Staying on GPU while working on a series of equations

Open discussion for MAGMA library (Matrix Algebra on GPU and Multicore Architectures)
Post Reply
NASA_SimDeveloper
Posts: 8
Joined: Wed Apr 17, 2019 11:50 am

Staying on GPU while working on a series of equations

Post by NASA_SimDeveloper » Wed Apr 17, 2019 11:59 am

I have several equations of motion (EOM) that I want to finish on the GPU before returning to the CPU.

            // Block Matrix Inverse:
            // A = M^-1*RHS
            // A^T = |Arns Af| (separate rigid/nozzle/slosh from flex)
            // RHS^T = |xrns xf|
            // | A   B |^-1 |xrns| = | (A - B*D^-1*C)^-1           -(A - B*D^-1*C)^-1*B*D^-1             | |xrns|
            // | C   D |    | xf |   | -D^-1*C*(A - B*D^-1*C)^-1   D^-1 + D^-1*C*(A - B*D^-1*C)^-1B*D^-1 | | xf |
            // Arns = (A - B*D^-1*C)^-1*(Xrns - B*D^-1*Xf)
            // Af   = D^-1*Xf - D^-1*C*Arns

What documentation do I read for this? Can I finish all of these equations in sequence before returning to the CPU? I am PCIe constrained if I cannot perform these in sequence while staying on the GPU.

Post Reply