| Paderborn_Center_for_Parallel_Computing Computing and service center of University of Paderborn, Germany. Hosting and participating several national and international projects, operating innovative parallel computers. Good reputation in |
| PARADIGM A parallelizing compiler that translates HPF to Fortran 77. Research papers. |
| Parallel_I/O_Archive_at_Dartmouth Cluster designed specifically for large parametric modelling computations. Offers case studies and performance metrics. |
| Purdue\'s_Adapter_for_Parallel_Execution_and_Rapid_Synchronization Hardware to reduce latency in communication between nodes of a parallel computing cluster. Paper describes the performance and software interface. |
| QUID Papers and links about research into efficient programming of hybrid parallel machines. |
| SHRIMP The Scalable High-performance Really Inexpensive Multi-Processor project investigates how to construct high-performance servers with a network of commodity PCs and commodity operating systems. Softwar |
| UC_Berkeley_Clustered_Computing Project to develop and deploy a hierarchical campus-wide "cluster of clusters" to support advanced applications in scientific computing, simulation, and modelling. |
| VUB_Parallel_Computing_Laboratory Research to improve the performance of multiprocessor servers. Theses and other publications. |
| Avoka_Technologies Software and services for benchmarking and load testing of web sites, especially eCommerce. White papers and links. |
| The_Benchmark_Gateway TOP performers in all of the major public benchmarks, TPC, SPEC, Oracle, SAP, and Intel. |
| Benchmarks_For_PCs Pre-compiled benchmarks for PCs, covering CPU, RAM, HDD and graphics. |
| BenchWeb A starting point for finding information about computer system performance, benchmark test results and benchmark source code. |
| Bonnie Benchmarks that measure the performance of Unix file system operations, concerned mainly with identifying bottlenecks. |
| Chris\'_Lightwave_Benchmarks A constantly growing database of computer systems benchmarked using NewTek's LightWave 3D. |
| CPU_Benchmarks_with_POVRAY Multi and single CPU system benchmark tests. Containing a gallery of generated images. |
| Dacris_Benchmarks__NET Developer of Benchmarking/Optimization tools for Windows PC's. |
| David_Kubelka Performance tools for computer professionals. |
| EEMBC EDN Embedded Microprocessor Benchmarking Consortium is a non-profit consortium that develops benchmark suites that target key embedded system applications. |
| Fresh_Diagnose Free software to analyze and benchmark your computer system. |
| Haveland-Robinson_Associates_-_PoVBench Benchmark database, serving as a guide to the relative maths performance of various computers, processors and compilers. |
| IT_Transition Offering benchmark services in the UK. |
| LMBench Tools for performance analysis, latency and bandwidth measurement of hardware and the operating system. [for Unix] |
| Load_Testing_of_any_technology Consulting practice focused on load testing with the Mercury Interactive tool. |
| NT_vs__Linux_Server_Benchmark_Data Links and summaries of results of benchmarks comparing Windows NT and Linux network performance. |
| Open_Source_FTP_Benchmark Home page for the dkftpbench FTP benchmark. Measuring how many simultaneous dialup users can be down loading from an FTP site at the same time. |
| Open_Source_Passive_TCP_Application_Response_Time_Monitor_for_Linux Uses packet sniffer technology to monitor IP applications, such as HTTP, SMTP and POP3. It measures response times, through put and congestion. In beta release as of 7 May 2002. |
| The_Performance_Database_Server SPEC information provided courtesy of SPEC and the University of Tennessee. |
| PerfSuite A collection of tools to help analyze and improve software performance on Intel (x86 and ia64) and AMD (x86 and x86-64) systems running Linux, including tools for measuring hardware performance (CPU/c |
| Radifed Sample benchmarks and links to benchmarking programs |
| Software,_System_and_network_testing Benchmark testing operating systems with Microsoft funded Windows NT verses Linux tests. |
| Specbench_CPU95_Results This is the HTML FORM's interface to more than one thousand benchmark results published by SPEC. |
| Standards_Performance_Evaluation_Corporation_(SPEC) A standards body for performance benchmarks. SPEC is an umbrella organization encompassing the efforts of the Open Systems Group. |
| STREAM Sustainable memory bandwidth discussion, with results on a wide variety of computer systems. From Macs and PCs to the most current and recent workstations, right up to Cray supercomputers. From the De |
| TPC Transaction Processing Performance Council, a non-profit corporation founded to define transaction processing and database benchmarks and to disseminate objective, verifiable TPC performance data to t |
| Capacitas Performance and capacity planning consultancy and training services. Includes whitepapers. Head office located in London, UK. |
| Characterizing_Web_Response_Time Master's thesis by Binzhang Liu |
| CMG_-_Computer_Measurement_Group Professional organization for capacity planners. |
| DB2_System_Performance_Metrics Here Joel Goldstein discusses various DB2 capacity metrics. |
| Jonathan_Hardwick Product information about Microsoft's System Center Capacity Planner. |
| Load_Balancing_Your_Web_Site Practical Approaches for Distributing HTTP Traffic by Ralf S.Engelschall. |
The goal of the Avalanche project is to enable theconstruction of usable and truly scalable parallel computing platformsthat are not exorbitantly expensive, yet are still capable ofachieving peta-op performance levels.Low communication latency is the key to achievingperformance scalability for both of the common parallel computation models,namely Message Passing and Distributed Shared Memory.Toward this end, we are developing a memory architecture that tightlyintegrates the processor, the entire memory hierarchy, and theinterconnect fabric.The core of the effort is the development of a newCache and Communication Controller Unit(CCCU) for theHewlett-PackardPA 8000 CPU and the Myrinet network fabric (fromMyricom Inc).The CCCU will inject incoming data traffic into the "appropriate level"of the memory hierarchy to minimize message latency and cache misspenalties. Furthermore, it supports a flexible suite of cachecoherence protocols for DSM applications In order to achieve reasonable cost it is necessary to adopt anapproach that takes advantage of the significant performanceadvantages and momentum already provided by commercial microprocessorand interconnect fabric development efforts.The target for the project is a 64 processing element prototypewhich will be constructed in the final year of theARPA(CSTO)/ SPAWARsupported project duration. [ Status Reports| Publications| Personnel| Facilities| Related Sites] 
Feedback to:avalanche@jensen.cs.utah.eduLast modified around November 13, 1995. This work was sponsored by theSpace and Naval Warfare Systems Command (SPAWAR) andAdvanced Research Projects Agency (ARPA),Communication and Memory Architectures forScalable Parallel Computing,ARPA order #B990 under SPAWAR contract #N00039-95-C-0018.