A. Roy, Ian T Foster, W. Gropp, N. Karonis, V. Sander, B. Toonen
Parallel programmers typically assume that all resources required for a program’s execution are dedicated to that purpose. However, in local and wide area networks, contention for shared networks, CPUs, and I/O systems can result in significant variations in availability, with consequent adverse effects on overall performance. We describe a new message-passing architecture, MPICH-GQ, that uses quality of service (QoS) mechanisms to manage contention and hence improve performance of message passing interface (MPI) applications. MPICH-GQ combines new QoS specification, traffic shaping, QoS reservation, and QoS implementation techniques to deliver QoS capabilities to the high-bandwidth bursty flows, complex structures, and reliable protocols used in high-performance applications-characteristics very different from the low-bandwidth, constant bit-rate media flows and unreliable protocols for which QoS mechanisms were designed. Results obtained on a differentiated services testbed demonstrate our ability to maintain application performance in the face of heavy network contention.
{"title":"MPICH-GQ: Quality-of-Service for Message Passing Programs","authors":"A. Roy, Ian T Foster, W. Gropp, N. Karonis, V. Sander, B. Toonen","doi":"10.1109/SC.2000.10017","DOIUrl":"https://doi.org/10.1109/SC.2000.10017","url":null,"abstract":"Parallel programmers typically assume that all resources required for a program’s execution are dedicated to that purpose. However, in local and wide area networks, contention for shared networks, CPUs, and I/O systems can result in significant variations in availability, with consequent adverse effects on overall performance. We describe a new message-passing architecture, MPICH-GQ, that uses quality of service (QoS) mechanisms to manage contention and hence improve performance of message passing interface (MPI) applications. MPICH-GQ combines new QoS specification, traffic shaping, QoS reservation, and QoS implementation techniques to deliver QoS capabilities to the high-bandwidth bursty flows, complex structures, and reliable protocols used in high-performance applications-characteristics very different from the low-bandwidth, constant bit-rate media flows and unreliable protocols for which QoS mechanisms were designed. Results obtained on a differentiated services testbed demonstrate our ability to maintain application performance in the face of heavy network contention.","PeriodicalId":228250,"journal":{"name":"ACM/IEEE SC 2000 Conference (SC'00)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134608578","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}
This is a project for developing a distributed job execution environment for highly iterative jobs. An iterative job is one where the same binary code is run hundreds of times with incremental changes in the input values for each run. An execution environment is a set of resources on a computing platform that can be made available to run the job and hold the output until it is collected. The goal is to design a complete, object-oriented scheduling system that will run a variety of jobs with minimal changes. Areas of code that are unique to one specific type of job are decoupled from the rest. The system allows for fine-grained job control, timely status notification and dynamic registration and deregistration of execution platforms depending on resources available. Several objected-oriented technologies are employed: Java, CORBA, UML, and software design patterns. The environment has been tested using a CFD code, INS2D.
{"title":"An Object-Oriented Job Execution Environment","authors":"L. Smith, R. Fatoohi","doi":"10.1109/SC.2000.10036","DOIUrl":"https://doi.org/10.1109/SC.2000.10036","url":null,"abstract":"This is a project for developing a distributed job execution environment for highly iterative jobs. An iterative job is one where the same binary code is run hundreds of times with incremental changes in the input values for each run. An execution environment is a set of resources on a computing platform that can be made available to run the job and hold the output until it is collected. The goal is to design a complete, object-oriented scheduling system that will run a variety of jobs with minimal changes. Areas of code that are unique to one specific type of job are decoupled from the rest. The system allows for fine-grained job control, timely status notification and dynamic registration and deregistration of execution platforms depending on resources available. Several objected-oriented technologies are employed: Java, CORBA, UML, and software design patterns. The environment has been tested using a CFD code, INS2D.","PeriodicalId":228250,"journal":{"name":"ACM/IEEE SC 2000 Conference (SC'00)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114231420","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}
A. Wong, L. Oliker, W. Kramer, T. Kaltz, D. Bailey
This article describes a new benchmark, called the Effective System Performance (ESP) test, which is designed to measure system-level performance, including such factors as job scheduling efficiency, handling of large jobs and shutdown-reboot times. In particular, this test can be used to study the effects of various scheduling policies and parameters. We present here some results that we have obtained so far on the Cray T3E and IBM SP systems, together with insights obtained from simulations.
{"title":"ESP: A System Utilization Benchmark","authors":"A. Wong, L. Oliker, W. Kramer, T. Kaltz, D. Bailey","doi":"10.1109/SC.2000.10056","DOIUrl":"https://doi.org/10.1109/SC.2000.10056","url":null,"abstract":"This article describes a new benchmark, called the Effective System Performance (ESP) test, which is designed to measure system-level performance, including such factors as job scheduling efficiency, handling of large jobs and shutdown-reboot times. In particular, this test can be used to study the effects of various scheduling policies and parameters. We present here some results that we have obtained so far on the Cray T3E and IBM SP systems, together with insights obtained from simulations.","PeriodicalId":228250,"journal":{"name":"ACM/IEEE SC 2000 Conference (SC'00)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123959586","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}
As evidenced by the popularity of MPI (Message Passing Interface), message passing is an effective programming technique for managing coarse-grained concurrency on distributed computers. Unfortunately, debugging message-passing applications can be difficult. Software complexity, data races, and scheduling dependencies can make programming errors challenging to locate with manual, interactive debugging techniques. This article describes Umpire, a new tool for detecting programming errors at runtime in message passing applications. Umpire monitors the MPI operations of an application by interposing itself between the application and the MPI runtime system using the MPI profiling layer. Umpire then checks the application’s MPI behavior for specific errors. Our initial collection of programming errors includes deadlock detection, mismatched collective operations, and resource exhaustion. We present an evaluation on a variety of applications that demonstrates the effectiveness of this approach.
{"title":"Dynamic Software Testing of MPI Applications with Umpire","authors":"J. Vetter, B. Supinski","doi":"10.1109/SC.2000.10055","DOIUrl":"https://doi.org/10.1109/SC.2000.10055","url":null,"abstract":"As evidenced by the popularity of MPI (Message Passing Interface), message passing is an effective programming technique for managing coarse-grained concurrency on distributed computers. Unfortunately, debugging message-passing applications can be difficult. Software complexity, data races, and scheduling dependencies can make programming errors challenging to locate with manual, interactive debugging techniques. This article describes Umpire, a new tool for detecting programming errors at runtime in message passing applications. Umpire monitors the MPI operations of an application by interposing itself between the application and the MPI runtime system using the MPI profiling layer. Umpire then checks the application’s MPI behavior for specific errors. Our initial collection of programming errors includes deadlock detection, mismatched collective operations, and resource exhaustion. We present an evaluation on a variety of applications that demonstrates the effectiveness of this approach.","PeriodicalId":228250,"journal":{"name":"ACM/IEEE SC 2000 Conference (SC'00)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129869572","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}
Dimitrios S. Nikolopoulos, T. Papatheodorou, C. Polychronopoulos, Jesús Labarta, E. Ayguadé
This paper investigates the performance implications of data placement in OpenMP programs running on modern ccNUMA multiprocessors. Data locality and minimization of the rate of remote memory accesses are critical for sustaining high performance on these systems. We show that due to the low remote-to-local memory access latency ratio of state-of-the-art ccNUMA architectures, reasonably balanced page placement schemes, such as round-robin or random distribution of pages incur modest performance losses. We also show that performance leaks stemming from suboptimal page placement schemes can be remedied with a smart user-level page migration engine. The main body of the paper describes how the OpenMP runtime environment can use page migration for implementing implicit data distribution and redistribution schemes without programmer intervention. Our experimental results support the effectiveness of these mechanisms and provide a proof of concept that there is no need to introduce data distribution directives in OpenMP and warrant the portability of the programming model.
{"title":"Is Data Distribution Necessary in OpenMP?","authors":"Dimitrios S. Nikolopoulos, T. Papatheodorou, C. Polychronopoulos, Jesús Labarta, E. Ayguadé","doi":"10.1109/SC.2000.10025","DOIUrl":"https://doi.org/10.1109/SC.2000.10025","url":null,"abstract":"This paper investigates the performance implications of data placement in OpenMP programs running on modern ccNUMA multiprocessors. Data locality and minimization of the rate of remote memory accesses are critical for sustaining high performance on these systems. We show that due to the low remote-to-local memory access latency ratio of state-of-the-art ccNUMA architectures, reasonably balanced page placement schemes, such as round-robin or random distribution of pages incur modest performance losses. We also show that performance leaks stemming from suboptimal page placement schemes can be remedied with a smart user-level page migration engine. The main body of the paper describes how the OpenMP runtime environment can use page migration for implementing implicit data distribution and redistribution schemes without programmer intervention. Our experimental results support the effectiveness of these mechanisms and provide a proof of concept that there is no need to introduce data distribution directives in OpenMP and warrant the portability of the programming model.","PeriodicalId":228250,"journal":{"name":"ACM/IEEE SC 2000 Conference (SC'00)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130270123","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}
This paper describes the performance and interoperability issues that arise in the process of integrating cluster management systems into a wide-area network-computing environment, and provides solutions in the context of the Purdue University Network Computing Hubs (PUNCH). The described solution provides users with a single point of access to resources spread across administrative domains, and an intel ligent translation process makes it possible for users to submit jobs to different types of cluster management systems in a transparent manner. The approach does not require any modifications to the cluster management software; however, call-back and caching capabilities that would improve performance and make such systems more interoperable with wide-area computing systems are discussed.
{"title":"Performance and Interoperability Issues in Incorporating Cluster Management Systems within a Wide-Area Network-Computing Environment","authors":"S. Adabala, N. Kapadia, J. Fortes","doi":"10.1109/SC.2000.10021","DOIUrl":"https://doi.org/10.1109/SC.2000.10021","url":null,"abstract":"This paper describes the performance and interoperability issues that arise in the process of integrating cluster management systems into a wide-area network-computing environment, and provides solutions in the context of the Purdue University Network Computing Hubs (PUNCH). The described solution provides users with a single point of access to resources spread across administrative domains, and an intel ligent translation process makes it possible for users to submit jobs to different types of cluster management systems in a transparent manner. The approach does not require any modifications to the cluster management software; however, call-back and caching capabilities that would improve performance and make such systems more interoperable with wide-area computing systems are discussed.","PeriodicalId":228250,"journal":{"name":"ACM/IEEE SC 2000 Conference (SC'00)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130842562","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}
K. Lindlan, J. Cuny, A. Malony, S. Shende, B. Mohr, R. Rivenburgh, C. Rasmussen
The developers of high-performance scientific applications often work in complex computing environments that place heavy demands on program analysis tools. The developers need tools that interoperate, are portable across machine architectures, and provide source-level feedback. In this paper, we describe a tool framework, the Program Database Toolkit (PDT), that supports the development of program analysis tools meeting these requirements. PDT uses compile-time information to create a complete database of high-level program information that is structured for well-defined and uniform access by tools and applications. PDT’s current applications make heavy use of advanced features of C++, in particular, templates. We describe the toolkit, focussing on its most important contribution -- its handling of templates -- as well as its use in existing applications.
{"title":"A Tool Framework for Static and Dynamic Analysis of Object-Oriented Software with Templates","authors":"K. Lindlan, J. Cuny, A. Malony, S. Shende, B. Mohr, R. Rivenburgh, C. Rasmussen","doi":"10.1109/SC.2000.10052","DOIUrl":"https://doi.org/10.1109/SC.2000.10052","url":null,"abstract":"The developers of high-performance scientific applications often work in complex computing environments that place heavy demands on program analysis tools. The developers need tools that interoperate, are portable across machine architectures, and provide source-level feedback. In this paper, we describe a tool framework, the Program Database Toolkit (PDT), that supports the development of program analysis tools meeting these requirements. PDT uses compile-time information to create a complete database of high-level program information that is structured for well-defined and uniform access by tools and applications. PDT’s current applications make heavy use of advanced features of C++, in particular, templates. We describe the toolkit, focussing on its most important contribution -- its handling of templates -- as well as its use in existing applications.","PeriodicalId":228250,"journal":{"name":"ACM/IEEE SC 2000 Conference (SC'00)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124150666","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}
The hybrid memory model of clusters of multiprocessors raises two issues: programming model and performance. Many parallel programs have been written by using the MPI standard. To evaluate the pertinence of hybrid models for existing MPI codes, we compare a unified model (MPI) and a hybrid one (OpenMP fine grain parallelization after profiling) for the NAS 2.3 benchmarks on two IBM SP systems. The superiority of one model depends on 1) the level of shared memory model parallelization, 2) the communication patterns and 3) the memory access patterns. The relative speeds of the main architecture components (CPU, memory, and network) are of tremendous importance for selecting one model. With the used hybrid model, our results show that a unified MPI approach is better for most of the benchmarks. The hybrid approach becomes better only when fast processors make the communication performance significant and the level of parallelization is sufficient.
{"title":"MPI versus MPI+OpenMP on the IBM SP for the NAS Benchmarks","authors":"F. Cappello, D. Etiemble","doi":"10.1109/SC.2000.10001","DOIUrl":"https://doi.org/10.1109/SC.2000.10001","url":null,"abstract":"The hybrid memory model of clusters of multiprocessors raises two issues: programming model and performance. Many parallel programs have been written by using the MPI standard. To evaluate the pertinence of hybrid models for existing MPI codes, we compare a unified model (MPI) and a hybrid one (OpenMP fine grain parallelization after profiling) for the NAS 2.3 benchmarks on two IBM SP systems. The superiority of one model depends on 1) the level of shared memory model parallelization, 2) the communication patterns and 3) the memory access patterns. The relative speeds of the main architecture components (CPU, memory, and network) are of tremendous importance for selecting one model. With the used hybrid model, our results show that a unified MPI approach is better for most of the benchmarks. The hybrid approach becomes better only when fast processors make the communication performance significant and the level of parallelization is sufficient.","PeriodicalId":228250,"journal":{"name":"ACM/IEEE SC 2000 Conference (SC'00)","volume":"124 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132626546","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}
Compiler transformations can significantly improve data locality for many scientific programs. In this paper, we show iterative solvers for partial differential equations (PDEs) in three dimensions require new compiler optimizations not needed for 2D codes, since reuse along the third dimension cannot fit in cachefor larger problem sizes. Tiling is a program transformation compilers can apply to capture this reuse, but successful application of tiling requires selection of non-conflicting tiles and/or padding array dimensions to eliminate conflicts. We present new algorithms and cost models for selecting tiling shapes and array pads. We explain why tiling is rarely needed for 2D PDE solvers, but can be helpful for 3D stencil codes. Experimental results show tiling 3D codes can reduce miss rates and achieve performance improvements of 17-121% for key scientific kernels, including a 27% average improvement for the key computational loop nest in the SPEC/NAS benchmark MGRID.
{"title":"Tiling Optimizations for 3D Scientific Computations","authors":"Gabriel Rivera, C. Tseng","doi":"10.1109/SC.2000.10015","DOIUrl":"https://doi.org/10.1109/SC.2000.10015","url":null,"abstract":"Compiler transformations can significantly improve data locality for many scientific programs. In this paper, we show iterative solvers for partial differential equations (PDEs) in three dimensions require new compiler optimizations not needed for 2D codes, since reuse along the third dimension cannot fit in cachefor larger problem sizes. Tiling is a program transformation compilers can apply to capture this reuse, but successful application of tiling requires selection of non-conflicting tiles and/or padding array dimensions to eliminate conflicts. We present new algorithms and cost models for selecting tiling shapes and array pads. We explain why tiling is rarely needed for 2D PDE solvers, but can be helpful for 3D stencil codes. Experimental results show tiling 3D codes can reduce miss rates and achieve performance improvements of 17-121% for key scientific kernels, including a 27% average improvement for the key computational loop nest in the SPEC/NAS benchmark MGRID.","PeriodicalId":228250,"journal":{"name":"ACM/IEEE SC 2000 Conference (SC'00)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132302719","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}
Toshiyuki Takahashi, S. Sumimoto, A. Hori, H. Harada, Y. Ishikawa
This paper introduces a high performance communication middle layer, called PM2, for hetero-geneous network environments. PM2 currently supports Myrinet, Ethernet, and SMP. Binary code written in PM2 or written in a communication library, such as MPICH-SCore on top of PM2, may run on any combination of those networks without re-compilation. According to a set of NAS parallel benchmark results, MPICH-SCore performance is better than dedicated communication libraries such as MPICH-BIP/SMP and MPICH-GM when running some benchmark programs.
{"title":"PM2: High Performance Communication Middleware for Heterogeneous Network Environments","authors":"Toshiyuki Takahashi, S. Sumimoto, A. Hori, H. Harada, Y. Ishikawa","doi":"10.1109/SC.2000.10013","DOIUrl":"https://doi.org/10.1109/SC.2000.10013","url":null,"abstract":"This paper introduces a high performance communication middle layer, called PM2, for hetero-geneous network environments. PM2 currently supports Myrinet, Ethernet, and SMP. Binary code written in PM2 or written in a communication library, such as MPICH-SCore on top of PM2, may run on any combination of those networks without re-compilation. According to a set of NAS parallel benchmark results, MPICH-SCore performance is better than dedicated communication libraries such as MPICH-BIP/SMP and MPICH-GM when running some benchmark programs.","PeriodicalId":228250,"journal":{"name":"ACM/IEEE SC 2000 Conference (SC'00)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2000-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130318317","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：