Skip to main content
Computational Science

Return to Question

deleted 97 characters in body
Source Link
mirams
mirams
  • 468
  • 3
  • 17

I would like to farm out solving systems of ODEs onto GPUs, in a 'trivially parallelisable' setting. For example, doing a sensitivity analysis with 512 different parameter sets, or solving the (independent) ODEs associated with something like nodes of a finite element mesh.

Ideally I want to do ODE solving with a smart adaptive timestep solver like CVODE, rather than a fixed timestep like Forward Euler, but running it on an NVIDIA GPU instead of CPU.

Has anyone done this? Are there libraries for it?

I would like to farm out solving systems of ODEs onto GPUs, in a 'trivially parallelisable' setting. For example, doing a sensitivity analysis with 512 different parameter sets, or solving the (independent) ODEs associated with something like nodes of a finite element mesh.

Ideally I want to do ODE solving with a smart adaptive timestep solver like CVODE, rather than a fixed timestep like Forward Euler, but running it on an NVIDIA GPU instead of CPU.

Has anyone done this? Are there libraries for it?

I would like to farm out solving systems of ODEs onto GPUs, in a 'trivially parallelisable' setting. For example, doing a sensitivity analysis with 512 different parameter sets.

Ideally I want to do ODE solving with a smart adaptive timestep solver like CVODE, rather than a fixed timestep like Forward Euler, but running it on an NVIDIA GPU instead of CPU.

Has anyone done this? Are there libraries for it?

Notice removed Canonical answer required by CommunityBot
Bounty Ended with no winning answer by CommunityBot
clarify different ODE solver options
Source Link
mirams
mirams
  • 468
  • 3
  • 17

I would like to farm out solving systems of ODEs onto GPUs, in a 'trivially parallelisable' setting. For example, doing a sensitivity analysis with 512 different parameter sets, or solving the (independent) ODEs associated with something like nodes of a finite element mesh.

Ideally I want to do ODE solving with a smart adaptive timestep solver like CVODE, rather than a fixed timestep like Forward Euler or something, but running it on an NVIDIA GPU instead of CPU.

Has anyone done this? Are there libraries for it?

I would like to farm out solving systems of ODEs onto GPUs, in a 'trivially parallelisable' setting. For example, doing a sensitivity analysis with 512 different parameter sets, or solving the (independent) ODEs associated with something like nodes of a finite element mesh.

Ideally I want to do ODE solving with a smart adaptive solver like CVODE, rather than Forward Euler or something, but running it on an NVIDIA GPU instead of CPU.

Has anyone done this? Are there libraries for it?

I would like to farm out solving systems of ODEs onto GPUs, in a 'trivially parallelisable' setting. For example, doing a sensitivity analysis with 512 different parameter sets, or solving the (independent) ODEs associated with something like nodes of a finite element mesh.

Ideally I want to do ODE solving with a smart adaptive timestep solver like CVODE, rather than a fixed timestep like Forward Euler, but running it on an NVIDIA GPU instead of CPU.

Has anyone done this? Are there libraries for it?

Notice added Canonical answer required by mirams
Bounty Started worth 50 reputation by mirams
Tweeted twitter.com/#!/StackSciComp/status/422252565515214848
Source Link
mirams
mirams
  • 468
  • 3
  • 17

Options for solving ODE systems on GPUs?

I would like to farm out solving systems of ODEs onto GPUs, in a 'trivially parallelisable' setting. For example, doing a sensitivity analysis with 512 different parameter sets, or solving the (independent) ODEs associated with something like nodes of a finite element mesh.

Ideally I want to do ODE solving with a smart adaptive solver like CVODE, rather than Forward Euler or something, but running it on an NVIDIA GPU instead of CPU.

Has anyone done this? Are there libraries for it?