GPU support

From v1.12.0, PyLops supports computations on GPUs powered by cupy and cusignal.

Apart from a few exceptions, all operators and solvers in PyLops can seamlessly work with numpy arrays on CPU as well as with cupy arrays on GPU. Users do simply need to consistently create operators and provide data vectors to the solvers - e.g., when using pylops.MatrixMult the input matrix must be a cupy array if the data provided to a solver is a cupy array.

pylops.LinearOperator methods that are currently not available for GPU computations are:

• eigs, cond, and tosparse, and estimate_spectral_norm

Operators that are currently not available for GPU computations are:

• pylops.Spread
• pylops.signalprocessing.Radon2D
• pylops.signalprocessing.Radon3D
• pylops.signalprocessing.DWT
• pylops.signalprocessing.DWT2D
• pylops.signalprocessing.Seislet
• pylops.waveeqprocessing.Demigration
• pylops.signalprocessing.LSM

Solvers that are currently not available for GPU computations are:

• pylops.optimization.sparsity.SPGL1