Title: The Wisconsin Wind Tunnel Project PIs: Mark D. Hill, James R. Larus, David A. Wood Email: wwt@cs.wisc.edu WWW: http://www.cs.wisc.edu/~wwt Anonymous FTP: ftp ftp.cs.wisc.edu; cd wwt Our WWW and anonymous ftp site contains the following papers: annobib.ps An overview and annotated bibliography tempest_talk.ps Slides for an overview talk (Mar 1995) nsf96_summary.ps Project summary for NSF (appendix==compcon95_tempest.ps) asplos5_csm.ps First paper on cooperative shared memory asplos6_fine_grain.ps Discusses fine-grain access control and Blizzard asplos6_lcm.ps Loosely coherent memory (LCM) support for C** asplos6_sm_mp.ps Compares 4 shared memory and message passing programs asplos98_fastsim.ps Fast Out-Of-Order Processor Simulation Using Memoization asplos98_fastsim_slides.ps Slides for FastSim talk given at ASPLOS-VIII cce_electrostatics.ps Solving Microstructure Electrostatics on CSM compcon95_tempest.ps Overview of Tempest and our project computer95_cost.ps Shows when parallel computing is cost-effective computer98_nicase.ps Shows how processor-NI interactions can be improved computer98_sccase.ps Argues for simple memory consistency models concurrency00_wwt2.ps Discusses the design of WWT II dsl97_experiences.ps Experience with Teapot on LCM and Berkeley xFS hotinter97_case.ps Case for treating NI accesses as memory accesses (slides) hpca97.ps Shows when dedicated protocol processing makes sense hpca98_impact.ps Impact of Data Transfer and Buffering on Network Interface design hpca98_nitrans.ps Address Translation Mechanisms in Network Interfaces hpca99_lamport.ps Verifying TSO and Alpha Memory Consistency Models hpca99_pdq.ps Parallel Dispatch Queue hw_sw_sm.ps Discussion of compiler and hardware shared memory icpp94_cachier.ps Cachier automatically inserts CICO annotations ics94_directory.ps Proposes and evaluates multicast directory protocols ics96_synch.ps Examines hardware synchronization support for a NOW isca93_mechanisms.ps Examines directory protocol complexity & performance isca94_typhoon.ps Tempest and Typhoon: user-level shared memory isca95_dsi.ps Dynamic Self-Invalidation: Reducing Coherence Overhead isca96_cni.ps Coherent Network Interfaces isca96_dcpld.ps Decoupled Hardware Support for Distributed Shared Memory lcpc96.ps HPF on Fine-Grain DSM: Early Experience isca97.ps Proposes Reactive NUMA isca98_cosmos.ps Proposes using prediction in coherence protocols isca98_model.ps Analytic model for ILP Multiprocessors isca99_multifacet.ps Proposes Multicast Snooping with an Ordered Network ismm98_cache_gc.ps Using Garbage Collection for Cache-Conscious Data Placement lebeck.ps Alvin Lebeck's PhD thesis micro.ps Efficient path profiling micro29_eel.ps Instruction scheduling and Executable Editing p4_cico.ps Describes check-in-check-out programming model pact98.ps Describes the Sirocco Fine-Grain DSM pads94_costperf.ps Examines cost-performance of parallel simulation pads96_optimistic.ps Optimistic simulation techniques using executables paid97_wwt2.ps Describes the Wisconsin Wind Tunnel II simulator pldi95_eel.ps Description of EEL (Executable Editing Library) pldi96_teapot.ps Language Suport for Writing Memory Coherence Protocols pldi97_paths.ps Exploiting Hardware Counters with Path Profiling pldi98_dataflow.ps Improving Data-flow Analysis with Path Profiles pldi99_cache_layout.ps Cache-Conscious Structure Layout pldi99_cache_def.ps Cache-Conscious Structure Definition computer00_conscious Gentle intro into cache-conscious work ppopp95_irregular.ps Studies three irregular applications on CHAOS and Tempest ppopp97_dsmgran.ps Evaluates performance of different consistency models and coherence granularities ppopp97_memprof.ps Describes a new approach to profile shared-memory performance ppopp97_hpf.ps Describes compiler optimizations for a fine-grain dsm sc94_paging.ps Explores paging in distributed-shared-memory machines sc94_protocols.ps Examines writing application-specific protocols sc96_compiler_sm.ps Describes a compiler-directed protocol for adaptive applications sigmetrics93_wwt.ps First paper on the Wisconsin Wind Tunnel (WWT) sigmetrics95_am.ps Active Memory: A New Abstraction for Memory-System Simulation sigmetrics00_model.ps Modeling techniques for handling a server with bursty requests spaa98_lamport.ps Method for Verifying Directory Protocols tocs93_csm.ps Revised version of asplos5_csm tomacs97_perf.ps Describes the models in pads94_costperf in detail tr95_tempest_spec.ps Tempest Specification TR tr96_scheduling.ps When to dedicate protocol processors on COW tr97_ni_survey.ps Survey of User-Level Network Interfaces for System Area Networks tr97_sc_case.ps Advocates Simple Memory Consistency Models tr98_lamport.ps Method for verifying bus protocols traenkle_ms.ps M.S. Thesis that elaborates on cce_electrostatics.ps.Z usenix93_kernel.ps Explores OS support for WWT vldb99_dbms_eval.ps Evalulates four databases on a Pentium Pro platform wcsss96_eel.ps Instruction Scheduling and Executable Editing wwt_tutorial.ps Tutorial for new users of WWT Misc/ Directory of miscellaneous things (see README's) Benchmarks/ Benchmarks released by the Wind Tunnel Theses/ WWT's Phd Theses