main.bbl

\begin{thebibliography}{10}

\bibitem{Hoard}
E.~D. Berger, K.~S. McKinley, R.~D. Blumofe, and P.~R. Wilson.
\newblock Hoard: a scalable memory allocator for multithreaded applications.
\newblock In {\em ASPLOS-IX: Proceedings of the ninth international conference
  on Architectural support for programming languages and operating systems},
  pages 117--128, New York, NY, USA, 2000. ACM Press.

\bibitem{Berger:2001:CHM:378795.378821}
E.~D. Berger, B.~G. Zorn, and K.~S. McKinley.
\newblock Composing high-performance memory allocators.
\newblock In {\em Proceedings of the ACM SIGPLAN 2001 Conference on Programming
  Language Design and Implementation}, PLDI '01, pages 114--124, New York, NY,
  USA, 2001. ACM.

\bibitem{parsec}
C.~Bienia.
\newblock {\em Benchmarking Modern Multiprocessors}.
\newblock PhD thesis, Princeton University, January 2011.

\bibitem{falseshare:effect}
W.~J. Bolosky and M.~L. Scott.
\newblock False sharing and its effect on shared memory performance.
\newblock In {\em {SEDMS IV}: USENIX Symposium on Experiences with Distributed
  and Multiprocessor Systems}, pages 57--71, Berkeley, CA, USA, 1993. USENIX
  Association.

\bibitem{DBLP:conf/sc/BuckH04}
B.~R. Buck and J.~K. Hollingsworth.
\newblock Data centric cache measurement on the {Intel ltanium} 2 processor.
\newblock In {\em {SC '04}: Proc. of the 2004 ACM/IEEE Conf. on
  Supercomputing}, page~58, Washington, DC, USA, 2004. IEEE Computer Society.

\bibitem{AMDIBS:07}
P.~J. Drongowski.
\newblock Instruction-based sampling: A new performance analysis technique for
  {AMD} family 10h processors.
\newblock \url{http://developer.amd.com/Assets/AMD\_IBS\_paper\_EN.pdf},
  November 2007.
\newblock Last accessed: Dec. 13, 2013.

\bibitem{gprof}
{Gprof community }.
\newblock Gnu gprof.
\newblock \url{https://sourceware.org/binutils/docs/gprof/}.

\bibitem{DBLP:conf/sigplan/GrahamKM82}
S.~L. Graham, P.~B. Kessler, and M.~K. McKusick.
\newblock gprof: a call graph execution profiler.
\newblock In {\em SIGPLAN Symposium on Compiler Construction}, pages 120--126,
  1982.

\bibitem{falseshare:binaryinstrumentation1}
S.~M. G\"{u}nther and J.~Weidendorfer.
\newblock Assessing cache false sharing effects by dynamic binary
  instrumentation.
\newblock In {\em WBIA '09: Proceedings of the Workshop on Binary
  Instrumentation and Applications}, pages 26--33, New York, NY, USA, 2009.
  ACM.

\bibitem{rtdsc}
Intel.
\newblock Using the rdtsc instruction for performance monitoring.
\newblock \url{https://www.ccsl.carleton.ca/~jamuir/rdtscpm1.pdf}.

\bibitem{Intel:VTune}
{Intel Corporation}.
\newblock Intel {VTune} performance analyzer.
\newblock \url{http://www.intel.com/software/products/vtune}.

\bibitem{detect:ptu}
{Intel Corporation}.
\newblock {\em Intel Performance Tuning Utility 3.2 Update}, November 2008.

\bibitem{detect:intel}
{Intel Corporation}.
\newblock Avoiding and identifying false sharing among threads.
\newblock
  \url{http://software.intel.com/en-us/articles/avoiding-and-identifying-false-sharing-among-threads/},
  February 2010.

\bibitem{IntelArch:PEBS:Sept09}
{Intel Corporation}.
\newblock {Intel 64 and IA-32} architectures software developer's manual,
  {Volume 3B}: System programming guide, {Part 2, Number 253669-032}, June
  2010.

\bibitem{DBLP:conf/sc/ItzkowitzWAK03}
M.~Itzkowitz, B.~J.~N. Wylie, C.~Aoki, and N.~Kosche.
\newblock Memory profiling using hardware counters.
\newblock In {\em SC '03: Proc. of the 2003 ACM/IEEE Conf. on Supercomputing},
  page~17, Washington, DC, USA, 2003. IEEE Computer Society.

\bibitem{mldetect}
S.~Jayasena, S.~Amarasinghe, A.~Abeyweera, G.~Amarasinghe, H.~De~Silva,
  S.~Rathnayake, X.~Meng, and Y.~Liu.
\newblock Detection of false sharing using machine learning.
\newblock In {\em Proceedings of SC13: International Conference for High
  Performance Computing, Networking, Storage and Analysis}, SC '13, pages
  30:1--30:9, New York, NY, USA, 2013. ACM.

\bibitem{oprofile}
J.~Levon and P.~Elie.
\newblock Oprofile: A system profiler for {Linux}, 2004.

\bibitem{falseshare:binaryinstrumentation2}
C.-L. Liu.
\newblock False sharing analysis for multithreaded programs.
\newblock Master's thesis, National Chung Cheng University, July 2009.

\bibitem{Sheriff}
T.~Liu and E.~D. Berger.
\newblock Sheriff: precise detection and automatic mitigation of false sharing.
\newblock In {\em Proceedings of the 2011 ACM international conference on
  Object oriented programming systems languages and applications}, OOPSLA '11,
  pages 3--18, New York, NY, USA, 2011. ACM.

\bibitem{Predator}
T.~Liu, C.~Tian, H.~Ziang, and E.~D. Berger.
\newblock Predator: Predictive false sharing detection.
\newblock In {\em Proceedings of 19th ACM SIGPLAN Symposium on Principles and
  Practice of Parallel Programming}, PPOPP'14, New York, NY, USA, 2014. ACM.

\bibitem{ibs-sc}
X.~Liu and J.~M. {Mellor-Crummey}.
\newblock A data-centric profiler for parallel programs.
\newblock In {\em Proc. of the 2013 ACM/IEEE Conference on Supercomputing},
  Denver, CO, USA, 2013.

\bibitem{ibs-pact}
X.~Liu, K.~Sharma, and J.~Mellor-Crummey.
\newblock Arraytool: A lightweight profiler to guide array regrouping.
\newblock In {\em Proceedings of the 23rd International Conference on Parallel
  Architectures and Compilation}, PACT '14, pages 405--416, New York, NY, USA,
  2014. ACM.

\bibitem{ibs-sc2}
X.~Liu and B.~Wu.
\newblock {ScaAnalyzer}: A tool to identify memory scalability bottlenecks in
  parallel programs.
\newblock In {\em Proc. of the 2015 ACM/IEEE Conference on Supercomputing},
  Austin, TX, USA, 2015.

\bibitem{OSdetection}
M.~Nanavati, M.~Spear, N.~Taylor, S.~Rajagopalan, D.~T. Meyer, W.~Aiello, and
  A.~Warfield.
\newblock Whose cache line is it anyway?: operating system support for live
  detection and repair of false sharing.
\newblock In {\em Proceedings of the 8th ACM European Conference on Computer
  Systems}, EuroSys '13, pages 141--154, New York, NY, USA, 2013. ACM.

\bibitem{MESI}
M.~S. Papamarcos and J.~H. Patel.
\newblock A low-overhead coherence solution for multiprocessors with private
  cache memories.
\newblock In {\em Proceedings of the 11th Annual International Symposium on
  Computer Architecture}, ISCA '84, pages 348--354, New York, NY, USA, 1984.
  ACM.

\bibitem{DProf}
A.~Pesterev, N.~Zeldovich, and R.~T. Morris.
\newblock Locating cache performance bottlenecks using data profiling.
\newblock In {\em EuroSys '10: Proceedings of the 5th European conference on
  Computer systems}, pages 335--348, New York, NY, USA, 2010. ACM.

\bibitem{phoenix-hpca}
C.~Ranger, R.~Raghuraman, A.~Penmetsa, G.~Bradski, and C.~Kozyrakis.
\newblock Evaluating {MapReduce} for multi-core and multiprocessor systems.
\newblock In {\em HPCA '07: Proceedings of the 2007 IEEE 13th International
  Symposium on High Performance Computer Architecture}, pages 13--24,
  Washington, DC, USA, 2007. IEEE Computer Society.

\bibitem{falseshare:simulator}
M.~Schindewolf.
\newblock Analysis of cache misses using {SIMICS}.
\newblock Master's thesis, Institute for Computing Systems Architecture,
  University of Edinburgh, 2007.

\bibitem{Dramon}
W.~Wang, T.~Dey, J.~Davidson, and M.~Soffa.
\newblock {DraMon}: Predicting memory bandwidth usage of multi-threaded
  programs with high accuracy and low overhead.
\newblock In {\em High Performance Computer Architecture (HPCA), 2014 IEEE 20th
  International Symposium on}, pages 380--391, Feb 2014.

\bibitem{Wicaksono11detectingfalse}
B.~Wicaksono, M.~Tolubaeva, and B.~Chapman.
\newblock Detecting false sharing in openmp applications using the darwin
  framework.
\newblock In {\em In Proceedings of International Workshop on Languages and
  Compilers for Parallel Computing}, 2011.

\bibitem{openmp}
B.~Wicaksono, M.~Tolubaeva, and B.~Chapman.
\newblock Detecting false sharing in openmp applications using the darwin
  framework.
\newblock In S.~Rajopadhye and M.~Mills~Strout, editors, {\em Languages and
  Compilers for Parallel Computing}, volume 7146 of {\em Lecture Notes in
  Computer Science}, pages 283--297. Springer Berlin Heidelberg, 2013.

\bibitem{qinzhao}
Q.~Zhao, D.~Koh, S.~Raza, D.~Bruening, W.-F. Wong, and S.~Amarasinghe.
\newblock Dynamic cache contention detection in multi-threaded applications.
\newblock In {\em The International Conference on Virtual Execution
  Environments}, Newport Beach, CA, Mar 2011.

\end{thebibliography}