PDF
  6. OCT
    30
    Michael Barton
    Michael Barton
    United States Army Research Laboratory (ARL)
    Data Intensive Science and Computing PDF
  7. NOV
    3
    Takeshi Fukaya
    Takeshi Fukaya
    Hokkaido University
    CholeskyQR2: Cholesky QR factorization with reorthogonalization PDF
  8. NOV
    3
    Toshiyuki Imamura
    Toshiyuki Imamura
    RIKEN AICS
    ASPEN.K2+MUBLAS:level2 CUDA BLAS kernels PDF
  9. NOV
    6
    Moritz Kreutzer
    Moritz Kreutzer
    Friedrich-Alexander University Erlangen-Nürnberg
    Performance Engineering of the Kernel Polynomal Method on Large-Scale CPU-GPU Systems PDF
  10. NOV
    13
    Sticks Mabakane
    Sticks Mabakane
    University of Cape Town
    Novel Visualizations for Optimization of Parallel Programs PDF

Upcoming Lunch Talks

  1. DEC
    4
    Azzam Haidar
    Azzam Haidar
    Batched Matrix Computations on Hardware Accelerators PDF
  2. DEC
    11
    Kalyan Perumalla
    Kalyan Perumalla
    ORNL

Visitors

  1. Takeshi Fukaya
    Takeshi Fukaya from Hokkaido University will be visiting from October 30 through November 5.
  2. Toshiyuki Imamura
    Toshiyuki Imamura from RIKEN will be visiting from October 30 through November 5.

People

  1. Chunyan Tang
    ICL alum Chunyan Tang landed a position as a Programmer Analyst at Merced County in central California. Congratulations, Chunyan!
  2. Yulu Jia
    Yulu Jia successfully defended his dissertation this month and has earned his PhD in Computer Science with a minor in Computational Science. The University of Tennessee will formally present his diploma on December 10th at which time Yulu will be working for Intel. Congratulations Yulu!
  3. Tingxing Dong
    Tingxing Dong also successfully defended his dissertation this month and has earned his PhD in Computer Science with a minor in Computational Science. The University of Tennessee will formally present his diploma on December 10th. Meanwhile, Tingxing has been working at AMD in Austin, TX. Congratulations Tingxing!

Visitors

  1. Takeshi Fukaya
    Takeshi Fukaya from Hokkaido University will be visiting from October 30 through November 5.
  2. Toshiyuki Imamura
    Toshiyuki Imamura from RIKEN will be visiting from October 30 through November 5.

congratulations

Mariam Abdelfattah

MariamICL’s Ahmad Abdelfattah and his wife Nada are now the proud parents of Mariam Abdelfattah! Mariam was born on November 5, 2015 in Cairo and weighed in at 6.2lbs. Both mother and baby are doing well. Congratulations!

Dates to Remember

SC15 ICL Dinner

Save the date! The SC15 ICL dinner will be on Wednesday,November 18th, 7pm, at Z’ Tejas (1110 West 6th Street) in Austin, TX.