A study of hardware performance counters selection for cross architectural GPU power modeling

Título:

A study of hardware performance counters selection for cross architectural GPU power modeling

Autor:

Pi Puig, Martín

Colaboradores:

; De Giusti, Laura Cristina; Naiouf, Ricardo Marcelo; De Giusti, Armando Eduardo

Temas:

PROCESADORES GRÁFICOS (GPUs)

En:

Congreso Argentino de Ciencias de la Computación (25to : 2019 : Río Cuarto, Córdoba)

Resumen:

In the exascale race where huge corporations are spending billions of dollars on designing highly efficient heterogeneous supercomputers, the real need to reduce power envelopes forces current technologies to face crucial challenges as well as it demands the scientific community to evaluate and optimize the performance-power ratio. While energy consumption continues to climb up, the viability of these massive systems becomes a growing concern. In this context, the relevance of specific power-related research works turns into a priority. So we here develop an exhaustive step-by-step process for selecting a comprehensive set of hardware performance counters to serve as an input in an eventual GPU cross-architectural power consumption model. Our experiments show a high power-performance correlation between shared GPU events. Also, we present a set of events that delivers exclusive performance information in order to predict accurately GPU power fluctuations.

URL/DOI:

http://sedici.unlp.edu.ar/handle/10915/90904

Palabras clave:

consumo de energía

Medio:

Soporte electrónico

Tipo de documento:

Artículo

Descripción física:

1 archivo (1,2 MB)

Idioma:

Español

Publicación:

, 2019

Puede solicitar más fácilmente el ejemplar con: A1302

Ver estantes