@string{ BELL     = "Bell System Technical Journal" }
@string{ TOC      = "IEEE Transactions on Computers" }
@string{ COMPCON  = "Proc. of the IEEE Computer Society International Conferrence (COMPCON)"}
@string{ HOTI     = "Proc. of the Symposium on Hot Interconnects"}
@string{ HPCA     = "Proc. of the Symposium on High Performance Computer Architecture"}
@string{ MICRO    = "Proc. of the Annual IEEE/ACM International Symposium on Microarchitecture"}
@string{ ICCD     = "Proc. of the IEEE International Conference on Computer Design"}
@string{ ISCA     = "Proc. of the International Symposium on Computer Architecture"}
@string{ ASPLOS   = "Proc. of the International Conference on Architectural Support for Programming Languages and Operating Systems"}






@comment{ ================================================================== }
@comment{ ============= Imagine, Stanford Streams ========================== }

@inproceedings{ khailany03_scalability,
  author = 	{Brucek Khailany and William J. Dally and Scott Rixner and Ujval J. Kapasi and John D. Owen and Brian Towles},
  title = 	{Exploring the VLSI Scalability of Stream Processors},
  booktitle = 	HPCA,
  pages = 	{153--164},
  year = 	{2003},
  month = 	{February},
  address = 	{Anaheim, California, USA}
}

@article{ khailany01_imagine,
  author = 	{Brucek Khailany and William J. Dally and Scott Rixner and Ujval J. Kapasi and Peter Mattson and Jinyung Namkoong and John D. Owens and Brian Towles and Andrew Chang},
  title = 	{Imagine: Media Processing with Streams},
  journal = 	{IEEE Micro},
  year = 	{2001},
  pages = 	{35--46},
  month = 	{March/April}
}

@article{ kapasi03_imaginecomputer,
  author = 	{Ujval J. Kapasi and Scott Rixner and William J. Dally and Brucek Khailany and Jung Ho Ahn and Peter Mattson and John D. Owens},
  title =       {Programmable Stream Processors},
  journal =     {IEEE Computer},
  year =        {2003},
  month =       {August},
}

@article{ jayasena04_indexedsrf,
  author = 	{N. Jayasena and M. Erez and J.H. Ahn and W.J. Dally},
  title =       {Stream Register Files with Indexed Access},
  journal =     HPCA,
  year =        {2004},
}

@article{ kapasi00_conditionals,
  author = 	{U.J. Kapasi and W.J. Dally and S. Rixner and P. Mattson and J.D. Owens and B. Khailany},
  title =       {Efficient Conditional Operations for Data-parallel Architectures},
  journal =     MICRO,
  year =        {2000},
  month = 	{December},
  pages = 	{159--170}
}

@article{ khailany02_imaginevlsi,
  author = 	{B. Khailany and W.J. Dally and A. Chang and U.J. Kapasi and J. Namkoong and B. Towles},
  title =       {VLSI Design and Verification of the Imagine Processor},
  journal =     ICCD,
  year =        {2002},
  pages = 	{289--296}
}

@phdthesis{ mattson02_thesis,
  author = 	{P. Mattson},
  title =       {A Programming System for the Imagine Media Processor},
  year =        {2002},
  school =	{Stanford University},
}

@inproceedings{ mattson00_commsched,
  author =	{Peter Mattson and William J. Dally and Scott Rixner and Ujval J. Kapasi and John D. Owens},
  title	= 	{Communication Scheduling},
  booktitle = 	ASPLOS,
  year = 	{2000},
  OPTmonth = 	{November}
}

@inproceedings{ kapasi01_streamsched,
  author =	{Ujval J. Kapasi and Peter Mattson and William J. Dally and John D. Owens and Brian Towles},
  title =	{Stream Scheduling},
  booktitle =	{Proc. of the 3rd Workshop on Media and Streaming Processors},
  pages = 	{101--106},
  year = 	{2001},
  OPTaddress = 	{Austin, TX},
  OPTmonth = 	{Dec. 2},
  url = 	{citeseer.nj.nec.com/kapasi01stream.html} }

@phdthesis{ kapasi_thesis,
  author = 	{Ujval J. Kapasi},
  title  = 	{Conditional Techniques for Stream Processing Kernels},
  school = 	{Stanford University},
  year   = 	{to be published}
}








@comment{ ================================================================== }
@comment{ ============= Compilers ========================================== }

@article{ loveman77_stripmining,
  author = 	{David B. Loveman},
  title = 	{Program Improvement by Source-to-Source Transformation},
  journal = 	{Journal of the ACM},
  volume = 	{24},
  number = 	{1},
  pages = 	{121-145},
  month = 	{January},
  year = 	{1977}
}

@misc{ gcc,
  title = 	{Gnu Compiler Collection},
  note = 	{http://gnu.gcc.org}
}

@misc {tendra,
  title = 	{The TenDRA Project},
  note = 	{http://www.tendra.org/}
}

@misc{ suif1,
  title = 	{SUIF 1.x Compiler System},
  note = 	{http://suif.stanford.edu/suif/suif1/}
}

@misc{ suif2,
  title = 	{SUIF 2 Compiler System},
  note = 	{http://suif.stanford.edu/suif/suif2/}
}

@misc{ open64,
  title = 	{Open64 Compiler},
  note = 	{http://sourceforge.net/projects/open64/}
}

@misc{ orc,
  title = 	{Open Research Compiler for Itanium$^{TM}$ Processor Family},
  note = 	{http://ipf-orc.sourceforge.net/}
}

@unpublished{ metacompiler,
  author = 	{Ben Chelf},
  title = 	{Brook Metacompilation},
  year = 	{2002},
  note = 	{SSS Internal Document}
}

@article{ lam88_swp,
  author = 	{M.S. Lam},
  title = 	{Software Pipelining},
  journal = 	{Proc. of the SIGPLAN Conference on Programming Language Design and Implementation},
  pages = 	{318--328},
  year = 	{1988}
}








@comment{ ================================================================== }
@comment{ ============= Scientific Computing - Apps ======================== }

@techreport{ reed73_trimesh,
  author = 	{W.H. Reed and T.R. Hill},
  title  = 	{Triangular mesh methods for the neutron transport equation},
  institution =	{Los Alamos National Laboratory},
  number =	{LA-UR-73-479},
  address =	{Los Alamos, New Mexico},
  year =	{1973}
}

@article{ cockburn90_fem,
  author = 	{B. Cockburn and  S. Hou and C.W. Shu},
  title  = 	{TVB {Runge-Kutta} Local Projection Discontinuous {Galerkin} Finite Element Method for Conservation Laws IV: The multidimensional case},
  journal = 	{Math. Comp.},
  volume  = 	{54},
  pages   = 	{545--581},
  year    = 	{1990}
}

@article{ jaffre95_fem,
  author = 	{J. Jaffre and C. Johnson and A. Szepessy},
  title = 	{Convergence of the Discontinuous Galerkin Finite Element Method for Hyperbolic Conservation Laws},
  journal = 	{Math. Models and Methods in Appl. Sci.},
  year = 	{1995},
  volume = 	{5},
  number = 	{3},
  pages = 	{367--386}
}

@incollection{ barth99_fem,
  booktitle = 	{Discontinuous Galerkin Methods},
  title  = 	{Simplified Discontinuous {Galerkin} Methods for Systems of Conservation Laws with Convex Extension},
  author = 	{T.J. Barth},
  editor = 	{ Cockburn and Karniadakis and Shu},
  publisher =	{Springer-Verlag},
  address = 	{Heidelberg},
  series  = 	{Lecture Notes in Computational Science and Engineering},
  volume = 	{11},
  year = 	{1999}
}

@article{ darve01_force,
  author = 	{E. Darve and A. Pohorille},
  title = 	{Calculating Free Energies using Average Force},
  journal = 	{Chemical Physics},
  year = 	{2001},
  volume = 	{115},
  number = 	{20},
  pages = 	{9169--9183}
}

@article{ darve02_algo,
  author = 	{E. Darve and M.A. Wilson and A. Pohorille},
  title = 	{Calculating Free Energies using a Scaled-Force Molecular Dynamics Algorithm},
  journal = 	{Molecular Simulation},
  year = 	{2002},
  volume = 	{28},
  number = 	{1--2},
  pages = 	{113--144}
}

@inproceedings{ fatica04_streamflo,
  author = 	{Massimiliano Fatica and Antony Jameson and Juan J. Alonso},
  title = 	{STREAMFLO: an Euler solver for streaming architectures},
  booktitle = 	{submitted to AIAA Conference},
  year = 	{2004},
  address = 	{Reno, Nevada, USA}
}

@article{ jameson95_flo82a,
  author = 	{Antony Jameson},
  title = 	{Analysis and design of numerical schemes for gas dynamics 1. Artificial diffusion, upwind biasing, limiters and their effects on accuracy and multigrid convergence},
  journal = 	{International Journal of Computational Fluid Dynamics},
  volume = 	{Volume 4},
  year = 	{1995},
  pages = 	{171--218}
}

@article{ jameson95_flo82b,
  author = 	{Antony Jameson},
  title = 	{Analysis and design of numerical schemes for gas dynamics 2. Artificial diffusion and discrete shock structure},
  journal = 	{International Journal of Computational Fluid Dynamics},
  volume = 	{Volume 5},
  year = 	{1995},
  pages =	{1--38}
}

@article{ kallinderis94_scatteradd,
  author = 	{Y. Kallinderis and A. Vidwans},
  title = 	{Generic Parallel Adaptive-Grid NavierStokes Algorithm},
  journal = 	{AIAA Journal},
  year = 	{1994},
  volume = 	{32},
  pages = 	{54--61}
}






@comment{ ================================================================== }
@comment{ ============= Networks =========================================== }

@article{ clos53_nonblock,
  author = 	{Charles Clos},
  title = 	{A Study of Non-Blocking Switching Networks},
  journal = 	BELL,
  year = 	{1953},
  volume = 	{32},
  pages = 	{406--424}
}

@article{ leiserson85_fattree,
  author = 	{Charles E. Leiserson},
  title = 	{Fat-Trees: Universal Networks for Hardware Efficient Supercomputing},
  journal = 	TOC,
  year = 	{1985},
  volume = 	{34},
  number = 	{10},
  pages = 	{892--901},
  month = 	{October}
}

@article{ dally91_kncube,
  author = 	{William J. Dally},
  title = 	{Performance Analysis of k-ary n-cube Interconnection Networks},
  journal = 	TOC,
  year = 	{1991},
  volume = 	{39},
  number = 	{6},
  pages = 	{775--785},
  month = 	{June}
}

@inproceedings{ scott96_t3e,
  author = 	{Steven L. Scott and Gregory M. Thorson},
  title = 	{The {C}ray {T3E} Network: {A}daptive Routing in a High Performance {3D} Torus},
  booktitle = 	HOTI,
  pages = 	{147--156},
  year = 	{1996},
  month = 	{August}
}

@inproceedings{ gupta02_soenet,
  author = 	{Amit K Gupta and William J. Dally and Arjun Singh and Brian Towles},
  title = 	{Scalable Opto-Electronic Network (SOENet)},
  booktitle = 	{proceedings of Hot Interconnects (HotI) X},
  year = 	{2002},
  month = 	{August},
  address = 	{Stanford, California, USA}
}






@comment{ ================================================================== }
@comment{ ============= Supercomputers ===================================== }


@inproceedings{ kessler93_t3d,
  author = 	{R.E. Kessler and J.L. Schwarzmeier},
  title = 	{Cray {T3D}: a new dimension for {C}ray {R}esearch},
  booktitle = 	COMPCON,
  pages = 	{176--182},
  year = 	{1993},
  month = 	{February}
}

@article{ simmons92_perfcomp,
  author =	"Margaret L. Simmons and Harvey J. Wasserman and Olaf M. Lubeck and Christopher Eoyang and Raul Mendez and Hiroo Harada and Misako Ishiguro",
  title =       "A performance comparison of four supercomputers",
  journal =     "Communications of the ACM",
  volume =      "35",
  number =      "8",
  pages =       "116--124",
  month =       {August},
  year =        "1992",
  coden =       "CACMA2",
  ISSN =        "0001-0782",
  bibdate =     "Thu May 30 09:41:10 MDT 1996",
  url =         "http://www.acm.org/pubs/toc/Abstracts/0001-0782/135234.html",
}

@article{ russell78_cray1,
  author =       "Richard M. Russell",
  title =        "The {CRAY-1} Computer System",
  journal =      "Communications of the ACM",
  volume =       "21",
  number =       "1",
  pages =        "63--72",
  month =        {January},
  year =         "1978",
  coden =        "CACMA2",
  ISSN =         "0001-0782",
  bibdate =      "Tue Dec 30 07:29:05 1997",
  classification="722; 723",
  corpsource =   "Cray Res. Inc., Minneapolis, MN, USA",
  journalabr =   "Commun ACM",
  treatment =    "P Practical",
}







@comment{ ================================================================== }
@comment{ ============= Chips ============================================== }

@misc{ nv30,
  title = 	{\textit{n}VIDIA$^{\textrm{\scriptsize\textregistered}}$ GeFORCE$^{TM}$ FX},
  author = 	{\textit{n}VIDIA$^{\textrm{\scriptsize\textregistered}}$},
  note = 	{http://www.nvidia.com/docs/lo/2430/SUPP/ PO\_GFFX\_Consumer\_030503.pdf}
}

@manual{ mips,
  organization ={MIPS Technologies},
  title = 	{MIPS64 20Kc Core },
  note = 	{http://www.mips.com/ProductCatalog/P\_MIPS6420KcCore}
}

@misc{ intel1,
  author = 	{Intel$^{\textrm{\scriptsize\textregistered}}$},
  title = 	{Intel$^{\textrm{\scriptsize\textregistered}}$ 850E Chipset},
  note = 	{http://www.intel.com/design/chipsets/850e/index.htm}
}

@misc{ intel2,
  author = 	{Intel$^{\textrm{\scriptsize\textregistered}}$},
  title = 	{Intel$^{\textrm{\scriptsize\textregistered}}$ Pentium$^{\textrm{\scriptsize\textregistered}}$ 4 Processor},
  note = 	{http://www.intel.com/products/desktop/processors/ pentium4/index.htm}
}








@comment{ ================================================================== }
@comment{ ============= Vectors ============================================ }

@article{ smith00_vectorconditionals,
  author = 	{J.E. Smith and G. Faanes and R. Sugumar},
  title =       {Vector Instruction Set Support for Conditional Operations},
  journal =     ISCA,
  year =        {2000},
  pages = 	{260--269}
}








@comment{ ================================================================== }
@comment{ ============= Arithmetic ========================================= }

@article{ alverson91_iterdiv,
  author = 	{R. Alverson},
  title =       {Integer division using reciprocals},
  journal =     ISCA,
  year =        {1991},
  pages = 	{186--190}
}

@article{ flynn70_division,
  author = 	{M. Flynn},
  title =       {On Division by Functional Iteration},
  journal =     TOC,
  year =        {1970},
  month =       {August},
  pages = 	{702--706},
  volume = 	{19},
  number = 	{8},
}

@phdthesis{ liddicoat02_thesis,
  author = 	{A. Liddicoat},
  title =       {High-Performance Arithmetic for Division and the Elementary Fucntions},
  year =        {2002},
  school =	{Stanford University},
}








@comment{ ================================================================== }
@comment{ ============= Misc =============================================== }

@manual{ itrs,
  organization ={Semiconductor Industry Association},
  title = 	{The International Technology Roadmap for Semiconductors},
  year = 	{2001 Edition},
}

@book{ dally98_dse,
  author = 	{William J. Dally and W. Poulton},
  title = 	{Digital Systems Engineering},
  publisher = 	{Cambridge University Press},
  year = 	{1998}
}