Unified Parallel C (UPC) is a parallel extension of ANSI C based on the Partitioned Global Address Space (PGAS) programming model, which provides a shared memory view that simplifies code development while it can ...Unified Parallel C (UPC) is a parallel extension of ANSI C based on the Partitioned Global Address Space (PGAS) programming model, which provides a shared memory view that simplifies code development while it can take advantage of the scalability of distributed memory architectures. Therefore, UPC allows programmers to write parallel applications on hybrid shared/distributed memory architectures, such as multi-core clusters, in a more productive way, accessing remote memory by means of different high-level language constructs, such as assignments to shared variables or collective primitives. However, the standard UPC collectives library includes a reduced set of eight basic primitives with quite limited functionality. This work presents the design and implementation of extended UPC collective functions that overcome the limitations of the standard collectives library, allowing, for example, the use of a specific source and destination thread or defining the amount of data transferred by each particular thread. This library fulfills the demands made by the UPC developers community and implements portable algorithms, independent of the specific UPC compiler/runtime being used. The use of a representative set of these extended collectives has been evaluated using two applications and four kernels as case studies. The results obtained confirm the suitability of the new library to provide easier programming without trading off performance, thus achieving high productivity in parallel programming to harness the performance of hybrid shared/distributed memory architectures in high performance computing.展开更多
The production-oriented approach (POA) has been developed over a decade. It is driven by the need to improve English classroom instruction for university students in China (Wen, 2016). It is also motivated by the ...The production-oriented approach (POA) has been developed over a decade. It is driven by the need to improve English classroom instruction for university students in China (Wen, 2016). It is also motivated by the aspiration to enhance the quality of foreign language education in other similar pedagogical contexts outside China. A volume of research has been done by Wen Qiufang and her research team, to formulate the theory of POA and to test its effectiveness in classroom pedagogy (e.g. Wen, 2016, 2015; Yang, 2015; Zhang, 2015). At the moment, the POA is still at an early stage of theory building and almost all empirical research is done in the Chinese context. In order to improve the quality of this theory and to make it intelligible to the international academic community, a one-day symposium was held in Beijing Foreign Studies University on May 15, 2017. The symposium was entitled 'The first international forum on innovative foreign language education in China: Appraisal of the POA'. In the forum, leading experts in applied linguistics were invited to discuss the strengths and weaknesses of the POA and the directions for its future development. The symposium was the first attempt for the POA research team to discuss its latest work with international scholars. This Viewpoint section collects the responses of four experts who participated in the symposium, listed in alphabetical order. The collection of articles covers three topics related to the POA: its pedagogical application, its use for teacher training, and its research. Alister Cumming is Professor Emeritus and the former Head of the Centre for Educational Research on Languages and Literacies, University of Toronto, Canada. His article focuses primarily on POA research as an exemplary case of design-based research. Rod Ellis is Research Professor in the School of Education at Curtin University, Australia. He discusses POA in terms of pedagogy, teacher training and research, with both critiques and constructive suggestions. Paul Kei M展开更多
基金funded by Hewlett-Packard (Project "Improving UPC Usability and Performance in Constellation Systems:Implementation/Extensions of UPC Libraries")partially supported by the Ministry of Science and Innovation of Spain under Project No.TIN2010-16735the Galician Government (Consolidation of Competitive Research Groups,Xunta de Galicia ref.2010/6)
文摘Unified Parallel C (UPC) is a parallel extension of ANSI C based on the Partitioned Global Address Space (PGAS) programming model, which provides a shared memory view that simplifies code development while it can take advantage of the scalability of distributed memory architectures. Therefore, UPC allows programmers to write parallel applications on hybrid shared/distributed memory architectures, such as multi-core clusters, in a more productive way, accessing remote memory by means of different high-level language constructs, such as assignments to shared variables or collective primitives. However, the standard UPC collectives library includes a reduced set of eight basic primitives with quite limited functionality. This work presents the design and implementation of extended UPC collective functions that overcome the limitations of the standard collectives library, allowing, for example, the use of a specific source and destination thread or defining the amount of data transferred by each particular thread. This library fulfills the demands made by the UPC developers community and implements portable algorithms, independent of the specific UPC compiler/runtime being used. The use of a representative set of these extended collectives has been evaluated using two applications and four kernels as case studies. The results obtained confirm the suitability of the new library to provide easier programming without trading off performance, thus achieving high productivity in parallel programming to harness the performance of hybrid shared/distributed memory architectures in high performance computing.
文摘The production-oriented approach (POA) has been developed over a decade. It is driven by the need to improve English classroom instruction for university students in China (Wen, 2016). It is also motivated by the aspiration to enhance the quality of foreign language education in other similar pedagogical contexts outside China. A volume of research has been done by Wen Qiufang and her research team, to formulate the theory of POA and to test its effectiveness in classroom pedagogy (e.g. Wen, 2016, 2015; Yang, 2015; Zhang, 2015). At the moment, the POA is still at an early stage of theory building and almost all empirical research is done in the Chinese context. In order to improve the quality of this theory and to make it intelligible to the international academic community, a one-day symposium was held in Beijing Foreign Studies University on May 15, 2017. The symposium was entitled 'The first international forum on innovative foreign language education in China: Appraisal of the POA'. In the forum, leading experts in applied linguistics were invited to discuss the strengths and weaknesses of the POA and the directions for its future development. The symposium was the first attempt for the POA research team to discuss its latest work with international scholars. This Viewpoint section collects the responses of four experts who participated in the symposium, listed in alphabetical order. The collection of articles covers three topics related to the POA: its pedagogical application, its use for teacher training, and its research. Alister Cumming is Professor Emeritus and the former Head of the Centre for Educational Research on Languages and Literacies, University of Toronto, Canada. His article focuses primarily on POA research as an exemplary case of design-based research. Rod Ellis is Research Professor in the School of Education at Curtin University, Australia. He discusses POA in terms of pedagogy, teacher training and research, with both critiques and constructive suggestions. Paul Kei M