مؤتمر
Temporal blocking of finite-difference stencil operators with sparse 'off-the-grid' sources
| العنوان: | Temporal blocking of finite-difference stencil operators with sparse 'off-the-grid' sources |
|---|---|
| المؤلفون: | Bisbas, G, Luporini, F, Louboutin, M, Nelson, R, Gorman, GJ, Kelly, PHJ |
| المساهمون: | Engineering & Physical Science Research Council (EPSRC) |
| المصدر: | 35th IEEE International Parallel and Distributed Processing Symposium (IPDPS) ; 506 ; 497 |
| بيانات النشر: | IEEE COMPUTER SOC |
| سنة النشر: | 2021 |
| المجموعة: | Imperial College London: Spiral |
| مصطلحات موضوعية: | Science & Technology, Technology, Computer Science, Hardware & Architecture, Software Engineering, Theory & Methods, temporal blocking, stencil computations, code generation, partial differential equations, seismic imaging, domain-specific languages, wave-propagation, REVERSE-TIME MIGRATION, PARALLEL EXECUTION, WAVE, LOCALITY, ALGORITHMS, EQUATIONS, SOLVERS, CODE, cs.DC |
| جغرافية الموضوع: | Portland, OR, USA |
| الوصف: | Stencil kernels dominate a range of scientific applications, including seismic and medical imaging, image processing, and neural networks. Temporal blocking is a performance optimization that aims to reduce the required memory bandwidth of stencil computations by re-using data from the cache for multiple time steps. It has already been shown to be beneficial for this class of algorithms. However, applying temporal blocking to practical applications' stencils remains challenging. These computations often consist of sparsely located operators not aligned with the computational grid (“off-the-grid”). Our work is motivated by modelling problems in which source injections result in wavefields that must then be measured at receivers by interpolation from the grided wavefield. The resulting data dependencies make the adoption of temporal blocking much more challenging. We propose a methodology to inspect these data dependencies and reorder the computation, leading to performance gains in stencil codes where temporal blocking has not been applicable. We implement this novel scheme in the Devito domain-specific compiler toolchain. Devito implements a domain-specific language embedded in Python to generate optimized partial differential equation solvers using the finite-difference method from high-level symbolic problem definitions. We evaluate our scheme using isotropic acoustic, anisotropic acoustic, and isotropic elastic wave propagators of industrial significance. After auto-tuning, performance evaluation shows that this enables substantial performance improvement through temporal blocking over highly-optimized vectorized spatially-blocked code of up to 1.6x. |
| نوع الوثيقة: | conference object |
| اللغة: | unknown |
| تدمد: | 1530-2075 |
| العلاقة: | 2021 IEEE 35TH INTERNATIONAL PARALLEL AND DISTRIBUTED PROCESSING SYMPOSIUM (IPDPS); http://hdl.handle.net/10044/1/92275Test; EP/R029423/1; EP/V001493/1 |
| DOI: | 10.1109/IPDPS49936.2021.00058 |
| الإتاحة: | https://doi.org/10.1109/IPDPS49936.2021.00058Test http://hdl.handle.net/10044/1/92275Test |
| حقوق: | © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. |
| رقم الانضمام: | edsbas.82265AAA |
| قاعدة البيانات: | BASE |
| تدمد: | 15302075 |
|---|---|
| DOI: | 10.1109/IPDPS49936.2021.00058 |