Publications

Self Contained, Accurate Precomputation Prefetchting
Islam Atta, Xin Tong, Vijayalakshmi Srinivasan, Ioana Baldini, Andreas Moshovos
48th International IEEE/ACM Symposium on Microarchitecture (MICRO-48), December, 2015.

ADDICT: Advanced Instruction Chasing for Transactions
Pınar Tözün, Islam Atta, Anastasia Ailamaki, Andreas Moshovos
Proceedings of Very Large Databases, Vol. 7 (PVLDB-7), 2014.

Evaluating the Memory System Behavior of Smartphone Workloads
G. Narancic, P. Judd, D. Wu, I. Atta, M. ElNacouzi, J. Zebchuk, N. Enright-Jerger, S. Gadelrab, K. Kutulakos, A. Moshovos, J. Albericio
14th International Conference on Embedded Computer Systems: Architectures, Modeling and Simulation (SAMOS-XIV), July, 2014.
(PDF)

STREX: Boosting Instruction Cache Reuse in OLTP Workloads Through Stratified Transaction Execution
Islam Atta, Pınar Tözün, Xin Tong, Anastasia Ailamaki, Andreas Moshovos
40th International Symposium on Computer Architecture (ISCA-40), June, 2013.
(PDF, PPT)

A Dual-Grain Hit/Miss Detector for Large Stacked-Die DRAM Caches
Michel ElNacouzi, Islam Atta, Myrto Papadopoulou, Jason Zebchuk, Natalie Enright, Andreas Moshovos
2013 Design, Automation and Test in Europe Conference and Exhibition (DATE-13), March, 2013.
(PDF)

SLICC: Self-Assembly of Instruction Cache Collectives for OLTP Workloads
Islam Atta, Pınar Tözün, Anastasia Ailamaki, Andreas Moshovos
45th International IEEE/ACM Symposium on Microarchitecture (MICRO-45), December, 2012.
(PDF, PPT, Poster)

Reducing Instruction Misses for OLTP with Thread Migration
Islam Atta, Pınar Tözün, Anastasia Ailamaki, Andreas Moshovos
DaMoN '12 Proceedings of the Eighth International Workshop on Data Management on New Hardware, collocated with ACM SIGMOD/PODS, May, 2012
(PDF, PPT)

 

Patent

System and Method for Tree Search and Manipulation in Distributed Memory Environment***
Islam Atta, Hisham El-Shishiny
Number: 20110016153
Publication year: 2011
Country: United States
Assignee: IBM Corporation (Armonk, NY, US)
(Patent Link)

 

Unpublished Research

Parallel Tree Manipulation
Course projects for ECE1749H and ECE1755H.
*** An experimental evaluation of the patent mentioned above.
(PDF, PPT)

 

MSc Thesis

Dynamically Partitioned Hybrid Last-Level Caches for Chip-Multiprocessors
Computer Engineering department., Faculty of Engineering, Cairo University, Giza, Egypt, 2010.
Supervisor: Mohamed Zahran, Associate Professor, Computer Sciences department, NYU.
(PDF, PPT)

 

Invited

Rethinking OLTP Execution
Cloud Technology Workshop, Stanford University, CA, Dec. 2013. (Andreas, my supervisor, replaced me)

OLTP Execution: Stratified or Collective?
Poster at the 1st Annual Amazon PhD Symposium, Amazon Campus, Seattle, WA, Nov. 2012.
(Poster)

Parallel Tree Manipulation
CARG-IBM seminars, IBM, Markham, ON, Canada, Mar. 2012.
(PPT)

Dynamic Branch Direction Hint Instrumentation for the Cell BE using RapidMind
Cell BE Technology and Programming Workshop, Alexandria University, Alexandria, Egypt, Sep. 2007.