检索结果-内蒙古大学图书馆

IEEE 23rd Annual Symposium on High-Performance Interconnects

作者： Shamis, Pavel Venkata, Manjunath Gorentla Lopez, M. Graham Baker, Matthew B. Hernandez, Oscar Itigin, Yossi Dubman, Mike Shainer, Gilad Graham, Richard L. Liss, Liran Shahar, Yiftah Potluri, Sreeram Rossetti, Davide Becker, Donald Poole, Duncan Lamb, Christopher Kumar, Sameer Stunkel, Craig Bosilca, George Bouteiller, Aurelien Oak Ridge Natl Lab Oak Ridge TN 37831 USA Mellanox Technol Yokneam Illit Israel NVIDIA Corp Santa Clara CA USA IBM Corp Armonk NY USA Univ Tennessee Knoxville TN USA

ISBN: (纸本)9781467391603

This paper presents Unified Communication X (UCX), a set of network APIs and their implementations for high throughput computing. UCX comes from the combined effort of national laboratories, industry, and academia to design and implement a high-performing and highly-scalable network stack for next generation applications and systems. UCX design provides the ability to tailor its APIs and network functionality to suit a wide variety of application domains and hardware. We envision these APIs to satisfy the networking needs of many programming models such as Message Passing Interface (MPI), OpenSHMEM, Partitioned Global Address Space (PGAS) languages, task-based paradigms and I/O bound applications. To evaluate the design we implement the APIs and protocols, and measure the performance of overhead-critical network primitives fundamental for implementing many parallel programming models and system libraries. Our results show that the latency, bandwidth, and message rate achieved by the portable UCX prototype is very close to that of the underlying driver. With UCX, we achieved a message exchange latency of 0.89 us, a bandwidth of 6138.5 MB/s, and a message rate of 14 million messages per second. As far as we know, this is the highest bandwidth and message rate achieved by any network stack (publicly known) on this hardware.

关键词： application program interfaces input-output programs message passing parallel programming public domain software HPC network APIs I/O bound applications MPI OpenSHMEM PGAS languages UCX Unified Communication X high throughput computing highly-scalable network stack message passing interface open source framework parallel programming models partitioned global address space languages system libraries task-based paradigms Bandwidth Electronics packaging Hardware Libraries Memory management programming Protocols HPC Infiniband Middleware PGAS RDMA message passing mannose phosphate isomerase remote procedure calls parallel programming input-output programs open source software Application programming interfaces Infiniband Electronics packaging RDMA Bandwidth High Performance Computing Computer hardware Store management Middleware

来源：评论

学校读者我要写书评

暂无评论

Accelerating OpenSHMEM Collectives using In-Network Computing Approach 31

Accelerating OpenSHMEM Collectives using In-Network Computin...

引用

31st International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)

作者： Venkata, Manjunath Gorentla Shainer, Gilad Graham, Richard L. Bloch, Gil Mellanox Technol Sunnyvale CA 94085 USA Mellanox Technol Yokneam IL USA

ISBN: (纸本)9781728141947

OpenSHMEM is one of the key programming models for High Performance Computing (HPC) applications with irregular communication patterns. Particularly, it is useful for problems that cannot be decomposed easily such as graph partitioning. The programming model supports Remote Memory Access (RMA), atomics, and collective operations. In this paper, we explore and evaluate the In-network Computing approach for accelerating the OpenSHMEM collective operations, particularly barrier, broadcast, and reduction operations. To achieve acceleration, In-network Computing leverages hardware engines on the networking elements and effective software that can efficiently use these capabilities. We explore the value of this approach for collective operations on the InfiniBand Host Channel Adapters (HCAs) and switches. Particularly, we focus on the recently introduced collective offload feature provided by the Mellanox Scalable Hierarchical Aggregation and Reduction Protocol (SHARP)(TM) capability, which accelerates the barriers and reduction operations;the multicast capability accelerates the broadcast collective operation. To leverage the hardware capabilities, we complement it with an effective software stack that includes Hierarchical Collectives (HCOLL) library, and SHARP layer. Our evaluation on Oak Ridge National Laboratory (ORNL)'s Summit system, which is the fastest supercomputer on the June 2019 Top 500 list, show that the hardware and software acceleration in the In-network Computing approach is key for achieving the performance and scalability required for collectives and applications. For a 5120 process OpenSHMEM job, our results show that the barrier operation is 710% faster, broadcast is 370% faster, and reduction operation is 10 times faster when compared with the implementation of collective operations with no acceleration. Further, experiments with a 2D-Heat kernel show that the In-network Computing approach is very effective for real-world applications.

关键词： parallel programming models Collective Operations HPC MPI InfiniBand

来源：评论

学校读者我要写书评

暂无评论

Scalable task parallel programming in the partitioned global address space

Scalable task parallel programming in the partitioned global...

引用

作者： Dinan, James Scott The Ohio State University

学位级别：Ph.D.

Applications that exhibit irregular, dynamic, and unbalanced parallelism are growing in number and importance in the computational science and engineering communities. These applications span many domains including computational chemistry, physics, biology, and data mining. In such applications, the units of computation are often irregular in size and the availability of work may be depend on the dynamic, often recursive, behavior of the program. Because of these properties, it is challenging for these programs to achieve high levels of performance and scalability on modern high performance clusters.@pqdt@break@A new family of programming models, called the Partitioned Global Address Space (PGAS) family, provides the programmer with a global view of shared data and allows for asynchronous, one-sided access to data regardless of where it is physically stored. In this model, the global address space is distributed across the memories of multiple nodes and, for any given node, is partitioned into local patches that have high affinity and low access cost and remote patches that have a high access cost due to communication. The PGAS data model relaxes conventional two-sided communication semantics and allows the programmer to access remote data without the cooperation of the remote processor. Thus, this model is attractive for supporting irregular and dynamic applications on distributed memory clusters. However, in spite of the flexible data model, PGAS execution models require the programmer to explicitly partition the computation into a process-centric execution.@pqdt@break@In this work, we build a complete environment to support irregular and dynamic parallel computations on large scale clusters by extending the PGAS data model with a task parallel execution model. Task parallelism allows the programmer to express their computation as a dynamic collection of tasks. The execution of these tasks is managed by a scalable and efficient runtime system that performs dynamic

关键词： Computer Science High performance computing parallel programming models Scalable runtime systems

来源：评论

学校读者我要写书评

暂无评论

KokkACC: Enhancing Kokkos with OpenACC 9

KokkACC: Enhancing Kokkos with OpenACC

引用

9th Workshop on Accelerator programming Using Directives (WACCPD)

作者： Valero-Lara, Pedro Lee, Seyong Gonzalez-Tallada, Marc Denny, Joel Vetter, Jeffrey S. Oak Ridge Natl Lab ORNL Oak Ridge TN 37830 USA

ISBN: (纸本)9781665490191

Template metaprogramming is gaining popularity as a high-level solution for achieving performance portability on heterogeneous computing resources. Kokkos is a representative approach that offers programmers high-level abstractions for generic programming while most of the device-specific code generation and optimizations are delegated to the compiler through template specializations. For this, Kokkos provides a set of device-specific code specializations in multiple back ends, such as CUDA and HIP. Unlike CUDA or HIP, OpenACC is a high-level and directive-based programming model. This descriptive model allows developers to insert hints (pragmas) into their code that help the compiler to parallelize the code. The compiler is responsible for the transformation of the code, which is completely transparent to the programmer. This paper presents an OpenACC back end for Kokkos: KokkACC. As an alternative to Kokkos's existing device-specific back ends, KokkACC is a multi-architecture back end providing a high-productivity programming environment enabled by OpenACC's high-level and descriptive programming model. Moreover, we have observed competitive performance;in some cases, KokkACC is faster (up to 9x) than NVIDIA's CUDA back end and much faster than OpenMP's GPU offloading back end. This work also includes implementation details and a detailed performance study conducted with a set of mini-benchmarks (AXPY and DOT product) and three mini-apps (LULESH, miniFE and SNAP, a LAMMPS proxy mini-app).

关键词： OpenACC C plus plus Metaprogramming Kokkos CUDA OpenMP Target parallel programming models

来源：评论

学校读者我要写书评

暂无评论

programming bare-metal accelerators with heterogeneous threading models:a case study of Matrix-3000

引用

Frontiers of Information Technology & Electronic Engineering 2023年第4期24卷 509-520页

作者： Jianbin FANG Peng ZHANG Chun HUANG Tao TANG Kai LU Ruibo WANG Zheng WANG College of Computer Science and Technology National University of Defense TechnologyChangsha 410073China School of Computing University of LeedsLeeds LS29JTUK

As the hardware industry moves toward using specialized heterogeneous many-core processors to avoid the effects of the power wall,software developers are finding it hard to deal with the complexity of these *** this paper,we share our experience of developing a programming model and its supporting compiler and libraries for Matrix-3000,which is designed for next-generation exascale supercomputers but has a complex memory hierarchy and processor *** assist its software development,we have developed a software stack from scratch that includes a low-level programming interface and a high-level OpenCL *** low-level programming model offers native programming support for using the bare-metal accelerators of Matrix-3000,while the high-level model allows programmers to use the OpenCL programming *** detail our design choices and highlight the lessons learned from developing system software to enable the programming of bare-metal *** programming models have been deployed in the production environment of an exascale prototype system.

关键词： Heterogeneous computing parallel programming models Programmability Compilers Runtime systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Kokkos with OpenACC

引用

INTERNATIONAL JOURNAL OF HIGH PERFORMANCE COMPUTING APPLICATIONS 2024年第5期38卷 409-426页

作者： Valero-Lara, Pedro Lee, Seyong Gonzalez-Tallada, Marc Denny, Joel Teranishi, Keita Vetter, Jeffrey S. Oak Ridge Natl Lab 1 Bethel Valley Rd Oak Ridge TN 37830 USA Univ Politecn Cataluna Barcelona Spain

C++ template metaprogramming has emerged as a prominent approach for achieving performance portability in heterogeneous computing. Kokkos represents a notable paradigm in this domain, offering programmers a suite of high-level abstractions for generic programming while deferring much of the device-specific code generation and optimization to the compiler through template specializations. Kokkos furnishes a range of device-specific code specializations across multiple back ends, including CUDA and HIP. Diverging from conventional back ends, the OpenACC implementation presents a high-level, multicompiler, multidevice, and directive-based programming model. This paper presents recent advancements in the OpenACC back end for Kokkos (i.e., KokkACC) and focuses on its integration into the Kokkos ecosystem, exploration of automatic device selection capabilities to enhance productivity, and performance evaluation on modern hardware such as NVIDIA H100 GPUs. The study includes implementation details and a thorough performance assessment across various computational benchmarks, including minibenchmarks (AXPY and DOT product), miniapps (LULESH, MiniFE, and SNAP-LAMMPS), and a scientific kernel based on the lattice Boltzmann method.

关键词： OpenACC C plus plus metaprogramming Kokkos CUDA OpenMP target parallel programming models

来源：评论

学校读者我要写书评

暂无评论

Task-based parallel programming for Scalable Matrix Product Algorithms

引用

ACM TRANSACTIONS ON MATHEMATICAL SOFTWARE 2023年第2期49卷 15-15页

作者： Agullo, Emmanuel Buttari, Alfredo Guermouche, Abdou Herrmann, Julien Jego, Antoine Inria LaBRI 200 Vieille Tour F-33405 Talence France IRIT ENSEEIHT 2 Rue Charles Camichel F-31071 Toulouse France

Task-based programming models have succeeded in gaining the interest of the high-performance mathematical software community because they relieve part of the burden of developing and implementing distributed-memory parallel algorithms in an efficient and portable way. In increasingly larger, more heterogeneous clusters of computers, these models appear as a way to maintain and enhance more complex algorithms. However, task-based programming models lack the flexibility and the features that are necessary to express in an elegant and compact way scalable algorithms that rely on advanced communication patterns. We show that the Sequential Task Flow paradigm can be extended to write compact yet efficient and scalable routines for linear algebra computations. Although, this work focuses on dense General Matrix Multiplication, the proposed features enable the implementation of more complex algorithms. We describe the implementation of these features and of the resulting GEMM operation. Finally, we present an experimental analysis on two homogeneous supercomputers showing that our approach is competitive up to 32,768 CPU cores with state-of-the-art libraries and may outperform them for some problem dimensions. Although our code can use GPUs straightforwardly, we do not deal with this case because it implies other issues which are out of the scope of this work.

关键词： parallel programming models scalable linear algebra algorithms runtime systems distributed memory parallelism sequential task flow

来源：评论

学校读者我要写书评

暂无评论

EVALUATING COMPUTATIONAL COSTS WHILE HANDLING DATA AND CONTROL parallelISM

引用

parallel PROCESSING LETTERS 2008年第1期18卷 165-174页

作者： Campa, Sonia Univ Pisa Dept Comp Sci I-56123 Pisa Italy

The aim of this work is to introduce a computational costs system associated to a semantic framework for orthogonal data and control parallelism handling. In such a framework a parallel application is described by a semantic expression involving in an orthogonal manner both data access and control parallelism abstractions. The evaluation of such an expression is driven by a set of rewriting rules each of which is combined with a computational cost. We present how to proceed in the evaluation of the final cost of the application as well as how such information together with the semantic framework capabilities can be exploited to increase the overall performance.

关键词： parallel programming models data parallelism control parallelism formal semantics cost modelling

来源：评论

学校读者我要写书评

暂无评论

parallel signal processing with S-Net

引用

Procedia Computer Science 2010年第1期1卷 2085-2094页

作者： Frank Penczek Stephan Herhut Clemens Grelck Sven-Bodo Scholz Alex Shafarenko Rémi Barrère Eric Lenormand University of Hertfordshire School of Computer Science Hatfield UK University of Amsterdam Institute of Informatics Amsterdam The Netherlands Thales Research & Technologies Palaiseau France

We argue that programming high-end stream-processing applications requires a form of coordination language that enables the designer to represent interactions between stream-processing functions asynchronously. We further argue that the level of abstraction that current programming tools engender should be drastically increased and present a coordination language and component technology that is suitable for that purpose. We demonstrate our approach on a real radar-data processing application from which we reuse all existing components and present speed-ups that we were able to achieve on contemporary multi-core hardware.

关键词： parallel programming models Component models Signal processing Stream processing

来源：评论

学校读者我要写书评

暂无评论

Enabling HMMER for the Grid with COMP Superscalar

引用

Procedia Computer Science 2010年第1期1卷 2629-2638页

作者： Enric Tejedor Rosa M. Badia Romina Royo Josep L. Gelpí Universitat Politècnica de Catalunya Jordi Girona 34. 08034 Barcelona Spain Barcelona Supercomputing Center Jordi Girona 29. 08034 Barcelona Spain Consejo Superior de Investigaciones Científicas Serrano 117. Madrid E-28006 Spain National Institute of Bioinformatics Dept of Biochemistry and Molecular Biology (Universitat de Barcelona) & Institute of Research on Biomedicine

The continuously increasing size of biological sequence databases has motivated the development of analysis suites that, by means of parallelization, are capable of performing faster searches on such databases. However, many of these tools are not suitable for execution on mid-to-large scale parallel infrastructures such as computational Grids. This paper shows how COMP Superscalar can be used to effectively parallelize on the Grid a sequence analysis program. In particular, we present a sequential version of the HMMER hmmpfam tool that, when run with COMP Superscalar, is decomposed into tasks and run on a set of distributed resources, not burdening the programmer with parallelization efforts. Although performance is not a main objective of this work, we also present some test results where COMP Superscalar, using a new pre-scheduling technique, clearly outperforms a well-known parallelization of the hmmpfam algorithm.

关键词： parallel programming models Bionformatics applications

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：