Co-design Implications of Cost-effective On-demand Acceleration for Cloud Healthcare Analytics: The AEGLE approach
Dimosthenis Masouros1,a, Konstantina Koliogeorgi1,b, Georgios Zervakis1,c, Alexandra Kosvyra2,f, Achilleas Chytas2,g, Sotirios Xydis1,d, Ioanna Chouvarda2,h and Dimitrios Soudris1,e
1Microprocessors and Digital Systems Laboratory, ECE , National Technical University of Athens, Greece
ademo.masouros@microlab.ntua.gr
bkonstantina@microlab.ntua.gr
czervakis@microlab.ntua.gr
dsxydis@microlab.ntua.gr
edsoudris@microlab.ntua.gr
2Lab of Computing, Medical Informatics and Biomedical Imaging Technologies, SM, Aristotle University of Thessaloniki, Greece
faekosvyra@auth.gr
gachillec@auth.gr
hioannach@auth.gr
ABSTRACT
Nowadays, big data and machine learning are transforming the way we realize and manage our data. Even though the healthcare domain has recognized big data analytics as a prominent candidate, it has not yet fully grasped their promising benefits that allow medical information to be converted to useful knowledge. In this paper, we introduce AEGLE's big data infrastructure provided as a Platform as a Service. Utilizing the suite of genomic analytics from the Chronic Lymphocytic Leukaemia (CLL) use case, we show that on-demand acceleration is profitable w.r.t a pure software cloud-based solution. However, we further show that on-demand acceleration is not offered as a "free-lunch" and we provide an in-depth analysis and lessons learnt on the co-design implications to be carefully considered for enabling cost-effective acceleration at the cloud-level.
Keywords: Cloud, Platform as a Service (PaaS), Big Data Framework, Big Data Analytics, Co-design, On-demand Acceleration, Genomic.
