Study of Raspberry Pi 2 Quad-core Cortex A7 CPU Cluster as a Mini Supercomputer

摘要

High performance computing (HPC) devices is no longer exclusive for academic,R&D, or military purposes. The use of HPC device such as supercomputer nowgrowing rapidly as some new area arise such as big data, and computersimulation. It makes the use of supercomputer more inclusive. Todayssupercomputer has a huge computing power, but requires an enormous amount ofenergy to operate. In contrast a single board computer (SBC) such as RaspberryPi has minimum computing power, but require a small amount of energy tooperate, and as a bonus it is small and cheap. This paper covers the result ofutilizing many Raspberry Pi 2 SBCs, a quad-core Cortex A7 900 MHz, as a clusterto compensate its computing power. The high performance linpack (HPL) is usedto benchmark the computing power, and a power meter with resolution 10mV / 10mAis used to measure the power consumption. The experiment shows that theincrease of number of cores in every SBC member in a cluster is not givingsignificant increase in computing power. This experiment give a recommendationthat 4 nodes is a maximum number of nodes for SBC cluster based on thecharacteristic of computing performance and power consumption.