Title :
From GPGPU to Many-Core: Nvidia Fermi and Intel Many Integrated Core Architecture
Author :
Heinecke, Alexander ; Klemm, Michael ; Bungartz, Hans-Joachim
Author_Institution :
Tech. Univ. Munchen (TUM), Munich, Germany
Abstract :
Comparing the architectures and performance levels of an Nvidia Fermi accelerator with an Intel MIC Architecture coprocessor demonstrates the benefit of the coprocessor for bringing highly parallel applications into, or even beyond, GPGPU performance regions.
Keywords :
graphics processing units; multiprocessing systems; parallel architectures; GPGPU; Intel MIC Architecture coprocessor; Intel many integrated core architecture; Nvidia Fermi accelerator; parallel applications; Computer architecture; Coprocessors; Graphics processing unit; Microwave integrated circuits; Performance evaluation; Programming; Random access memory; GPGPU; Intel MIC Architecture; accelerator; coprocessor; many-core; scientific computing;
Journal_Title :
Computing in Science & Engineering
DOI :
10.1109/MCSE.2012.23
