% BibTeX bibliography file

%%
%% WARNING: This file has been edited to conform to HTML output rather
%%          than TeX output.  You will need to fix special characters,
%%          some braces, emphasis, etc.
%%


%%
%% Active messages
%%
%% the original CMAM and CMAML papers
%% some performance results
%% the AM-II and VIA specifications
%% the AM-II protocol paper
%%

@InProceedings{am,
    author = {T. von Eicken and D. E. Culler and S. C. Goldstein and 
	      K. E. Schauser},
    title = {{Active Messages: a Mechanism for Integrated Communication and 
	      Computation}},
    booktitle = {Proceedings of the 19th International Symposium on Computer
		 Architecture},
    address = {Gold Coast, Queensland, Australia},
    month = {May},
    year = {1992},
    pages = {256-66}
}

@InProceedings{hpam,
    author = {R. P. Martin},
    title = {{HPAM: an Active Message Layer for a Network of HP Workstations}},
    booktitle = {Proceedings of Hot Interconnects II},
    month = {August},
    year = {1994},
    pages = {40-58}
}

@Article{cmam,
    author = {L. Tucker and A. M. Mainwaring},
    title = {{CMMD: Active Messages on the CM-5}},
    journal = {Parallel Computing},
    volume = {20},
    number = {4},
    month = {August},
    year = {1994},
    pages = {481-96}
}

@InProceedings{csam,
    author = {K. E. Schauser and C. Scheiman},
    title = {{Experience with Active Messages on the Meiko CS-2}},
    booktitle = {Proceedings of the 9th International Parallel Processing
		 Symposium},
    address = {Santa Barbara, California},
    month = {April},
    year = {1995},
    pages = {140-9}
}

@Article{atmam,
    author = {T. von Eicken and V. Avula and A. Basu and V. Buch},
    title = {{Low-latency Communication over ATM Networks Using Active 
	      Messages}},
    journal = {IEEE Micro},
    volume = {15},
    number = {1},
    month = {February},
    year = {1995},
    pages = {46-53}
}

@InProceedings{liu, 
    author = {L. T. Liu and D. E. Culler},
    title = {{Evaluation of the Intel Paragon on Active Message 
 	      Communication}},
    booktitle = {Proceedings of the Intel Supercomputer Users Group 
		 Conference},
    month = {June}, 
    year = {1995},
    url = {http://now.CS.Berkeley.EDU},
    link = {available via the NOW project}
}

@InProceedings{fm,
    author = {S. Pakin and M. Lauria and A. A. Chien},
    title = {{High Performance Messaging on Workstations: Illinois
              Fast Messages (FM) for Myrinet}},
    booktitle = {Proceedings of Supercomputing 1995},
    address = {San Diego, California},
    month = {December},
    year = {1995}
}

@TechReport{am-ii, 
    author = {A. M. Mainwaring and D. E. Culler},
    title = {{Active Message Applications Programming Interface and 
 	      Communication Subsystem Organization}},
    institution = {U. C. Berkeley},
    number = {#CSD-96-918},
    month = {October}, 
    year = {1996}
}

@InProceedings{unet,
    author = {M. D. Welsh and A. Basu and T. von Eicken},
    title = {{ATM and Fast Ethernet Network Interfaces for User-Level
              Communication}},
    booktitle = {Proceedings of 3rd International Symposium on 
                 High-Performance Computer Architecture},
    address = {San Antonio, Texas},
    month = {February},
    year = {1997},
    pages = {332-42}
}

@Unpublished{via,
    key = {VIA},
    title = {{Virtual Interface Architecture Specification, Version 1.0,
	      published by Compaq, Intel, and Microsoft}},
    month = {December},
    year = {1997},
    url = {http://www.viarch.org},
    link = {available online}
}

@Article{hoti,
    author = {B. N. Chun and A. M. Mainwaring and D. E. Culler},
    title = {{Virtual Network Transport Protocols for Myrinet}},
    journal = {IEEE Micro},
    volume = {18},
    number = {1},
    month = {January},
    year = {1998},
    pages = {53-63}
}

@InProceedings{fm-logp,
    author = {G. Iannello and M. Lauria and S. Mercolino},
    title = {{LogP Performance Characterization of Fast Messages atop
	      Myrinet}},
    booktitle = {Proceedings of the Sixth Euromicro Workshop on Parallel and
		 Distributed Processing},
    address = {Madrid, Spain},
    month = {January},
    year = {1998},
    pages = {395-401}
}

@InCollection{bip,
    author = {L. Prylli and B. Tourancheau},
    title = {BIP: A New Protocol Designed for High Performance
              Networking on Myrinet},
    booktitle = {Parallel and Distributed Processing},
    series = {Lecture Notes in Computer Science},
    volume = {1388},
    editor = {Jos&#233 Rolim},
    publisher = {Springer-Verlag},
    year = {1998},
    pages = {472-85}
}



%%
%% LogP, LogGP, the microbenchmark, and message cost breakdown (Scott & Cox)
%%

@InProceedings{logp,
    author = {D. E. Culler and R. M. Karp and D. A. Patterson and
              A. Sahay and K. E. Schauser and E. Santos and 
              R. Subramonian and T. von Eicken},
    title = {{LogP: Towards a Realistic Model of Parallel Computation}},
    booktitle = {Proceedings of the 4th Symposium on Principles 
                 and Practice of Parallel Programming},
    address = {San Diego, California},
    month = {May},
    year = {1993}
} 

@InProceedings{loggp,
    author = {A. Alexandrov and M. Ionescu and K. E. Schauser and
              C. Scheiman},
    title = {{LogGP: Incorporating Long Messages into the LogP 
	      Model---One Step Closer towards a Realistic Model
	      for Parallel Computation}},
    booktitle = {Proceedings of the 7th Symposium on Parallel
		 Algorithms and Architectures},
    address = {Santa Barbara, California},
    month = {July},
    year = {1995},
    pages = {95-105}
}

@Article{ubench,
    author = {D. E. Culler and L. T. Liu and R. P. Martin and 
 	      C. O. Yoshikawa},
    title = {{Assessing Fast Network Interfaces}},
    journal = {IEEE Micro},
    volume = {16},
    number = {1},
    month = {February},
    year = {1996},
    pages = {35-43}
}

@InProceedings{mp-overhead,
    author = {M. L. Scott and A. L. Cox},
    title = {{An Empirical Study of Message-Passing Overhead}},
    booktitle = {Proceedings of the 7th International Conference on 
                 Distributed Computing Systems},
    address = {Berlin, West Germany},
    month = {September},
    year = {1987},
    pages = {536-43}
}



%%
%% shared memory message-passing
%%
%% Byrd's models of 1-to-1 queues
%% hardware suggestions
%% message proxy work
%%

@TechReport{byrd,
    author = {G. T. Byrd},
    title = {{Models of Communication Latency in Shared Memory 
 	      Multiprocessors}},
    institution = {Stanford University},
    number = {CSL-TR-93-596},
    month = {December},
    year = {1993}
}

@Article{memory-based,
    author = {D. R. Cheriton and R. A. Kutter},
    title = {{Optimized Memory-Based Messaging: Leveraging the Memory 
 	     System for High-Performance Communication}},
    journal = {Computing Systems},
    volume = {9},
    number = {3},
    season =  {Summer},
    year = {1996},
    pages = {179-215}
}


%%
%% message proxy approaches and comparison
%%
%% message proxy paper, survey and comparison paper
%%
 
@InProceedings{proxies, 
    author = {B.-H. Lim and P. Heidelberger and P. Pattnaik and M. Snir},
    title = {{Message Proxies for Efficient, Protected Communication on 
 	      SMP Clusters}},
    booktitle = {Proceedings of the 3rd International Symposium on 
		 High-Performance Computer Architecture},
    address = {San Antonio, Texas},
    month = {February},
    year = {1997},
    pages = {116-27}
}

@InProceedings{falsafi,
    author = {B. Falsafi and D. A. Wood},
    title = {{Scheduling Communication on an SMP Node Parallel Machine}},
    booktitle = {Proceedings of the 3rd International Symposium on 
		 High-Performance Computer Architecture},
    address = {San Antonio, Texas},
    month = {February},
    year = {1997},
    pages = {128-38}
}



%%
%% application of MPP interconnection technology to workstations
%%
%% shrimp micro paper, myrinet paper
%%

@InProceedings{shrimp-ni,
    author = {M. A. Blumrich and K. Li and R. Alpert and C. Dubnicki
              and E. W. Felten and J. Sandberg},
    title = {{Virtual-Memory-Mapped Network Interface for the SHRIMP
              Multicomputer}}, 
    booktitle = {Proceedings of the 21st International Symposium on
                 Computer Architecture},
    address = {Chicago, Illinois},
    month = {April},
    year = {1994},
    pages = {142-53}
}

@Article{shrimp-micro,
    author = {M. A. Blumrich and C. Dubnicki and E. W. Felten and
              K. Li and M. R. Mesarina},
    title = {{Virtual-Memory-Mapped Network Interfaces}},
    journal = {IEEE Micro},
    volume = {15},
    number = {1},
    month = {February},
    year = {1995},
    pages = {21-28}
}

@Article{myrinet,
    author = {N. J. Boden and D. Cohen and R. E. Felderman and 
              A. E. Kulawik and C. L. Seitz and J. N. Seizovic and W. Su},
    title = {{Myrinet---A Gigabit-per-Second Local-Area Network}},
    journal = {IEEE Micro},
    volume = {15},
    number = {1},
    month = {February},
    year = {1995},
    pages = {29-38}
}

@Unpublished{asci,
    key = {DOE},
    title = {{Accelerated Strategic Computing Initiative, a program of the 
	      U. S. Department of Energy}},
    url = {http://www.llnl.gov/asci-alliances/},
    link = {information available online}
}

@Unpublished{bader,
    author = {D. A. Bader and J. J&#225J&#225},
    title = {{SIMPLE: A Methodology for Programming High Performance 
	      Algorithms on Clusters of Symmetric Multiprocessors (SMP's)}},
    url = {http://www.umiacs.umd.edu/research/EXPAR},
    link = {preliminary version},
    month = {May},
    year = {1997}
}

@InProceedings{brewer,
    author = {E. A. Brewer and B. C. Kuszmaul},
    title = {{How to Get Good Performance from the CM-5 Data Network}},
    booktitle = {Proceedings of the 8th International Parallel Processing 
		 Symposium},
    address = {Cancun, Mexico},
    month = {April},
    year = {1994},
    pages = {858-67}
}

@Article{p4,
    author = {R. Butler and E. Lusk},
    title = {{Monitors, Message, and Clusters: the p4 Parallel Programming
             System}},
    journal = {Parallel Computing},
    volume = {20},
    number = {4},
    month = {April},
    year = {1994}, 
    pages = {547-64}
}

@InProceedings{split-c,
    author = {D. E. Culler and A. Dusseau and S. C. Goldstein and 
 	      A. Krishnamurthy and S. S. Lumetta and T. von Eicken and 
              K. Yelick},
    title = {{Parallel Programming in Split-C}},
    booktitle = {Proceedings of Supercomputing 1993},
    address = {Portland, Oregon},
    month = {November},
    year = {1993},
    pages = {262-73}
}

@Unpublished{fink-baden,
    author = {S. J. Fink and S. B. Baden},
    title = {{Partitioning of Finite Difference Methods Running on SMP 
	      Clusters}},
    url = {http://www-cse.ucsd.edu/users/baden},
    link = {available online}
}

@InCollection{kelp,
    author = {S. J. Fink and S. B. Baden},
    title = {Runtime Support for Multi-Tier Programming of Block-Structured
	      Applications on SMP Clusters},
    booktitle = {Scientific Computing in Object-Oriented Parallel
		  Environments},
    series = {Lecture Notes in Computer Science},
    volume = {1343},
    editor = {Y. Ishikawa <I>et al.</I>},
    publisher = {Springer-Verlag},
    year = {1997},
    pages = {1-8},
    url = {http://www-cse.ucsd.edu/users/baden},
    link = {available online}
}

@Article{bsp,
    author = {L. G. Valiant},
    title = {{A Bridging Model for Parallel Computation}},
    journal = {Communications of the ACM},
    volume = {33},
    number = {8},
    month = {August},
    year = {1990},
    pages = {103-11}
}

@Article{nexus,
    author = {I. Foster and C. Kesselman and S. Tuecke},
    title = {{The Nexus Approach to Integrating Multithreading and 
	      Communication}},
    journal = {Journal of Parallel and Distributed Computing},
    volume = {37},
    month = {August},
    year = {1996},
    pages = {70-82}
}

@InProceedings{taxonomy,
    author = {W. W. Gropp and E. L. Lusk},
    title = {{A Taxonomy of Programming Models for Symmetric Multiprocessors
	      and SMP clusters}},
    booktitle = {Proceedings of Programming Models for Massively Parallel
		 Computers 1995},
    address = {Berlin, Germany},
    month = {October},
    year = {1995},
    pages = {2-7}
}

@InProceedings{chant,
    author = {M. Haines and D. Cronk and P. Mehrotra},
    title = {{On the Design of Chant: A Talking Threads Package}},
    booktitle = {Proceedings of Supercomputing 1994},
    address = {Washington, D.C.},
    month = {November},
    year = {1994},
    pages = {350-9}
}

@InProceedings{logp-metric,
    author = {R. P. Martin and A. M. Vahdat and D. E. Culler and 
 	      T. E. Anderson},
    title = {{Effects of Communication Latency, Overhead, and Bandwidth 
 	      in a Cluster Architecture}},
    booktitle = {Proceedings of the 24th International Symposium on Computer
		 Architecture},
    address = {Denver, Colorado},
    month = {June},
    year = {1997},
    pages = {85-97}
}

@InProceedings{micro-bench,
    author = {R. H. Saavedra},
    title = {{Micro Benchmark Analysis of the KSR1}},
    booktitle = {Proceedings of Supercomputing 1993},
    address = {Portland, Oregon},
    month = {November},
    year = {1993},
    pages = {202-13}
}

@InProceedings{gigaplane,
    author = {A. Singhal and D. Broniarczyk and F. Cerauskis and J. Price and
	      L. Yuan and C. Cheng and D. Doblar and S. Fosth and 
	      N. Agarwal and K. Harvey and E. Hagersten and B. Liencres},
    title = {{Gigaplane: A High Performance Bus for Large SMPs}},
    booktitle = {Proceedings of Hot Interconnects IV},
    address = {Stanford, California},
    month = {August},
    year = {1996},
    pages = {41-52}
}

@InProceedings{gigaplane-xb,
    author = {A. Charlesworth and A. Phelps and R. Williams and G. Gilbert},
    title = {{Gigaplane-XB: Extending the Ultra Enterprise Family}},
    booktitle = {Proceedings of Hot Interconnects V},
    address = {Stanford, California},
    month = {August},
    year = {1997},
    pages = {97-112}
}

@Article{super-trend,
    author = {P. R. Woodward},
    title = {{Perspectives on Supercomputing: Three Decades of Change}},
    journal = {IEEE Computer},
    volume = {29},
    month = {October},
    year = {1996},
    pages = {99-111}
}

@InProceedings{multi-grain,
    author = {D. Yeung and J. Kubiatowicz and A. Agarwal},
    title = {{MGS: A Multigrain Shared Memory System}},
    booktitle = {Proceedings of the 23rd International Symposium on Computer
		 Architecture},
    address = {Philadelphia, Pennsylvania},
    month = {May},
    year = {1996},
    pages = {44-55}
}


%%
%% wait-free algorithms
%%
%% Herlihy's universality and general construction papers
%% 

@InProceedings{universal,
    author = {M. P. Herlihy},
    title = {{Impossibility and Universality Results for Wait-Free
              Synchronization}},
    booktitle = {Proceedings of the 7th Symposium on 
		 Principles of Distributed Computing},
    address = {Toronto, Ontario, Canada},
    month = {August}, 
    year = {1988},
    pages = {276-290}
}

@Article{herlihy,
    author = {M. Herlihy},
    title = {{A Methodology for Implementing Highly Concurrent Data Objects}},
    journal = {ACM Transactions on Programming Languages and Systems},
    volume = {15},
    number = {5},
    month = {November},
    year = {1993},
    pages = {745-70}
}


%%
%% non-blocking algorithms
%%
%% synthesis and cache kernels
%% Michael and Scott's queue algorithm
%% Michael and Scott's comparison with preemption-safe locks
%% 

@TechReport{synthesis,
    author = {H. Massalin and C. Pu},
    title = {{A Lock-free Multiprocessor OS Kernel}},
    institution = {Columbia University},
    number = {CUCS-005-91},
    month = {June},
    year = {1991}
}

@InProceedings{cache-kernel,
    author = {M. Greenwald and D. Cheriton},
    title = {{The Synergy between Non-Blocking Synchronization and 
 	      Operating System Structure}},
    booktitle = {Proceedings of the 2nd Symposium on Operating Systems 
                 Design and Implementation},
    address = {Seattle, Washington},
    month = {October},
    year = {1996},
    pages ={123-36}
}

@InProceedings{queue-alg,
    author = {M. M. Michael and M. L. Scott},
    title = {{Simple, Fast, and Practical Non-Blocking and Blocking 
 	      Concurrent Queue Algorithms}},
    booktitle = {Proceedings of the 15th Symposium on Principles of 
                 Distributed Computing},
    address = {Philadelphia, Pennsylvania},
    month = {May},
    year = {1996},
    pages = {267-75}
}

@InProceedings{no-block-perf,
    author = {M. M. Michael and M. L. Scott},
    title = {{Relative Performance of Preemption-Safe Locking and
      	      Non-Blocking Synchronization on Multiprogrammed
              Shared Memory Multiprocessors}},
    booktitle = {Proceedings of the 11th International Parallel Processing 
		 Symposium},
    address = {Geneva, Switzerland},
    month = {April},
    year = {1997},
    pages = {267-73}
}



%%
%% lock-free algorithms
%%
%% NYU Ultracomputer work
%% remote queue and FM algorithms
%% 

@Article{ultra-q,
    author = {A. Gottlieb and B. D. Lubachevsky and L. Rudolph},
    title = {{Basic Techniques for the Efficient Coordination of Very Large
	      Numbers of Cooperating Sequential Processors}},
    journal = {ACM Transactions on Programming Languages and Systems},
    volume = {5},
    number = {2},
    month = {April},
    year = {1983},
    pages = {164-89}
}

@PhDThesis{rudolph,
    author = {L. Rudolph},
    title = {Software Structures for Ultraparallel Computing},
    school = {New York University},
    month = {December},
    year = {1981}
}

@InProceedings{remote-q,
    author = {E. A. Brewer and F. T. Chong and L. T. Liu and
              S. D. Sharma and J. D. Kubiatowicz},
    title = {{Remote Queues: Exposing Message Queues for Optimization and 
	      Atomicity}},
    booktitle = {Proceedings of the 7th Symposium on Parallel Algorithms and 
		 Architectures},
    address = {Santa Barbara, California},
    month = {July},
    year = {1995},
    pages = {42-53}
}

@InProceedings{cm5-t3d,
    author = {V. Karamcheti and A. A. Chien},
    title = {{A Comparison of Architectural Support for Messaging
              in the TMC CM-5 and the Cray T3D}},
    booktitle = {Proceedings of the 22nd International Symposium on Computer
		 Architecture},
    address = {Santa Margherita Ligure, Italy},
    month = {June},
    year = {1995},
    pages = {298-307}
}

@InProceedings{valois,
    author = {J. D. Valois},
    title = {{Implementing Lock-Free Queues}},
    booktitle = {Proceedings of 7th International Conference on Parallel and 
		 Distributed Computing Systems},
    address = {Las Vegas, Nevada},
    month = {October},
    year = {1994},
    pages = {64-9}
}


%%
%% spin lock algorithms
%%
%% ticket/bakery locks
%% Anderson locks
%% Mellor-Crummey and Scott survey paper
%%

@Article{reed,
    author = {D. P. Reed and R. K. Kanodia},
    title = {{Synchronization with Eventcounts and Sequencers}},
    journal = {Communications of the ACM},
    volume = {22},
    number = {2},
    month = {February},
    year = {1979}, 
    pages = {115-23}
}

@Article{anderson,
    author = {T. E. Anderson},
    title = {{The Performance of a Spin Lock Alternative for Shared-Memory
              Multiprocessors}},
    journal = {IEEE Transactions on Parallel and Distributed Systems},
    volume = {1},
    number = {1},
    month = {January},
    year = {1990},
    pages = {6-16}
}

@Article{mcs,
    author = {J. M. Mellor-Crummey and M. L. Scott},
    title = {{Algorithms for Scalable Synchronization on Shared-Memory
	      Multiprocessors}},
    journal = {ACM Transactions on Computer Systems},
    volume = {9},
    number = {1},
    month = {Feb.},
    year = {1991},
    pages = {21-65}
}

@InProceedings{multi-spin,
    author = {R. W. Wisniewski and L. I. Kontothanassis and M. L. Scott},
    title = {{High Performance Synchronization Algorithms for 
              Multiprogrammed Multiprocessors}},
    booktitle = {Proceedings of the 5th Symposium on Principles and Practice
                 of Parallel Programming},
    address = {Santa Barbara, California},
    month = {July},
    year = {1995},
    pages = {199-206}
}


%%
%% my conference papers from my thesis
%%

@InProceedings{mp-synch,
    author = {S. S. Lumetta and D. E. Culler},
    title = {{Managing Concurrent Access for Shared Memory Active Messages}},
    booktitle = {Proceedings of the International Parallel Processing
		 Symposium},
    address = {Orlando, Florida},
    month = {March},
    year = {1998},
    pages = {272-8}
}

@InProceedings{multi-protocol,
    author = {S. S. Lumetta and A. M. Mainwaring and D. E. Culler},
    title = {{Multi-Protocol Active Messages on a Cluster of SMP's}},
    booktitle = {Proceedings of SC97: High Performance Networking and 
		 Computing},
    address = {San Jose, California},
    month = {November}, 
    year = {1997}
}


%%
%% combining networks
%%
%% Rudolph, Kruskal, etc.
%%

@InProceedings{rmw-combine,
    author = {C. P. Kruskal and L. Rudolph and M. Snir},
    title = {{Efficient Synchronization on Multiprocessors with Shared
              Memory}},
    booktitle = {Proceedings of the 5th Symposium on Principles
		 of Distributed Computing},
    address = {Calgary, Alberta, Canada},
    month = {August},
    year = {1986},
    pages = {218-28}
}


%%
%% queue models
%%
%% Kelly
%%

@Book{kelly,
    author = {F. P. Kelly},
    title = {Reversability and Stochastic Networks},
    publisher = {John Wiley and Sons Ltd.},
    year = {1979}
}


%%
%% marketing and technical documents for convergence argument
%%    and other hardware specifications
%% 
%% IBM S/390 Parallel Enterprise Server (Generation 5)
%% Technology road map
%% Parallel Sysplex article
%% UltraSPARC-I data sheet
%%

@Booklet{s390,
    key = {IBM},
    author = {International Business Machines Corporation},
    title = {{S/390 Parallel Enterprise Server and OS/390 Reference
              Guide}},
    month = {May},
    year = {1998}
}

@Unpublished{ibm-roadmap,
    key = {IBM},
    title = {{IBM S/390: The Defining Standard of Enterprise Computing, 
	      Today and Tomorrow, International Business Machines 
              Corporation}},
    month = {May},
    year = {1998},
    note = {Document #GF22-5043-00.},
    url = {http://www.s390.ibm.com/marketing/gf225043.html},
    link = {available online}
}
    
@Article{par-sysplex,
    author = {J. M. Nick and B. B. Moore and J.-Y. Chung and N. S. Bowen},
    title = {{S/390 Cluster Technology: Parallel Sysplex}},
    journal = {IBM Systems Journal},
    volume = {36},
    number = {2},
    year = {1997},
    pages = {172-202}
}

@Booklet{ultra-datasheet,
    key = {SME},
    author = {Sun Microsystems Computer Corporation},
    title = {{UltraSPARC-I Data Sheet: First Generation SPARC v9 64-Bit
              Microprocessor with VIS}},
    month = {July},
    year = {1997},
    note = {Document #STP1030A.},
    url = {http://www.sun.com/microelectronics/datasheets/stp1030a/},
    link = {available online}
}


%%
%% linearizability
%%
%% Herlihy and Wing
%%

@Article{linearizability,
    author = {M. P. Herlihy and J. M. Wing},
    title = {{Linearizability: A Correctness Condition for Concurrent
              Objects}},
    journal = {ACM Transactions on Programming Languages and Systems},
    volume = {12},
    number = {3},
    month = {July},
    year = {1990},
    pages ={463-92}
}


%%
%% Assorted NOW papers
%%
%% case for NOW, mapper paper, scheduling results, glunix, Andrea's thesis
%%

@Article{casenow,
    author = {T. E. Anderson and D. E. Culler and D. A. Patterson and
              the NOW Team},
    title = {{A Case for NOW (Networks of Workstations)}},
    journal = {IEEE Micro},
    volume = {15},
    number = {1},
    month = {February},
    year = {1995},
    pages = {54-64}
}

@InProceedings{schedule-skew,
    author = {R. H. Arpaci and A. C. Dusseau and A. H. Vahday and L. T. Liu
              and T. E. Anderson and D. A. Patterson},
    title = {{The Interaction of Parallel and Sequential Workloads on a 
              Network of Workstations}},
    booktitle = {Proceedings of SIGMETRICS Joint International Conference on
                 Measurement and Modeling of Computer Systems},
    address = {Ottawa, Canada},
    month = {May},
    year = {1995},
    pages = {267-78}
}

@InProceedings{mapper,
    author = {A. M. Mainwaring and B. N. Chun and S. Schleimer and 
              D. Wilkerson},
    title = {{System Area Network Mapping}},
    booktitle = {Proceedings of the 9th Symposium on Parallel
                 Algorithms and Architectures},
    address = {Newport, Rhode Island},
    month = {May},
    year = {1997},
    pages = {116-26}
}

@InProceedings{sysadmin,
    author = {E. Anderson and D. A. Patterson},
    title = {{Extensible, Scalable Monitoring for Clusters of
              Computers}},
    booktitle = {Proceedings of the 11th Systems Administration
                 Conference (LISA'97)},
    address = {San Diego, California},
    month = {October},
    year = {1997},
    pages = {9-16}
}

@InProceedings{scheduling,
    author = {A. C. Arpaci-Dusseau and D. E. Culler and A. M. Mainwaring},
    title = {{Scheduling with Implicit Information in Distributed
              Systems}},
    booktitle = {Proceedings of the SIGMETRICS'98/PERFORMANCE'98 Joint
                 International Conference on Measurement and Modeling
                 of Computer Systems},
    address = {Madison, Wisconsin},
    month = {June}, 
    year = {1998},
    pages = {233-43}
}

@Article{glunix,
    author = {D. P. Ghormley and D. Petrou and S. H. Rodrigues and
              A. M. Vahdat and T. E. Anderson},
    title = {{GLUnix: a Global Layer Unix for a Network of
              Workstations}},
    journal = {Software---Practice and Experience},
    volume = {28},
    number = {9},
    month = {July},
    year = {1998},
    pages = {929-61}
}

@PhDThesis{dusseau,
    author = {A. C. Arpaci-Dusseau},
    title = {Implicit Coscheduling: Coordinated Scheduling with Implicit 
              Information in Distributed Systems},
    school = {University of California at Berkeley},
    month = {December},
    year = {1998}
}


%%
%% CC-NUMA architectures
%%
%% Stanford DASH
%% SGI Origin
%%

@InProceedings{DASH,
    author = {D. E. Lenoski and J. Laudon and K. Gharachorloo and
              A. Gupta and J. Hennessy},
    title = {{The Directory-Based Cache Coherence Protocol for the
              DASH Multiprocessor}},
    booktitle = {Proceedings of the 17th International Symposium on
                 Computer Architecture},
    address = {Seattle, Washington},
    month = {May},
    year = {1990},
    pages = {148-59}
}

@InProceedings{sting,
    author = {T. Lovett and R. Clapp},
    title = {{STiNG: A CC-NUMA Computer System for the Commercial 
              Marketplace}},
    booktitle = {Proceedings of the 23rd International Symposium on Computer
		 Architecture},
    address = {Philadelphia, Pennsylvania},
    month = {May},
    year = {1996},
    pages = {308-17}
}

@InProceedings{exemplar,
    author = {T. Brewer and G. Astfalk},
    title = {{The Evolution of the HP/Convex Exemplar}},
    booktitle = {Proceedings of COMPCON Spring '97},
    address = {San Jose, California},
    month = {February},
    year = {1997},
    pages = {81-6}
}

@InProceedings{origin,
    author = {J. Laudon and D. E. Lenoski},
    title = {{The SGI Origin: A ccNUMA Highly Scalable Server}},
    booktitle = {Proceedings of the 24th International Symposium on
                 Computer Architecture},
    address = {Denver, Colorado},
    month = {June},
    year = {1997},
    pages = {241-51}
}

@InProceedings{origin-fault,
    author = {K. Ghosh and A. J. Christie},
    title = {{Communication Across Fault-Containment Firewalls on the 
              SGI Origin}},
    booktitle = {Proceedings of the 4th International Symposium on
                 High-Performance Computer Architecture},
    address = {Las Vegas, Nevada},
    month = {February},
    year = {1998},
    pages = {277-87}
}



%%
%% FLASH/Hive related papers
%%

@InProceedings{FLASH,
    author = {J. Heinlein and K. Gharachorloo and S. Dresser and A. Gupta},
    title = {{Integration of Message Passing and Shared Memory in the
              Stanford FLASH Multiprocessor}},
    booktitle = {Proceedings of the 6th International Conference on 
                 Architectural Support for Programming Languages and 
                 Operating Systems},
    address = {San Jose, California},
    month = {November},
    year = {1994},
    pages = {38-50}
}

@InProceedings{hive,
    author = {J. Chapin and M. Rosenblum and S. Devine and T. Lahiri
             and D. Teodosiu and A. Gupta},
    title = {{Hive: Fault Containment for Shared-Memory Multiprocessors}},
    booktitle = {Proceedings of the 15th Symposium on Operating
                 Systems Principles},
    address = {Copper Mountain Resort, Colorado},
    month = {December},
    year = {1995},
    pages = {12-25}
}

@InProceedings{flash-hive,
    author = {D. Teodosiu and J. Baxter and K. Govil and J. Chapin and
              M. Rosenblum and M. Horowitz},
    title = {{Hardware Fault Containment in Scalable Shared-Memory
              Multiprocessors}}, 
    booktitle = {Proceedings of the 24th International Symposium on
                 Computer Architecture},
    address = {Denver, Colorado},
    month = {June},
    year = {1997},
    pages = {73-84}
}


%%
%% textbooks
%% David and J.P.'s book
%% Patterson and Hennessy undergrad book
%%

@Book{culler-singh,
    author = {D. E. Culler and J. P. Singh and with A. Gupta},
    title = {Parallel Computer Architecture: A Hardware/Software Approach},
    publisher = {Morgan Kaufmann},
    year = {1998}
}

@Book{ph-hsi,
    author = {D. A. Patterson and J. L. Hennessy},
    title = {Computer Organization and Design: The Hardware/Software 
              Interface},
    publisher = {Morgan Kaufmann},
    edition = {2nd},
    year = {1998}
}
 


%%
%% FM-QoS
%%

@InProceedings{fm-qos,
    author = {K. Connelly and A. A. Chien},
    title = {{FM-QoS: Real-time Communication using Self-synchronizing
              Schedules}},
    booktitle = {Proceedings of SC97: High Performance Networking and 
		 Computing},
    address = {San Jose, California},
    month = {November}, 
    year = {1997}
}



%%
%% IRAM--vectors returning inside microprocessors
%%

@Article{IRAM,
    author = {D. A. Patterson and T. E. Anderson and N. Cardwell and
              R. Fromm and K. Keeton and C. Kozyrakis and R. Thomas
              and K. Yelick},
    title = {{A Case for Intelligent RAM: IRAM}},
    journal = {IEEE Micro},
    volume = {17},
    number = {2},
    month = {April},
    year = {1997},
    pages = {29-38}
}


%%
%% Cycle-stealing via process migration
%%
%% early Condor and Sprite papers
%%
%% process migration in Sprite
%% process migration in Condor
%% batch processing in Condor
%%

@InProceedings{sprite,
    author = {F. Douglis and J. K. Ousterhout},
    title = {{Process Migration in the Sprite Operating System}},
    booktitle = {Proceedings of the 7th International Conference on
                 Distributed Computing Systems},
    address = {Berlin, West Germany},
    month = {September},
    year = {1987},
    pages = {18-25}
}

@InProceedings{condor,
    author = {M. J. Litzkow and M. Livny and M. W. Mutka},
    title = {{Condor---A Hunter of Idle Workstations}},
    booktitle = {Proceedings of the 8th International Conference on
                 Distributed Computing Systems},
    address = {San Jose, California},
    month = {June},
    year = {1988},
    pages = {104-11}
}

@InProceedings{condor-batch,
    author = {M. J. Litzkow and M. Livny},
    title = {{Making Workstations a Friendly Environment for Batch Jobs}},
    booktitle = {Proceedings of the 3rd Workshop on Workstation
                 Operating Systems},
    address = {Key Biscayne, Florida},
    month = {April},
    year = {1992},
    pages = {62-7}
}


%%
%% older scheduling efforts
%%
%% Ousterhout's original coscheduling paper
%% LLNL gang scheduling (recent report)
%%

@InProceedings{coscheduling,
    author = {J. K. Ousterhout},
    title = {{Scheduling Techniques for Concurrent Systems}},
    booktitle = {Proceedings of the 3rd International Conference on 
                 Distributed Computing Systems},
    address = {Miami/Fort Lauderdale, Florida},
    month = {October},
    year = {1982},
    pages = {22-30}
}

@InProceedings{llnl-gang,
    author = {Morris A. Jette},
    title = {{Performance Characteristics of Gang Scheduling in 
              Multiprogrammed Environments}},
    booktitle = {Proceedings of SC97: High Performance Networking and 
		 Computing},
    address = {San Jose, California},
    month = {November}, 
    year = {1997}
}


%%
%% Pfister's cluster book
%%

@Book{pfister,
    author = {G. F. Pfister},
    title = {In Search of Clusters: The Ongoing Battle in Lowly
              Parallel Computing},
    publisher = {Prentice Hall},
    edition = {2nd},
    year = {1998}
}


%%
%% Donald Yeung's thesis on multigrain shared memory
%%

@PhDThesis{yeung,
    author = {D. Yeung},
    title = {Multigrain Shared Memory},
    school = {Massachusetts Institute of Technology},
    month = {February},
    year = {1998}
}


%%
%% Titanium -- a programming language for clusters
%%

@InProceedings{titanium,
    author = {K. Yelick and L. Semenzato and G. Pike and C. Miyamoto
              and B. Liblit and A. Krishnamurthy and P. Hilfinger
              and S. Graham and D. Gay and P. Colella and A. Aiken},
    title = {{Titanium: A High-Performance Java Dialect}},
    booktitle = {Proceedings of the Workshop on Java for
                 High-Performance Network Computing},
    address = {Stanford, California},
    month = {February},
    year = {1998}
}

@Article{optimize,
    author = {A. Krishnamurthy and K. Yelick},
    title = {{Analyses and Optimizations for Shared Address Space Programs}},
    journal = {Journal of Parallel and Distributed Computing},
    volume = {38},
    number = {2},
    month = {November},
    year = {1996},
    pages = {130-44}
}



%%
%% MPI literature
%%
%% specification?
%%

@Unpublished{mpi-spec,
    key = {MPI},
    title = {{MPI-2: Extensions to the Message-Passing Interface}},
    month = {July},
    year = {1997},
    url = {http://www.mpi-forum.org/},
    link = {available from the Message Passing Interface Forum}
}
    


%%
%% DSM literature
%%
%% Cashmere-2L, Shasta, and SMP-Shasta
%%
%% I need Blizzard-S; see the WRL TR 96/2 on Shasta ref #18
%%

@InProceedings{hudak-li,
    author = {K. Li and P. Hudak},
    title = {{Memory Coherence in Shared Virtual Memory Systems}},
    booktitle = {Proceedings of the 5th Symposium on Principles
		 of Distributed Computing},
    address = {Calgary, Alberta, Canada},
    month = {August},
    year = {1986},
    pages = {229-39}
}

@InProceedings{shasta,
    author = {D. J. Scales and K. Gharachorloo and C. Thekkath},
    title = {{Shasta: A Low Overhead, Software-Only Approach for Supporting
              Fine-Grain Shared Memory}},
    booktitle = {Proceedings of the 7th International Conference on 
                 Architectural Support for Programming Languages and 
                 Operating Systems},
    address = {Cambridge, Massachusetts},
    month = {October},
    year = {1996},
    pages = {174-85},
    note = {Also available as DEC WRL Research Report 96/2.}
}

@InProceedings{cashmere,
    author = {L. Kontothanassis and G. Hunt and R. Stets and 
              N. Hardavellas and M. Cierniak and S. Parthasarathy and
              Meira, Jr., W. and S. Dwarkadas and M. Scott},
    title = {{VM-Based Shared Memory on Low-Latency, Remote-Memory-Access
              Networks}},
    booktitle = {Proceedings of the 24th International Symposium on
                 Computer Architecture},
    address = {Denver, Colorado},
    month = {June},
    year = {1997},
    pages = {157-69}
}

@InProceedings{cashmere-2l,
    author = {R. Stets and S. Dwarkadas and N. Hardavellas and G. Hunt and 
              L. Kontothanassis and S. Parthasarathy and M. Scott},
    title = {{Cashmere-2L: Software Coherent Shared Memory on a Clustered
              Remote-Write Network}},
    booktitle = {Proceedings of the 16th Symposium on Operating Systems
                 Principles},
    address = {Saint Malo, France},
    month = {October},
    year = {1997},
    pages = {170-83}
}

@InProceedings{smp-shasta,
    author = {D. J. Scales and K. Gharachorloo and A. Aggarwal},
    title = {{Fine-Grain Software Distributed Shared Memory on SMP Clusters}},
    booktitle = {Proceedings of the 4th International Symposium on
                 High-Performance Computer Architecture},
    address = {Las Vegas, Nevada},
    month = {February},
    year = {1998},
    pages = {125-36},
    note = {Also available as DEC WRL Research Report 97/3.}
}

@InProceedings{smp-brazos,
    author = {E. Speight and J. K. Bennett},
    title = {{Using Multicast and Multithreading to Reduce Communication in
              Software DSM Systems}},
    booktitle = {Proceedings of the 4th International Symposium on
                 High-Performance Computer Architecture},
    address = {Las Vegas, Nevada},
    month = {February},
    year = {1998},
    pages = {312-22}
}


%%
%% algorithms for applications
%%

@InProceedings{sample-sort,
    author = {G. Blelloch and C. Leiserson and B. Maggs},
    title = {{A Comparison of Sorting Algorithms for the Connection Machine
              CM-2}},
    booktitle = {Proceedings of the 3rd Symposium on Parallel
                 Algorithms and Architectures},
    address = {Hilton Head, South Carolina},
    month = {July},
    year = {1991},
    pages = {3-16}
}

@InCollection{con-comp-algo,
    author =    {A. Krishnamurthy and S. S. Lumetta and D. E. Culler and
                 K. Yelick},
    title =     {Connected Components on Distributed Memory Machines},
    booktitle = {Parallel Algorithms: Third DIMACS Implementation Challenge},
    editor =    {Sandeep Bhatt},
    series =    {DIMACS Series in Discrete Mathematics and Theoretical
                 Computer Science},
    volume =    {30},
    year =      {1997},
    pages =     {1-21}
}

@Book{numerical-recipe,
    author = {W. H. Press and S. A. Teukolsky and W. T. Vetterling and
              B. P. Flannery},
    title = {Numerical Recipes in C: The Art of Scientific Computing},
    publisher = {Cambridge University Press},
    edition = {2nd},
    month = {January},
    year = {1993}
}

@TechReport{em3d-algo,
    author = {N. K. Madsen},
    title = {{Divergence Preserving Discrete Surface Integral Methods for
              Maxwell's Curl Equations Using Non-Orthogonal Unstructured
              Grids}},
    institution = {NASA RIACS},
    number = {92.04},
    month = {February},
    year = {1992}
}


%%
%% implementations for applications
%%

@InBook{sort-logp,
    author = {D. E. Culler and A. C. Dusseau and R. P. Martin and 
              K. E. Schauser},
    title = {Fast Parallel Sorting under LogP: from Theory to Practice},
    booktitle = {Portability and Performance for Parallel Processing},
    publisher = {John Wiley and Sons},
    year = {1993},
    chapter = {4},
    pages = {71-98}
}

@InProceedings{con-comp,
    author =    {S. S. Lumetta and A. Krishnamurthy and D. E. Culler},
    title =     {{Towards Modeling the Performance of a Fast Connected
                  Components Algorithm on Parallel Machines}},
    booktitle = {Proceedings of Supercomputing 1995},
    month =     {December},
    year =      {1995},
    address =   {San Diego, California}
}


%%
%% migratory memory/coherence control
%%
%% two papers on extending coherence protocols to dynamically identify
%% migratory data, cooperative shared memory, and Tempest
%%

@InProceedings{cox-fowler,
    author = {A. L. Cox and R. J. Fowler},
    title = {{Adaptive Cache Coherency for Detecting Migratory Shared Data}},
    booktitle = {Proceedings of the 20th International Symposium on Computer
		 Architecture},
    address = {San Diego, California},
    month = {May},
    year = {1993},
    pages = {98-108}
}

@InProceedings{dash-migrate,
    author = {P. Stenstr&#246m and M. Brorsson and L. Sandberg},
    title = {{An Adaptive Cache Coherence Protocol Optimized for 
              Migratory Sharing}},
    booktitle = {Proceedings of the 20th International Symposium on Computer
		 Architecture},
    address = {San Diego, California},
    month = {May},
    year = {1993},
    pages = {109-18}
}

@InProceedings{csm,
    author = {M. D. Hill and J. R. Larus and S. K. Reinhardt and D. A. Wood},
    title = {{Cooperative Shared Memory: Software and Hardware for Scalable
              Multiprocessors}},
    booktitle = {Proceedings of the 5th International Conference on 
                 Architectural Support for Programming Languages and 
                 Operating Systems},
    address = {Boston, Massachusetts},
    month = {October},
    year = {1992},
    pages = {262-73}
}

@InProceedings{tempest,
    author = {S. K. Reinhardt and J. R. Larus and D. A. Wood},
    title = {{Tempest and Typhoon: User-Level Shared Memory}},
    booktitle = {Proceedings of the 21st International Symposium on
                 Computer Architecture},
    address = {Chicago, Illinois},
    month = {April},
    year = {1994},
    pages = {325-36}
}



%%
%% Cedar 
%%

@InProceedings{cedar,
    author = {D. Kuck and E. Davidson and D. Lawrie and A. Sameh and
              C.-Q. Zhu and A. Veidenbaum and J. Konicek and P. Yew
              and K. Gallivan and W. Jalby and H. Wijshoff and
              R. Bramley and U. M. Yang and P. Emrath and D. Padua and
              R. Eigenmann and J. Hoeflinger and G. Jaxon and Z. Li
              and T. Murphy and J. Andrews and S. Turner},
    title = {{The Cedar System and an Initial Performance Study}},
    booktitle = {Proceedings of the 20th International Symposium on Computer
		 Architecture},
    address = {San Diego, California},
    month = {May},
    year = {1993},
    pages = {213-23}
}



%%
%% Cilk
%%
%% cilk-5 implementation, non-blocking deque, and performance of n-b deque
%%

@InProceedings{cilk-5,
    author = {M. Frigo and C. E. Leiserson and K. H. Randall},
    title = {{The Implementation of the Cilk-5 Multithreaded Language}},
    booktitle = {Proceedings of Programming Language Design and 
                 Implementation},
    address = {Montreal, Quebec, Canada},
    month = {June},
    year = {1998},
    pages = {212-23}
}

% this was the citation from their home page, but I can't find it in
% inspec...the paper certainly exists on the home pages...
@InProceedings{arora,
    author = {N. S. Arora and R. D. Blumofe and C. G. Plaxton},
    title = {{Thread Scheduling for Multiprogrammed Multiprocessors}},
    booktitle = {Proceedings of the 10th Symposium on Parallel Algorithms and 
		 Architectures},
    address = {Puerto Vallarta, Mexico},
    month = {June},
    year = {1998},
    pages = {119-29}
}

@TechReport{blumofe,
    author = {R. D. Blumofe and D. Papadopoulos},
    title = {{The Performance of Work Stealing in Multiprogrammed 
              Environments}},
    institution = {University of Texas at Austin},
    number = {CS-TR-98-13},
    month = {May},
    year = {1998}
}


%%
%% moving NI's higher into the memory hierarchy (also integrating
%% shared memory and message-passing)
%%
%% Kubi's thesis (Alewife), Henry and Joerg, Star-T Voyager
%% survey by mukherjee and hill
%%

@PhDThesis{kubi,
    author = {J. D. Kubiatowicz},
    title = {Integrated Shared-Memory and Message-Passing Communication in
              the Alewife Multiprocessor},
    school = {Massachusetts Institute of Technology},
    month = {February},
    year = {1998}
}

@InProceedings{henry,
    author = {C. F. Joerg and D. S. Henry},
    title = {{A Tightly Coupled Processor-Network Interface}},
    booktitle = {Proceedings of the 5th International Conference on 
                 Architectural Support for Programming Languages and 
                 Operating Systems},
    address = {Boston, Massachusetts},
    month = {October},
    year = {1992},
    pages = {111-22}
}

@InProceedings{star-t-voyager,
    author = {B. S. Ang and D. Chiou and D. L. Rosenband and M. Ehrlich and
              L. Rudolph and Arvind},
    title = {{StarT-Voyager: A Flexible Platform for Exploring Scalable 
              SMP Issues}},
    booktitle = {Proceedings of SC98: High Performance Networking and 
		 Computing},
    address = {Orlando, Florida},
    month = {November}, 
    year = {1998}
}

@InProceedings{mukherjee,
    author = {S. S. Mukherjee and M. D. Hill},
    title = {{A Case for Making Network Interfaces Less Peripheral}},
    booktitle = {Proceedings of Hot Interconnects V},
    address = {Stanford, California},
    month = {August},
    year = {1997},
    pages ={21-6}
}


%%
%% MESI protocol
%%

@InProceedings{MESI,
    author = {M. S. Papamarcos and J. H. Patel},
    title = {{A Low-Overhead Coherence Solution for Multiprocessors
              with Private Cache Memories}},
    booktitle = {Proceedings of the 11th International Symposium on
                 Computer Architecture},
    address = {Ann Arbor, Michigan},
    month = {June},
    year = {1984},
    pages = {348-54}
}


%%
%% other multi-protocol work
%%
%% Nexus and MPI-StarT
%%

@InProceedings{nexus-multi,
    author = {I. Foster and J. Geisler and C. Kesselman and S. Tuecke},
    title = {{Managing Multiple Communication Methods in High-Performance 
	      Networked Computing Systems}},
    booktitle = {Journal of Parallel and Distributed Computing},
    volume = {40},
    month = {January},
    year = {1997},
    pages = {35-48}
}

@InProceedings{mpi-start,
    author = {P. J. Husbands and J. C. Hoe},
    title = {{MPI-StarT: Delivering Network Performance to Numerical 
              Applications}},
    booktitle = {Proceedings of SC98: High Performance Networking and 
		 Computing},
    address = {Orlando, Florida},
    month = {November}, 
    year = {1998}
}


%%
%% DSM consistency models
%%
%% release consistency/RC (DASH)
%% lazy release consistency/LRC (TreadMarks)
%% automatic update release consistency/AURC (Shrimp)
%% scope consistency (Shrimp)
%% software scope consistency (Brazos)
%%

@InProceedings{RC,
    author = {K. Gharachorloo and D. Lenoski and J. Laudon and P. Gibbons and
              A. Gupta and J. L. Hennessy},
    title = {{Memory Consistency and Event Ordering in Scalable Shared-Memory
              Multiprocessors}},
    booktitle = {Proceedings of the 17th International Symposium on
                 Computer Architecture},
    address = {Seattle, Washington},
    month = {May},
    year = {1990},
    pages = {15-26}
}

@InProceedings{LRC,
    author = {P. Keleher and A. L. Cox and W. Zwaenepoel},
    title = {{Lazy Release Consistency for Software Distributed Shared 
              Memory}},
    booktitle = {Proceedings of the 19th International Symposium on Computer
		 Architecture},
    address = {Gold Coast, Queensland, Australia},
    month = {May},
    year = {1992},
    pages = {13-21}
}

@InProceedings{AURC,
    author = {L. Iftode and C. Dubnicki and E. W. Felten and K. Li},
    title = {{Improving Release-Consistent Shared Virtual Memory Using
              Automatic Update}},
    booktitle = {Proceedings of the 2nd International Symposium on
                 High-Performance Computer Architecture},
    address = {San Jose, California},
    month = {February},
    year = {1996},
    pages = {14-25}
}

@InProceedings{ScS,
    author = {L. Iftode and J. P. Singh and K. Li},
    title = {{Scope Consistency: A Bridge between Release Consistency and
              Entry Consistency}},
    booktitle = {Proceedings of the 8th Symposium on Parallel Algorithms and 
		 Architectures},
    address = {Padua, Italy},
    month = {June},
    year = {1996},
    pages = {277-87}
}

@InProceedings{SScS,
    author = {E. Speight and J. K. Bennett},
    title = {{Brazos: A Third Generation DSM System}},
    booktitle = {Proceedings of the USENIX Windows NT Workshop},
    address = {Seattle, Washington},
    month = {August},
    year = {1997},
    pages = {95-106}
}


%%
%% DEC memory channel
%%

@Article{memory-channel,
    author = {R. B. Gillett and R. Kaufmann},
    title = {{Using the Memory Channel Network}},
    journal = {IEEE Micro},
    volume = {17},
    number = {1},
    month = {February},
    year = {1997},
    pages = {19-25}
}


%%
%% DSM performance papers
%%

@InProceedings{iftode,
    author = {L. Iftode and J. P. Singh and K. Li},
    title = {{Understanding Application Performance on Shared Virtual
              Memory Systems}},
    booktitle = {Proceedings of the 23rd International Symposium on Computer
		 Architecture},
    address = {Philadelphia, Pennsylvania},
    month = {May},
    year = {1996},
    pages = {122-33}
}

@InProceedings{SVM,
    author = {D. Jiang and H. Shan and J. P. Singh},
    title = {{Application Restructuring and Performance Portability on 
 	      Shared Virtual Memory and Hardware-Coherent Multiprocessors}},
    booktitle = {Proceedings of the 6th Symposium on Principles and Practice
                 of Parallel Programming},
    address = {Las Vegas, Nevada},
    month = {June},
    year = {1997},
    pages = {217-29}
}


%%
%% Mach IPC
%%

@InProceedings{mach,
    author = {M. Young and A. Tevanian and R. Rashid and D. Golub and
              J. Eppinger and J. Chew and W. Bolosky and D. Black and
              R. Baron},
    title = {{The Duality of Memory and Communication in the Implementation
              of a Multiprocessor Operating System}},
    booktitle = {Proceedings of the 11th Symposium on Operating Systems
                 Principles},
    address = {Austin, Texas},
    month = {November},
    year = {1987},
    pages = {63-76}
}



%%
%% Seth's thesis
%%

@PhDThesis{goldstein,
    author = {S. C. Goldstein},
    title = {Lazy Threads: Compiler and Runtime Structures for 
              Fine-Grained Parallel Programming},
    school = {University of California at Berkeley},
    month = {June},
    year = {1997}
}



%%
%% autoscheduling
%%

@InCollection{autosched,
    author = {J. E. Moreira and C. D. Polychronopoulos},
    title = {Autoscheduling in a Distributed Shared-Memory Environment},
    booktitle = {Proceedings of the 7th International Workshop on 
                 Languages and Compilers for Parallel Computing},
    series = {Lecture Notes in Computer Science},
    volume = {892},
    editor = {K. Pingali <I>et al.</I>},
    publisher = {Springer-Verlag},
    year = {1994},
    pages = {453-69}
}


%%
%% Girija's scheduling paper
%%

@InProceedings{narlikar,
    author = {G. Narlikar and G. Blelloch},
    title = {{Pthreads for Dynamic and Irregular Parallelism}},
    booktitle = {Proceedings of SC98: High Performance Networking and 
		 Computing},
    address = {Orlando, Florida},
    month = {November}, 
    year = {1998}
}