Towards dense linear algebra for hybrid GPU accelerated manycore systems
2009 · Parallel Computing · 438 citations
https://doi.org/10.1016/j.parco.2009.12.005
S
Stanimire Tomov
Claim or correct this author profile
Claim this profile or suggest corrections to the name, affiliation, bio, photo, or paper titles. Approved changes appear as verified CitedEvidence overlays.
320
Papers
7.2K
Citations
45
h-index
137
i10-index
Stanimire Tomov is an academic researcher from Nvidia (United States). The author has contributed to research in topics: Parallel Computing and Optimization Techniques & Matrix Theory and Algorithms & Distributed and Parallel Computing Systems. The author has an h-index of 45, co-authored 272 publications.
ORCID: 0000-0002-5937-7959Papers by this author
worksHarnessing GPU Tensor Cores for Fast FP16 Arithmetic to Speed up Mixed-Precision Iterative Refinement Solvers
2018 · 201 citations
https://doi.org/10.1109/sc.2018.00050
Using Mixed Precision for Sparse Matrix Computations to Enhance the Performance while Achieving 64-bit Accuracy
2008 · ACM Transactions on Mathematical Software · 99 citations
https://doi.org/10.1145/1377596.1377597
MAGMA templates for scalable linear algebra on emerging architectures
2020 · The International Journal of High Performance Computing Applications · 14 citations
https://doi.org/10.1177/1094342020938421
Optimizing the SVD Bidiagonalization Process for a Batch of Small Matrices
2017 · Procedia Computer Science · 7 citations
https://doi.org/10.1016/j.procs.2017.05.237
Clinical and surgical aspects of vulvar reconstruction with tensor fasciae latae flaps after en bloc radical vulvectomy.
2007 · PubMed · 4 citations
Research topics
topicsChat about Author
Papers
Chat
Click to start Chat