Buscar
Mostrando ítems 1-10 de 67
Function Call Re-vectorization
(Universidade Federal de Minas GeraisUFMG, 2017-03-21)
SPMD programming languages for SIMD hardware such as C for CUDA, OpenCL or ISPC have contributed to increase the programmability of SIMD accelerators and graphics processing units. However, SPMD languages still lack the ...
String Matching Aproximado mejorado con SIMD
(Facultad de Ciencias Exactas, Ingeniería y Agrimensura. Universidad Nacional de Rosario, 2022)
Implementación del algoritmo de Smith - Waterman utilizando instrucciones SIMD mediante OPENMP
(Universidad Nacional de San Antonio Abad del CuscoPE, 2016)
El presente trabajo aborda el problema de acelerar la ejecución del algoritmo de Smith-Waterman haciendo uso de las instrucciones vectoriales disponibles en las CPU modernas. Como ejemplo de implementaciones de Smith-Waterman ...
Aumentando os benefícios SIMD por meio de uma detecção de DLP em tempo de execução e energeticamente eficiente
(Universidade Federal de Santa MariaBrasilCiência da ComputaçãoUFSMPrograma de Pós-Graduação em Ciência da ComputaçãoCentro de Tecnologia, 2019-02-22)
Multimedia applications have been widely present in embedded devices. Due to their
intrinsic nature, such application domain is benefited from Data Level Parallelism (DLP). In order
to improve performance-energy tradeoff, ...
Divergência em GPU: análises e alocação de registradores
(Universidade Federal de Minas GeraisUFMG, 2013-03-08)
The use of graphics processing units (GPUs) for accelerating Data Parallel workloads is the new trend on the computing market. This growing interest brought renewed attention to the Single Instruction Multiple Data (SIMD) ...
Efficient Algorithms for Large-Scale Image Analysis
This work develops highly efficient algorithms for analyzing large images. Applications include object-based change detection and screening. The algorithms are 10-100 times as fast as existing software, sometimes even ...
Sincronização de threads em hardware SIMD
(Universidade Federal de Minas GeraisUFMG, 2013-08-23)
Performance is constrained by power consumption in modern computer architectures.One way to reduce power consumption, and hence increase performance, is to eliminate redundant operations between assembly instructions.This ...
Simd Parallel Algorithm For Classifying Binary Image Contours Based On Mathematical Morphology
(IEEE, Los Alamitos, CA, United States, 1996)