JaBEE: framework for object-oriented Java bytecode compilation and execution on graphics processor units
JaBEE: framework for object-oriented Java bytecode compilation and execution on graphics processor units
复制标题
JaBEE：图形处理器单元上面向对象的 Java 字节码编译和执行框架
DOI：
--
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
Vinod Grover
中科院分区：
文献类型：
--
作者：
Wojciech Zaremba;Yuan Lin;Vinod Grover
软件开发人员对执行Java和Java语言越来越感兴趣。. NET字节码程序在通用图形处理器单元（gpgpu）。现有的解决方案对对象操作的支持有限，并且通常需要显式处理CPU和GPU之间的内存传输。在本文中，我们描述了一个Java字节码执行环境（JaBEE），它支持gpu上常见的面向对象结构，如动态调度、封装和对象创建。此实验环境便于GPU代码编译、执行和透明内存管理。我们将我们的方法与基于cpu和基于cuda - c的相同程序的代码执行的性能进行比较。我们讨论了字节码在gpgpu上执行的挑战、限制和机遇。
There is an increasing interest from software developers in executing Java and .NET bytecode programs on General Purpose Graphics Processor Units (GPGPUs). Existing solutions have limited support for operations on objects and often require explicit handling of memory transfers between CPU and GPU. In this paper, we describe a Java Bytecode Execution Environment (JaBEE) which supports common object-oriented constructs such as dynamic dispatch, encapsulation and object creation on GPUs. This experimental environment facilitates GPU code compilation, execution and transparent memory management. We compare the performance of our approach with CPU-based and CUDA-C-based code executions of the same programs. We discuss challenges, limitations and opportunities of bytecode execution on GPGPUs.