Show simple item record

dc.contributor.authorGeorgiev, Pen
dc.contributor.authorLaney, NDen
dc.contributor.authorMascolo, Ceciliaen
dc.contributor.authorChu, Den
dc.date.accessioned2017-09-18T15:27:31Z
dc.date.available2017-09-18T15:27:31Z
dc.date.issued2017-06-16en
dc.identifier.urihttps://www.repository.cam.ac.uk/handle/1810/267271
dc.description.abstractGPUs have recently enjoyed increased popularity as general purpose software accelerators in multiple application domains including computer vision and natural language processing. However, there has been little exploration into the performance and energy trade-offs mobile GPUs can deliver for the increasingly popular workload of deep-inference audio sensing tasks, such as, spoken keyword spotting in energy-constrained smartphones and wearables. In this paper, we study these trade-offs and introduce an optimization engine that leverages a series of structural and memory access optimization techniques that allow audio algorithm performance to be automatically tuned as a function of GPU device specifications and model semantics. We find that parameter optimized audio routines obtain inferences an order of magnitude faster than sequential CPU implementations, and up to 6.5x times faster than cloud offloading with good connectivity, while critically consuming 3-4x less energy than the CPU. Under our optimized GPU, conventional wisdom about how to use the cloud and low power chips is broken. Unless the network has a throughput of at least 20Mbps (and a RTT of 25 ms or less), with only about 10 to 20 seconds of buffering audio data for batched execution, the optimized GPU audio sensing apps begin to consume less energy than cloud offloading. Under such conditions we find the optimized GPU can provide energy benefits comparable to low-power reference DSP implementations with some preliminary level of optimization; in addition to the GPU always winning with lower latency.
dc.description.sponsorshipThis work was supported by Microsoft Research through its PhD Scholarship Program.
dc.publisherAssociation for Computing Machinery
dc.titleAccelerating Mobile Audio Sensing Algorithms through On-Chip GPU Offloadingen
dc.typeConference Object
prism.endingPage318
prism.publicationDate2017en
prism.publicationNameMobiSys 2017 - Proceedings of the 15th Annual International Conference on Mobile Systems, Applications, and Servicesen
prism.startingPage306
dc.identifier.doi10.17863/CAM.13274
dcterms.dateAccepted2017-02-22en
rioxxterms.versionofrecord10.1145/3081333.3081358en
rioxxterms.versionAM*
rioxxterms.licenseref.urihttp://www.rioxx.net/licenses/all-rights-reserveden
rioxxterms.licenseref.startdate2017-06-16en
dc.contributor.orcidMascolo, Cecilia [0000-0001-9614-4380]
rioxxterms.typeConference Paper/Proceeding/Abstracten
pubs.conference-nameMobiSys '17 - 15th Annual International Conference on Mobile Systems, Applications, and Servicesen
pubs.conference-start-date2017-06-19en


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record