发布求助
文献互助 智能选刊 最新文献

Proceedings SUPERCOMPUTING '90最新文献

筛选
英文 中文
Perfect Benchmarks decomposition and performance on VAX multiprocessors 完美的基准分解和性能在VAX多处理器
Proceedings SUPERCOMPUTING '90 Pub Date : 1990-11-12 DOI: 10.1109/SUPERC.1990.130055
Z. Cvetanovic, E. Freedman, C. Nofsinger
{"title":"Perfect Benchmarks decomposition and performance on VAX multiprocessors","authors":"Z. Cvetanovic, E. Freedman, C. Nofsinger","doi":"10.1109/SUPERC.1990.130055","DOIUrl":"https://doi.org/10.1109/SUPERC.1990.130055","url":null,"abstract":"The authors present the methods for decomposition and the performance of the Perfect Benchmark suite on two VAX multiprocessors. Results indicate that it was possible to obtain significant performance gains on both VAX multiprocessors, relative to a uniprocessor case. A methodology that can be applied to decompose other existing scientific and engineering applications is proposed. Guidelines for autodecomposing compiler improvements are provided. The authors discuss and quantify the effect of different cache designs on the multiprocessor performance.<<ETX>>","PeriodicalId":408163,"journal":{"name":"Proceedings SUPERCOMPUTING '90","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133899666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 4
UC: a language for the connection machine UC:连接机使用的语言
Proceedings SUPERCOMPUTING '90 Pub Date : 1990-11-12 DOI: 10.1109/SUPERC.1990.130064
R. Bagrodia, K. Chandy, E. Kwan
{"title":"UC: a language for the connection machine","authors":"R. Bagrodia, K. Chandy, E. Kwan","doi":"10.1109/SUPERC.1990.130064","DOIUrl":"https://doi.org/10.1109/SUPERC.1990.130064","url":null,"abstract":"In designing parallel languages, the concern for defining a simple virtual machine must be balanced against the need to efficiently map a program on a specific architecture. UC addresses this problem by separating the programming task from efficiency considerations. UC programs are designed using a small set of constructs that include reduction, parallel assignment, and fixed-point computation. The language also provides a map section that may optionally be used by a programmer to specify data mappings for the program. The authors describe the UC constructs and their implementation on the Connection Machine. They also present measurements of the compiler for simple benchmarks.<<ETX>>","PeriodicalId":408163,"journal":{"name":"Proceedings SUPERCOMPUTING '90","volume":"2008 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125591856","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 10
Scan primitives for vector computers 扫描向量计算机的原语
Proceedings SUPERCOMPUTING '90 Pub Date : 1990-11-12 DOI: 10.1109/SUPERC.1990.130084
S. Chatterjee, G. Blelloch, Marco Zagha
{"title":"Scan primitives for vector computers","authors":"S. Chatterjee, G. Blelloch, Marco Zagha","doi":"10.1109/SUPERC.1990.130084","DOIUrl":"https://doi.org/10.1109/SUPERC.1990.130084","url":null,"abstract":"The authors describe an optimized implementation of a set of scan (also called all-prefix-sums) primitives on a single processor of a CRAY Y-MP, and demonstrate that their use leads to greatly improved performance for several applications that cannot be vectorized with existing computer technology. The algorithm used to implement the scans is based on an algorithm for parallel computers. A set of segmented versions of these scans is only marginally more expensive than the unsegmented versions. The authors describe a radix sorting routine based on the scans that is 13 times faster than a Fortran version and within 20% of a highly optimized library sort routine, three operations on trees that are between 10 to 20 times faster than the corresponding C versions, and a connectionist learning algorithm that is 10 times faster than the corresponding C version for sparse and irregular networks.<<ETX>>","PeriodicalId":408163,"journal":{"name":"Proceedings SUPERCOMPUTING '90","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115214988","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 114
Cost-performance analysis of heterogeneity in supercomputer architectures 超级计算机体系结构异构的成本-性能分析
Proceedings SUPERCOMPUTING '90 Pub Date : 1990-11-12 DOI: 10.1109/SUPERC.1990.130017
D. Menascé, Virgílio A. F. Almeida
{"title":"Cost-performance analysis of heterogeneity in supercomputer architectures","authors":"D. Menascé, Virgílio A. F. Almeida","doi":"10.1109/SUPERC.1990.130017","DOIUrl":"https://doi.org/10.1109/SUPERC.1990.130017","url":null,"abstract":"The cost-performance of heterogeneity in supercomputer architectures is analyzed. Queuing models are used to study the performance of homogeneous and heterogeneous supercomputer models. Grosch's law, which states that computer performance increases as the square of its cost, is used to analyze cost aspects of the models. It is concluded that heterogeneity in supercomputer architectures is a quite promising design approach that deserves further investigation.<<ETX>>","PeriodicalId":408163,"journal":{"name":"Proceedings SUPERCOMPUTING '90","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123398923","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 72
Improving instruction cache behavior by reducing cache pollution 通过减少缓存污染来改进指令缓存行为
Proceedings SUPERCOMPUTING '90 Pub Date : 1990-11-12 DOI: 10.1109/SUPERC.1990.130005
Rajiv Gupta, Chi-Hung Chi
{"title":"Improving instruction cache behavior by reducing cache pollution","authors":"Rajiv Gupta, Chi-Hung Chi","doi":"10.1109/SUPERC.1990.130005","DOIUrl":"https://doi.org/10.1109/SUPERC.1990.130005","url":null,"abstract":"Compiler techniques for improving instruction cache performance are described. Through repositioning of the code in the main memory, leaving memory locations unused, code duplication, and code propagation, the effectiveness of the cache can be improved due to reduced cache pollution and fewer cache misses. Results of experiments indicate that significant reduction in bus traffic results from the use of these techniques. Since memory bandwidth is a critical resource in shared memory multiprocessors, such systems can benefit from the techniques described. The notion of control dependence is used to decide when instructions belonging to different basic blocks can be allowed to share the same cache line without increasing cache pollution.<<ETX>>","PeriodicalId":408163,"journal":{"name":"Proceedings SUPERCOMPUTING '90","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131179444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 26
Parallel program debugging with on-the-fly anomaly detection 并行程序调试与动态异常检测
Proceedings SUPERCOMPUTING '90 Pub Date : 1990-11-12 DOI: 10.1109/SUPERC.1990.130004
R. Hood, K. Kennedy, J. Mellor-Crummey
{"title":"Parallel program debugging with on-the-fly anomaly detection","authors":"R. Hood, K. Kennedy, J. Mellor-Crummey","doi":"10.1109/SUPERC.1990.130004","DOIUrl":"https://doi.org/10.1109/SUPERC.1990.130004","url":null,"abstract":"An approach for parallel debugging that coordinates static analysis with efficient on-the-fly access anomaly detection is described. On-the-fly instrumentation mechanisms are being developed for the structured synchronization primitives of Parallel Computing Forum (PCF) Fortran, the emerging standard for parallel Fortran. The proposed instrumentation techniques guarantee that one can isolate schedule-dependent behavior in a schedule-independent fashion. The result is that a single-instrumented execution will either report sources of schedule-dependent behavior, or it will validate that all executions of the program on the same data compute the same result. When an instrumented execution is being used solely to find sources of schedule-dependent behavior, its cost can be reduced by slicing out computations that do not contribute to race conditions. Ongoing efforts to incorporate the proposed debugging approach in the ParaScope environment are described.<<ETX>>","PeriodicalId":408163,"journal":{"name":"Proceedings SUPERCOMPUTING '90","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123075686","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 73
Computer simulation of high-speed impact response of composites 复合材料高速冲击响应的计算机模拟
Proceedings SUPERCOMPUTING '90 Pub Date : 1990-11-12 DOI: 10.1109/SUPERC.1990.130107
S. Langlie, W. Cheng, I. Dilber
{"title":"Computer simulation of high-speed impact response of composites","authors":"S. Langlie, W. Cheng, I. Dilber","doi":"10.1109/SUPERC.1990.130107","DOIUrl":"https://doi.org/10.1109/SUPERC.1990.130107","url":null,"abstract":"The authors share some of their experiences with the use of a supercomputer to facilitate the analysis and design of high-velocity impact processes in composite systems. They also discuss the benefits of color animation of the results on a MacIntosh computer. The calculations were carried out on a CRAY-2 using an impact model developed for high-velocity impact/penetration of fiber-reinforced layered composites. The model is built on a continuum approach and includes a basic orthotropic constitutive material behavior. A computer program was developed to convert the results of the analysis for hundreds of time steps into 8-bit raster images and these are animated using graphic tools developed at NCSA. The same set of images were also directly recorded on a video tape. A fifteen-times improvement in speed has been recorded on the CRAY-2 over a VAX 8600 computer previously used for the same calculations.<<ETX>>","PeriodicalId":408163,"journal":{"name":"Proceedings SUPERCOMPUTING '90","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116969438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 7
Architectural support for register allocation in the presence of aliasing 在存在混叠的情况下对寄存器分配的体系结构支持
Proceedings SUPERCOMPUTING '90 Pub Date : 1990-11-12 DOI: 10.1109/SUPERC.1990.130093
Ben Heggy, M. Soffa
{"title":"Architectural support for register allocation in the presence of aliasing","authors":"Ben Heggy, M. Soffa","doi":"10.1109/SUPERC.1990.130093","DOIUrl":"https://doi.org/10.1109/SUPERC.1990.130093","url":null,"abstract":"A hardware support mechanism is presented that permits all classes of data objects, including dynamically allocated objects and array elements, to be held in registers without consideration of possible aliases and without requiring that the generated code maintain consistency between register and memory copies of variables. Use of this approach permits programs to benefit from the speed advantages and reduced memory traffic associated with register storage, obviates the need to collect aliasing information for use in register allocation, and reduces instruction traffic by eliminating code used solely to maintain register-memory consistency. The support hardware can be implemented using known hardware technology and without increasing the cycle time of the processor.<<ETX>>","PeriodicalId":408163,"journal":{"name":"Proceedings SUPERCOMPUTING '90","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117176185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 20
Parallelization of loops with exits on pipelined architectures 在流水线架构上具有出口的循环的并行化
Proceedings SUPERCOMPUTING '90 Pub Date : 1990-11-12 DOI: 10.1109/SUPERC.1990.130021
P. Tirumalai, Meng Lee, M. Schlansker
{"title":"Parallelization of loops with exits on pipelined architectures","authors":"P. Tirumalai, Meng Lee, M. Schlansker","doi":"10.1109/SUPERC.1990.130021","DOIUrl":"https://doi.org/10.1109/SUPERC.1990.130021","url":null,"abstract":"Modulo scheduling theory can be applied successfully to overlap Fortran DO loops on pipelined computers issuing multiple operations per cycle both with and without special loop architectural support. It is shown that a broader class of loops-repeat-until, while, and loops with more than one exit-where the trip count is not known beforehand, can also be overlapped efficiently on multiple issue pipelined machines. Special features that are required in the architecture as well as compiler representations for accelerating these loop constructions are discussed. The approach uses hardware architectural support, program transformation techniques, performance bounds calculations, and scheduling heuristics. Performance results are presented for a few select examples. A prototype scheduler is currently under construction for the Cydra 5 directed dataflow computer.<<ETX>>","PeriodicalId":408163,"journal":{"name":"Proceedings SUPERCOMPUTING '90","volume":"215 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122620446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 89
A taxonomy of concepts for evaluating chess strength 评估国际象棋实力的概念分类
Proceedings SUPERCOMPUTING '90 Pub Date : 1990-11-12 DOI: 10.1109/SUPERC.1990.130039
H. Berliner, D. Kopec, E. Northam
{"title":"A taxonomy of concepts for evaluating chess strength","authors":"H. Berliner, D. Kopec, E. Northam","doi":"10.1109/SUPERC.1990.130039","DOIUrl":"https://doi.org/10.1109/SUPERC.1990.130039","url":null,"abstract":"The authors present a taxonomy of positions in chess that require special knowledge. The taxonomy drives the selection of positions, not vice-versa. The authors present a set of annotated example problems from two specific categories that require understanding of critical concepts to achieve the maximum result.<<ETX>>","PeriodicalId":408163,"journal":{"name":"Proceedings SUPERCOMPUTING '90","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1990-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123748647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 11
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信
小红书