• Presented a paper titled “Performance Evaluation of the NVIDIA GeForce 8800 GTX GPU for Machine Learning”.
• The presentation I gave at ICCS08.

Bibtex:

@inproceedings{ELZEIN08,
   editor    = {Marian Bubak and Geert Dick van Albada and Jack Dongarra and Peter M.A. Sloot},
   booktitle = {Computational Science -- ICCS 2008},
   publisher = {Springer},
   location  = {Heidelberg},
   series    = {LNCS},
   volume    = {5101},
   year      = {2008},
   isbn      = {978-3-540-69383-3},
   author    = {Ahmed El Zein and Eric Mc{C}reath and Alistair Rendell and Alex Smola},
   title     = {Performance Evaluation of the {NVIDIA} {G}e{F}orce 8800 {GTX} {GPU} for Machine Learning},
   pages     = {466--475}
}

• Presented a poster illustrating the work we have done so far in implementing sparse matrix vector products on the GPU with CUDA. A PDF of the poster can be downloaded here.

Bibtex:

@InCollection{ELZEIN07,
  author =  "Ahmed El Zein and Eric McCreath and Alistair Rendell
         and Alex Smola",
  title =   "The {S}ony {P}lay{S}tation 3 and the {NVIDIA} 8800 {GPU}:
         Performance and Programmability Evaluation for Machine
         Learning",
  booktitle =   "SC'07 USB Key",
  publisher =   "ACM/IEEE",
  address = "Reno, NV",
  month =   nov,
  year =    "2007",
  keywords =    "poster,",
  abstract =    "This poster outlines our efforts to exploit the Sony
         PlayStation3 (PS3) and the NVIDIA GeForce 8800 for
         machine learning (ML) applications. It will compare
         both the performance obtained and the programmability
         of these two different systems.\par The ML algorithm is
         iterative requiring two large matrix vector operations
         to per iteration. Our implementation strategy is
         different on each machine. On the 8800 we have explored
         the use of NVIDIA's Compute Unified Device Architecture
         (CUDA) and its associated BLAS library (cuBlas). On the
         PS3 we have programmed our own routines. Comparison
         will be made between the use of these non-conventional
         compute platforms with alternatives (the PowerPC
         processor and a dual core Athlon64).\par This work is
         on going, and while we have preliminary results for
         both systems we expected to have additional data by the
         time of SC07. Results will be presented in a standard
         poster format using a variety of tables and figures.",
}

• some pictures of me with my poster: