BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20211207T054759Z
LOCATION:227-228
DTSTART;TZID=America/Chicago:20211116T140000
DTEND;TZID=America/Chicago:20211116T143000
UID:submissions.supercomputing.org_SC21_sess148_pap254@linklings.com
SUMMARY:Ribbon: Cost-Effective and QoS-Aware Deep Learning Model Inference
  Using a Diverse Pool of Cloud Computing Instances
DESCRIPTION:Paper\n\nRibbon: Cost-Effective and QoS-Aware Deep Learning Mo
 del Inference Using a Diverse Pool of Cloud Computing Instances\n\nLi, Roy
 , Patel, Gadepally, Gettings...\n\nDeep learning model inference is a key 
 service in many businesses and scientific discovery processes. This paper 
 introduces Ribbon, a novel deep learning inference serving system that mee
 ts two competing objectives: quality-of-service (QoS) target and cost-effe
 ctiveness. The key idea behind Ribbon is to intelligently employ a diverse
  set of cloud computing instances (heterogeneous instances) to meet the Qo
 S target and maximize cost savings. Ribbon devises a Bayesian Optimization
 -driven strategy that helps users build the optimal set of heterogeneous i
 nstances for their model inference service needs on cloud computing platfo
 rms -- and, Ribbon demonstrates its superiority over existing approaches o
 f inference serving systems using homogeneous instance pools. Ribbon saves
  up to 16% of the inference service cost for different learning models inc
 luding emerging deep learning recommender system models and drug-discovery
  enabling models.\n\nTag: Reproducibility Badge, Resource Management and S
 cheduling\n\nRegistration Category: Tech Program Reg Pass\n\nReproducibili
 ty Badges: Artifact Available, Artifact Functional, Results Reproduced
END:VEVENT
END:VCALENDAR