Kernel Optimization
Kernel Optimization is a methodological contribution in GPU computing that systematically enhances the performance of parallel computational kernels by minimizing execution time, resource usage, or energy consumption through architecture-aware refinements in thread organization, memory access patterns, and instruction-level parallelism.
742
Publications
43.4K
Citations
2.3K
Authors
629
Institutions
Publications per year
2017–2026
259
742
cuDNN: Efficient Primitives for Deep Learning
Sharan Chetlur, Cliff Woolley, Philippe Vandermersch et al. · arXiv (Cornell University) · 2014 · 1K citations · Full text
Jonathan Bachrach, Huy T. Vo, Brian Richards et al. · 2012 · 905 citations
Virginia Klema, Jack Dongarra, James R. Bunch et al. · Mathematics of Computation · 1980 · 648 citations
Debunking the 100X GPU vs. CPU myth
Victor W. Lee, Changkyu Kim, Jatin Chhugani et al. · 2010 · 626 citations
1–5 of 742
2.3K
18
h-index
14
h-index
11
h-index
10
h-index
9
h-index
1–5 of 2.3K
629
University of Illinois Urbana-Champaign
Urbana, United States
19 h-index
53 publications
2.9K citations
University of Tennessee at Knoxville
Knoxville, United States
16 h-index
86 publications
2.6K citations

Chinese Academy of Sciences
Beijing, China
16 h-index
72 publications
2.4K citations
The University of Texas at Austin
Austin, United States
15 h-index
33 publications
1.9K citations
Georgia Institute of Technology
Atlanta, United States
15 h-index
45 publications
1.4K citations

Oak Ridge National Laboratory
Oak Ridge, United States
14 h-index
45 publications
1.1K citations
Tsinghua University
Beijing, China
14 h-index
70 publications
2.5K citations
Intel (United States)
Santa Clara, United States
13 h-index
51 publications
13K citations
1–8 of 629
TPDS · 20 publications · 605 citations
16
h-index
Repository · 21 publications · 2.9K citations
16
h-index
14 publications · 259 citations
13
h-index
13 publications · 400 citations
12
h-index
12 publications · 648 citations
10
h-index
1–5