2020 IEEE Visualization Conference (VIS) 2020
DOI: 10.1109/vis47514.2020.00014
|View full text |Cite
|
Sign up to set email alerts
|

GPU Parallel Computation of Morse-Smale Complexes

Abstract: The Morse-Smale complex is a well studied topological structure that represents the gradient flow behavior of a scalar function. It supports multi-scale topological analysis and visualization of large scientific data. Its computation poses significant algorithmic challenges when considering large scale data and increased feature complexity. Several parallel algorithms have been proposed towards the fast computation of the 3D Morse-Smale complex. The non-trivial structure of the saddle-saddle connections are no… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1

Citation Types

0
3
0

Year Published

2023
2023
2024
2024

Publication Types

Select...
5
1

Relationship

1
5

Authors

Journals

citations
Cited by 9 publications
(3 citation statements)
references
References 19 publications
0
3
0
Order By: Relevance
“…Further parallel optimizations were achieved by merging gradient paths, enabling the computation of the gradient assignment and extrema traversals on the GPU [28,29]. Subhash et al [30] then accomplished computing all steps of the MS complex computation on the GPU. Even though some algorithms improved the steepest descent line tracing [17,20] by allowing the traversal to use edges and triangles, still all presented algorithms often produce incorrect connectivity and inaccurate geometry due to the refinement of the underlying discrete domain [31].…”
Section: Related Workmentioning
confidence: 99%
“…Further parallel optimizations were achieved by merging gradient paths, enabling the computation of the gradient assignment and extrema traversals on the GPU [28,29]. Subhash et al [30] then accomplished computing all steps of the MS complex computation on the GPU. Even though some algorithms improved the steepest descent line tracing [17,20] by allowing the traversal to use edges and triangles, still all presented algorithms often produce incorrect connectivity and inaccurate geometry due to the refinement of the underlying discrete domain [31].…”
Section: Related Workmentioning
confidence: 99%
“…Their algorithm and the associated software library, pyms3d [SN17], leveraged GPU parallelism for gradient assignment and extrema traversal and CPU parallelism for saddle-saddle traversal. Recently, Subhash et al [SPN20,SPN22] introduced gmsc, an end-to-end GPU parallel algorithm for 3D Morse-Smale complex computation, which resulted in substantial speedups over the CPU and hybrid approaches attempted thus far. gmsc transforms the saddle-saddle computation into a sequence of matrix operations that are amenable to fast parallel computation on the GPU, leading to significant improvement in runtime.…”
Section: Related Workmentioning
confidence: 99%
“…Recently, Subhash et al. [SPN20, SPN22] introduced g msc , an end‐to‐end GPU parallel algorithm for 3D Morse–Smale complex computation, which resulted in substantial speedups over the CPU and hybrid approaches attempted thus far. g msc transforms the saddle‐saddle computation into a sequence of matrix operations that are amenable to fast parallel computation on the GPU, leading to significant improvement in runtime.…”
Section: Introductionmentioning
confidence: 99%