检索结果-内蒙古大学图书馆

Flexible task-DAG management in PHAST library: Data-parallel tasks and orchestration support for heterogeneous systems

引用

CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE 2022年第2期34卷

作者： Peccerillo, Biagio Bartolini, Sandro Univ Siena Dept Informat Engn & Math Sci Via Roma 56 I-53100 Siena Italy

Heterogeneous architectures proved successful in achieving unprecedented performance and energy-efficiency. However, taking advantage of these diverse processing elements is still hard. Programmers need to code through the different approaches suitable for each target architecture and need to decide the distribution of activities on the different resources. The majority of current frameworks focuses on either performance or productivity. The former mainly provides low-level target-specific programming interfaces, and the latter offers high-level tools that often fail in achieving high-performance. In both cases, the design is usually data-parallel, as task-parallelism is not supported. In this work, we propose a task-based solution within the data-parallel heterogeneous single-source PHAST library. Tasks can be coded in a target-agnostic fashion, can be compiled and parallelized on multi-core CPUs and NVIDIA GPUs automatically and support the choice of the execution platform at runtime. We evaluate the capabilities of the proposed task-directed acyclic graph support in case of an extensive set of randomly generated task-based applications with different sizes and characteristics. We compare it against a SYCL implementation in terms of performance and complexity metrics, highlighting that PHAST achieves about 1.56x and 2.60x speedup over SYCL for multi-core CPU and GPU, respectively, while improving also code complexity metrics.

关键词： complexity metrics data-parallelism heterogeneous computing single-source parallel programming task-based parallelism

来源：评论

学校读者我要写书评

暂无评论

single-source Library for Enabling Seamless Assignment of Data-parallel Task-DAGs to CPUs and GPUs in Heterogeneous Architectures 2019

Single-source Library for Enabling Seamless Assignment of Da...

引用

10th Workshop on parallel programming and Run-Time Management Techniques for Many-Core Architectures / 8th Workshop on Design Tools and Architectures For Multicore Embedded Computing Platforms (PARMA-DITAM)

作者： Peccerillo, Biagio Bartolini, Sandro Univ Siena Dept Informat Engn & Math Sci Siena Italy

ISBN: (纸本)9781450363211

Currently, the majority of devices is heterogeneous and comprises at least a multi-core CPU and a GPU. Exploiting these modules requires programmers to a) assign parallel activities to the different hardware resources, and b) code each activity through target-specific approaches x(e.g., multi-core CPUs and GPUs). Current frameworks do not provide high-productivity while guaranteeing performance comparable to low-level ones. Also, they often lack the easy exploration of possible task assignments to the heterogeneous resources, mainly because the assignment needs to be done in advance and the targets have software incompatibilities. This paper introduces task-DAGs (Directed Acyclic Graph) concepts into PHAST, a single-source data-parallel library that supports multi-core CPUs and NVIDIA GPUs. The resulting framework allows postponing the task-to-target assignment to the testing or runtime phase. In fact, each task is coded in a target-agnostic fashion and can be automatically optimized for a specific platform. The consequent productivity effects are shown for a computer-vision benchmark comparing to a SYCL implementation and performing an automatic task assignment for maximum resources utilization.

关键词： Heterogeneous computing data-parallelism single-source parallel programming design-space exploration task-based applications

来源：评论

学校读者我要写书评

暂无评论

Task-DAG Support in single-source PHAST Library: Enabling Flexible Assignment of Tasks to CPUs and GPUs in Heterogeneous Architectures 10

Task-DAG Support in Single-Source PHAST Library: Enabling Fl...

引用

10th International Workshop on programming Models and Applications for Multicores and Manycores (PMAM)

作者： Peccerillo, Biagio Bartolini, Sandro Univ Siena Dept Informat Engn & Math Sci Siena Italy

ISBN: (纸本)9781450362900

Nowadays, the majority of desktop, mobile, and embedded devices in the consumer and industrial markets are heterogeneous, as they contain at least multi-core CPU and GPU resources in the same However, exploiting the performance and energy-efficiency of these diverse processing elements does not come for free from a software point of view: programmers need to a) code each activity through the specific approaches, libraries, and frameworks suitable for their target architecture (e.g., CPUs and GPUs) along with the orchestration of such heterogeneous execution, and b) decide the distribution of sequential and parallel activities towards the different parallel hardware resources available. Current frameworks typically provide either low-abstraction-level target-specific and/or generic but not high-performance in terfaces, which complicate the exploration of different task assignments, with DAG(1) precedence relationship, to the available heterogeneous resources. To enable this, tasks would typically need to be coded one time for each target architecture due to the profound differences in their programming. In this work, we include the support of tasks and DAGs of data-parallel tasks within the single-source PHAST library, which currently supports both multi-core CPUs and NVIDIA GPUs, so that tasks are coded in a target-agnostic fashion and their targeting to multi-core or GPU architectures is automatic and efficient. The integration of this coding approach with tasks can help to postpone the choice of the execution platform for each task up to the testing, or even to the runtime, phase. Finally, we demonstrate the effects of this approach in the case of a sample image pipeline benchmark from the computer vision domain. We compare our implementation to a SYCL implementation from a productivity point of view. Also, we show that various task assignments can be seamlessly explored by implementing both the PEFT2 mapping technique along with an exhaustive search in the mappin

关键词： Heterogeneous computing data-parallelism single-source parallel programming design-space exploration task-based 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：