A GPU Parallel Algorithm for Computing Morse-Smale Complexes

Subhash, Varshini; Pandey, Karran; Natarajan, Vijay

doi:10.1109/tvcg.2022.3174769

Cited by 3 publications

(4 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast, tachyon employs gradient path tracing from each saddle to compute the arcs. The gradient field and saddle‐extrema arc computation in g msc [SPN22] and pyms3d are identical. The only difference between the two implementations is that g msc uses CUDA whereas pyms3d uses OpenCL.…”

Section: Resultsmentioning

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%

See 2 more Smart Citations

tachyon: Efficient Shared Memory Parallel Computation of Extremum Graphs

Ande

Subhash

Natarajan

2023

Computer Graphics Forum

Self Cite

View full text Add to dashboard Cite

The extremum graph is a succinct representation of the Morse decomposition of a scalar field. It has increasingly become a useful data structure that supports topological feature‐directed visualization of 2D/3D scalar fields, and enables dimensionality reduction together with exploratory analysis of high‐dimensional scalar fields. Current methods that employ the extremum graph compute it either using a simple sequential algorithm for computing the Morse decomposition or by computing the more detailed Morse–Smale complex. Both approaches are typically limited to two and three‐dimensional scalar fields. We describe a GPU–CPU hybrid parallel algorithm for computing the extremum graph of scalar fields in all dimensions. The proposed shared memory algorithm utilizes both fine‐grained parallelism and task parallelism to achieve efficiency. An open source software library, tachyon, that implements the algorithm exhibits superior performance and good scaling behaviour.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

tachyon: Efficient Shared Memory Parallel Computation of Extremum Graphs

Ande

Subhash

Natarajan

2023

Computer Graphics Forum

Self Cite

View full text Add to dashboard Cite

show abstract

“…In contrast, TACHYON employs gradient path tracing from each saddle to compute the arcs. The gradient field and saddle-extrema arc computation in gMSC [SPN22] and pyms3d are identical. The only difference between the two implementations is that gMSC uses CUDA whereas pyms3d uses OpenCL.…”

Section: Performance Comparisonsmentioning

confidence: 99%

TACHYON: Efficient Shared Memory Parallel Computation of Extremum Graphs

Ande,

Subhash,

Natarajan

2023

Preprint

View full text Add to dashboard Cite

The extremum graph is a succinct representation of the Morse decomposition of a scalar field. It has increasingly become a useful data structure that supports topological feature directed visualization of 2D / 3D scalar fields, and enables dimensionality reduction together with exploratory analysis of high dimensional scalar fields. Current methods that employ the extremum graph compute it either using a simple sequential algorithm for computing the Morse decomposition or by computing the more detailed Morse-Smale complex. Both approaches are typically limited to two and three dimensional scalar fields. We describe a GPU-CPU hybrid parallel algorithm for computing the extremum graph of scalar fields in all dimensions. The proposed shared memory algorithm utilizes both fine grained parallelism and task parallelism to achieve efficiency. An open source software library, TACHYON, that implements the algorithm exhibits superior performance and good scaling behavior. CCS Concepts• Human-centered computing → Visualization techniques; • Computing methodologies → Parallel algorithms;

show abstract

Computational Experiments in Computer Science Research: A Literature Survey

Landeta-López,

Guevara-Vega

2024

IEEE Access

View full text Add to dashboard Cite

A GPU Parallel Algorithm for Computing Morse-Smale Complexes

Cited by 3 publications

References 30 publications

tachyon: Efficient Shared Memory Parallel Computation of Extremum Graphs

tachyon: Efficient Shared Memory Parallel Computation of Extremum Graphs

TACHYON: Efficient Shared Memory Parallel Computation of Extremum Graphs

Computational Experiments in Computer Science Research: A Literature Survey

Contact Info

Product

Resources

About