Lightweight Hardware Transactional Memory for GPU Scratchpad Memory.
IEEE Transactions on Computers(2018)
摘要
Graphics Processing Units (GPUs) have become the accelerator of choice for data-parallel applications, enabling the execution of thousands of threads in a Single Instruction - Multiple Thread (SIMT) fashion. Using OpenCL terminology, GPUs offer a global memory space shared by all the threads in the GPU, as well as a local memory space shared by only a subset of the threads. Programmers can use loc...
更多查看译文
关键词
Graphics processing units,Synchronization,Hardware,Memory management,Programming,Instruction sets,Genetic algorithms
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络