2026-05-30T03:55:42Zhttps://riuma.uma.es/rest/oai/request

oai:riuma.uma.es:10630/144252026-02-03T12:08:58Zcom_10630_2254col_10630_37959

Villegas Fernández, Alejandro Asenjo-Plaza, Rafael González-Navarro, María Ángeles Plata-González, Óscar Guillermo Ubal, Rafael Kaeli, David 2017-09-06T06:41:12Z 2017-09-06T06:41:12Z 2017-08-29 http://hdl.handle.net/10630/14425 http://orcid.org/0000-0002-1570-3863 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 low-latency local memory space shared by a subset of the threads. The latter is used as a scratchpad to improve the performance of the applications. We propose GPU-LocalTM, a hardware transactional memory (TM), as an alternative to data locking mechanisms in local memory. GPU-LocalTM allocates transactional metadata in the existing memory resources, minimizing the storage requirements for TM support. In addition, it ensures forward progress through an automatic serialization mechanism. In our experiments, GPU-LocalTM provides up to 100X speedup over serialized execution. eng open access by-nc-nd Ordenadores - Equipo de entrada y salida - Congresos Hardware support for scratchpad memory transactions on GPU architectures conference output