Distributing and Load Balancing Sparse Fluid Simulations

dc.contributor.authorShah, Chinmayeeen_US
dc.contributor.authorHyde, Daviden_US
dc.contributor.authorQu, Hangen_US
dc.contributor.authorLevis, Philipen_US
dc.contributor.editorThuerey, Nils and Beeler, Thaboen_US
dc.date.accessioned2018-07-23T10:06:38Z
dc.date.available2018-07-23T10:06:38Z
dc.date.issued2018
dc.description.abstractThis paper describes a general algorithm and a system for load balancing sparse fluid simulations. Automatically distributing sparse fluid simulations efficiently is challenging because the computational load varies across the simulation domain and time. A key challenge with load balancing is that optimal decision making requires knowing the fluid distribution across partitions for future time steps, but computing this state for an arbitrary simulation requires running the simulation itself. The key insight of this paper is that it is possible to predict future load by running a speculative low resolution simulation in parallel. We mathematically formulate the problem of load balancing over multiple time steps and present a polynomial time algorithm to compute an approximate solution to it. Our experimental results show that distributing and speculatively load balancing sparse FLIP simulations over 8 nodes speeds them up by 5.3 to 7.9, and that speculative load balancing generates assignments that perform within 20% of optimal.en_US
dc.description.number8
dc.description.sectionheadersCoupled Fluids
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume37
dc.identifier.doi10.1111/cgf.13510
dc.identifier.issn1467-8659
dc.identifier.pages35-46
dc.identifier.urihttps://doi.org/10.1111/cgf.13510
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf13510
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectComputing methodologies
dc.subjectDistributed computing methodologies
dc.subjectDistributed simulation
dc.subjectComputer graphics
dc.titleDistributing and Load Balancing Sparse Fluid Simulationsen_US
Files
Collections