DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Youngsok | - |
dc.contributor.author | JO, JAEEON | - |
dc.contributor.author | JANG, HANHWI | - |
dc.contributor.author | RHU, MINSOO | - |
dc.contributor.author | KIM, HANJUN | - |
dc.contributor.author | Kim, Jangwoo | - |
dc.date.accessioned | 2018-05-11T00:38:38Z | - |
dc.date.available | 2018-05-11T00:38:38Z | - |
dc.date.created | 2017-09-18 | - |
dc.date.issued | 2017-10-18 | - |
dc.identifier.uri | https://oasis.postech.ac.kr/handle/2014.oak/42832 | - |
dc.description.abstract | Graphics Processing Unit (GPU) vendors have been scaling single-GPU architectures to satisfy the ever-increasing user demands for faster graphics processing. However, as it gets extremely difficult to further scale single-GPU architectures, the vendors are aiming to achieve the scaled performance by simultaneously using multiple GPUs connected with newly developed, fast inter-GPU networks (e.g., NVIDIA NVLink, AMD XDMA). With fast inter-GPU networks, it is now promising to employ split frame rendering (SFR) which improves both frame rate and single-frame latency by assigning disjoint regions of a frame to different GPUs. Unfortunately, the scalability of current SFR implementations is seriously limited as they suffer from a large amount of redundant computation among GPUs. This paper proposes GPUpd, a novel multi-GPU architecture for fast and scalable SFR. With small hardware extensions, GPUpd introduces a new graphics pipeline stage called Cooperative Projection & Distribution (C-PD) where all GPUs cooperatively project 3D objects to 2D screen and efficiently redistribute the objects to their corresponding GPUs. C-PD not only eliminates the redundant computation among GPUs, but also incurs minimal inter-GPU network traffic by transferring object IDs instead of mid-pipeline outcomes between GPUs. To further reduce the redistribution overheads, GPUpd minimizes inter-GPU synchronizations by implementing batching and runahead-execution of draw commands. Our detailed cycle-level simulations with 8 real-world game traces show that GPUpd achieves a geomean speedup of 4.98X in single-frame latency with 16 GPUs, whereas the current SFR implementations achieve only 3.07X geomean speedup which saturates on 4 or more GPUs. | - |
dc.publisher | IEEE/ACM | - |
dc.relation.isPartOf | International Symposium on Microarchitecture | - |
dc.relation.isPartOf | Proceedings of the 50th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO) | - |
dc.title | GPUpd: A Fast and Scalable Multi-GPU Architecture Using Cooperative Projection and Distribution | - |
dc.type | Conference | - |
dc.type.rims | CONF | - |
dc.identifier.bibliographicCitation | International Symposium on Microarchitecture | - |
dc.citation.conferenceDate | 2017-10-14 | - |
dc.citation.conferencePlace | US | - |
dc.citation.title | International Symposium on Microarchitecture | - |
dc.contributor.affiliatedAuthor | JO, JAEEON | - |
dc.contributor.affiliatedAuthor | JANG, HANHWI | - |
dc.contributor.affiliatedAuthor | RHU, MINSOO | - |
dc.contributor.affiliatedAuthor | KIM, HANJUN | - |
dc.identifier.scopusid | 2-s2.0-85034065832 | - |
dc.description.journalClass | 1 | - |
dc.description.journalClass | 1 | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
library@postech.ac.kr Tel: 054-279-2548
Copyrights © by 2017 Pohang University of Science ad Technology All right reserved.