I/o Complexity
I/O Complexity is a computational complexity measure that quantifies the number of input/output operations required by an algorithm to solve a problem, distinguishing it from other complexity measures by focusing specifically on data transfer costs between hierarchical memory levels rather than CPU operations.
66
Publications
3K
Citations
156
Authors
84
Institutions
Publications per year
2017–2026
9
Parents
66
FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness
Tri Dao, Daniel Y. Fu, Stefano Ermon et al. · arXiv (Cornell University) · 2022 · 459 citations · Full text
1–5 of 66
156
6
h-index
Gheorghe Asachi Technical University of Iași, Romania
4 publications · 115 citations
4
h-index
3
h-index
3
h-index
3
h-index
1–5 of 156
84
Chinese University of Hong Kong
Hong Kong, Hong Kong
6 h-index
7 publications
236 citations
AT&T (United States)
Bedminster, United States
4 h-index
4 publications
179 citations
University of Illinois Urbana-Champaign
Urbana, United States
4 h-index
6 publications
458 citations

The University of Melbourne
Melbourne, Australia
3 h-index
9 publications
240 citations
Gheorghe Asachi Technical University of Iași
Iasi, Romania
3 h-index
4 publications
79 citations
IBM (United States)
Armonk, United States
2 h-index
4 publications
119 citations

École Normale Supérieure de Lyon
Lyon, France
2 h-index
4 publications
78 citations
Korea Advanced Institute of Science and Technology
Daejeon, South Korea
2 h-index
5 publications
206 citations
1–8 of 84
PVLDB · 3 publications · 121 citations
3
h-index
JACM · 3 publications · 128 citations
3
h-index
2 publications · 255 citations
2
h-index
TODS · 2 publications · 54 citations
2
h-index
Conference · 2 publications · 55 citations
2
h-index
1–5