Gpu Interconnects
GPU Interconnects is a hardware architecture mechanism that enables high-bandwidth, low-latency communication between multiple graphics processing units by specifying the physical and logical pathways for data transfer, distinguishing it from general-purpose interconnects through its optimization for parallel graphics and compute workloads.
69
Publications
3.5K
Citations
275
Authors
101
Institutions
Publications per year
2017–2026
36
Parents
69
Youngeun Kwon, Y. Lee, Minsoo Rhu · 2019 · 216 citations
Ultra-Performance Pascal GPU and NVLink Interconnect
Denis Foley, John M. Danskin · IEEE Micro · 2017 · 213 citations
Cheng Li, Min Tang, Ruofeng Tong et al. · ACM Transactions on Graphics · 2020 · 144 citations
1–5 of 69
275
4
h-index
3
h-index
3
h-index
Pacific Northwest National Laboratory, United States
3 publications · 354 citations
3
h-index
3
h-index
1–5 of 275
101
Nvidia (United States)
Santa Clara, United States
5 h-index
17 publications
447 citations
Georgia Institute of Technology
Atlanta, United States
3 h-index
6 publications
319 citations
Nvidia (United Kingdom)
Reading, United Kingdom
3 h-index
4 publications
491 citations
University of Potsdam
Potsdam, Germany
3 h-index
6 publications
179 citations
The Ohio State University
Columbus, United States
3 h-index
19 publications
1.5K citations
Argonne National Laboratory
Lemont, United States
3 h-index
11 publications
228 citations

Sapienza University of Rome
Rome, Italy
3 h-index
3 publications
68 citations
Istituto Nazionale di Fisica Nucleare, Sezione di Roma I
Rome, Italy
3 h-index
16 publications
242 citations
1–8 of 101
CSRD · 3 publications · 210 citations
3
h-index
2 publications · 225 citations
2
h-index
2 publications · 54 citations
2
h-index
2 publications · 34 citations
2
h-index
2 publications · 33 citations
2
h-index
1–5