Persistent Kernels for Iterative Memory-bound GPU Applications

Iterative memory-bound solvers commonly occur in HPC codes. Typical GPU implementations have a loop on the host side that invokes the GPU kernel as much as time/algorithm steps there are. The termination of each kernel implicitly acts as the barrier required after advancing the solution every time step. We propose a scheme for running memory-bound iterative GPU kernels: PERsistent KernelS (PERKS). In this scheme the time loop is moved inside a persistent kernel, and device-wide barriers are used for synchronization. We then reduce the traffic to device memory by caching a subset of the output in each time step in registers and shared memory to be used as input for the following time step. PERKS can be generalized to any iterative solver: they are largely independent of the solver's implementation. We explain the design principle of PERKS and demonstrate the effectiveness of PERKS for a wide range of iterative 2D/3D stencil benchmarks (geometric mean speedup of $2.29$x in small domains and $1.53$x in large domains), and a Krylov subspace solver (geometric mean speedup of $4.67$x in smaller SpMV datasets from SuiteSparse and $1.39$x in larger SpMV datasets, for conjugate gradient).