Optimized Composition: Generating Efficient Code for Heterogeneous\n Systems from Multi-Variant Components, Skeletons and Containers

2014/05/12 by Christoph Keßler, Kessler, Christoph, Usman Dastgeer +3
Computer Science · #Cloud Computing and Resource Management #Distributed #Distributed and Parallel Computing Systems #FOS: Computer and information sciences #Parallel #Parallel Computing and Optimization Techniques #and Cluster Computing (cs.DC)

paper · pdf · doi:10.48550/arxiv.1405.2915

openalex publication_date 2014/05/12 · openalex created_date 2019/07/30 · openalex updated_date 2026/07/28

Abstract

In this survey paper, we review recent work on frameworks for the high-level,\nportable programming of heterogeneous multi-/manycore systems (especially,\nGPU-based systems) using high-level constructs such as annotated user-level\nsoftware components, skeletons (i.e., predefined generic components) and\ncontainers, and discuss the optimization problems that need to be considered in\nselecting among multiple implementation variants, generating code and providing\nruntime support for efficient execution on such systems.\n

Citations

• MapReduce

Related

• Enabling Dynamic Selection of Implementation Variants in Component-Based Parallel Programming for Heterogeneous Systems
• Parallel Programming Models for Heterogeneous Many-Cores : A Survey
• Patterns and Rewrite Rules for Systematic Code Generation (From High-Level Functional Patterns to High-Performance OpenCL Code)
• A Unified Programming Model for Heterogeneous Computing with CPU and Accelerator Technologies
• Collaborative Heterogeneous Computing on MPSoCs