GPU Support for Automatic Generation of Finite-Differences Stencil Kernels

TL;DR

This paper introduces an extension to the Devito compiler that automatically generates optimized GPU kernels for finite-difference stencil computations, significantly improving performance for seismic inversion algorithms.

Contribution

It presents a high-level symbolic code generation approach for GPU-accelerated finite-difference kernels, bridging the gap between symbolic programming and high-performance GPU execution.

Findings

Achieves 63% of V100's peak performance on GPU

Achieves 24% of Titan Z's peak performance on GPU

Memory optimization is key to performance improvements

Abstract

The growth of data to be processed in the Oil & Gas industry matches the requirements imposed by evolving algorithms based on stencil computations, such as Full Waveform Inversion and Reverse Time Migration. Graphical processing units (GPUs) are an attractive architectural target for stencil computations because of its high degree of data parallelism. However, the rapid architectural and technological progression makes it difficult for even the most proficient programmers to remain up-to-date with the technological advances at a micro-architectural level. In this work, we present an extension for an open source compiler designed to produce highly optimized finite difference kernels for use in inversion methods named Devito. We embed it with the Oxford Parallel Domain Specific Language (OP-DSL) in order to enable automatic code generation for GPU architectures from a high-level representation. We aim to enable users coding in a symbolic representation level to effortlessly get their implementations leveraged by the processing capacities of GPU architectures. The implemented backend is evaluated on a NVIDIA GTX Titan Z, and on a NVIDIA Tesla V100 in terms of operational intensity through the roof-line model for varying space-order discretization levels of 3D acoustic isotropic wave propagation stencil kernels with and without symbolic optimizations. It achieves approximately 63% of V100's peak performance and 24% of Titan Z's peak performance for stencil kernels over grids with 256 points. Our study reveals that improving memory usage should be the most efficient strategy for leveraging the performance of the implemented solution on the evaluated architectures.