E²MC: Entropy Encoding Based Memory Compression for GPUs

dc.contributor.authorLal, Sohan
dc.contributor.authorLucas, Jan
dc.contributor.authorJuurlink, Ben
dc.date.accessioned2018-06-05T13:09:14Z
dc.date.available2018-06-05T13:09:14Z
dc.date.issued2017
dc.description.abstractModern Graphics Processing Units (GPUs) provide much higher off-chip memory bandwidth than CPUs, but many GPU applications are still limited by memory bandwidth. Unfortunately, off-chip memory bandwidth is growing slower than the number of cores and has become a performance bottleneck. Thus, optimizations of effective memory bandwidth play a significant role for scaling the performance of GPUs. Memory compression is a promising approach for improving memory bandwidth which can translate into higher performance and energy efficiency. However, compression is not free and its challenges need to be addressed, otherwise the benefits of compression may be offset by its overhead. We propose an entropy encoding based memory compression (E2MC) technique for GPUs, which is based on the well-known Huffman encoding. We study the feasibility of entropy encoding for GPUs and show that it achieves higher compression ratios than state-of-the-art GPU compression techniques. Furthermore, we address the key challenges of probability estimation, choosing an appropriate symbol length for encoding, and decompression with low latency. The average compression ratio of E2MC is 53% higher than the state of the art. This translates into an average speedup of 20% compared to no compression and 8% higher compared to the state of the art. Energy consumption and energy-delayproduct are reduced by 13% and 27%, respectively. Moreover, the compression ratio achieved by E2MC is close to the optimal compression ratio given by Shannon's source coding theorem.en
dc.description.sponsorshipEC/H2020/688759/EU/Low-Power Parallel Computing on GPUs 2/LPGPU2en
dc.identifier.eissn1530-2075
dc.identifier.isbn978-1-5386-3914-6
dc.identifier.urihttps://depositonce.tu-berlin.de//handle/11303/7914
dc.identifier.urihttp://dx.doi.org/10.14279/depositonce-7075
dc.language.isoenen
dc.relation.ispartof10.14279/depositonce-9156
dc.rights.urihttp://rightsstatements.org/vocab/InC/1.0/en
dc.subject.ddc004 Datenverarbeitung; Informatikde
dc.subject.othermemory compressionen
dc.subject.otherGPUsen
dc.subject.otherHuffman compressionen
dc.subject.othermemory bandwidthen
dc.subject.otherenergy efficiencyen
dc.titleE²MC: Entropy Encoding Based Memory Compression for GPUsen
dc.typeConference Objecten
dc.type.versionacceptedVersionen
dcterms.bibliographicCitation.doi10.1109/IPDPS.2017.101en
dcterms.bibliographicCitation.originalpublishernameIEEEen
dcterms.bibliographicCitation.originalpublisherplaceNew Yorken
dcterms.bibliographicCitation.pageend1128en
dcterms.bibliographicCitation.pagestart1119en
dcterms.bibliographicCitation.proceedingstitle2017 IEEE International Parallel and Distributed Processing Symposium (IPDPS)en
tub.accessrights.dnbfreeen
tub.affiliationFak. 4 Elektrotechnik und Informatik>Inst. Technische Informatik und Mikroelektronik>FG Architektur eingebetteter Systemede
tub.affiliation.facultyFak. 4 Elektrotechnik und Informatikde
tub.affiliation.groupFG Architektur eingebetteter Systemede
tub.affiliation.instituteInst. Technische Informatik und Mikroelektronikde
tub.publisher.universityorinstitutionTechnische Universität Berlinen
Files
Original bundle
Now showing 1 - 1 of 1
Loading…
Thumbnail Image
Name:
lal_lucas_juurlink_2017.pdf
Size:
820.78 KB
Format:
Adobe Portable Document Format
Description:
Collections