Automatic Code Generation and Optimization of Large-scale Stencil Computation on Many-core Processors

2021 ◽  
Author(s):  
Mingzhen Li ◽  
Yi Liu ◽  
Hailong Yang ◽  
Yongmin Hu ◽  
Qingxiao Sun ◽  
...  
Geophysics ◽  
2019 ◽  
Vol 84 (3) ◽  
pp. F57-F71 ◽  
Author(s):  
Philipp A. Witte ◽  
Mathias Louboutin ◽  
Navjot Kukreja ◽  
Fabio Luporini ◽  
Michael Lange ◽  
...  

Writing software packages for seismic inversion is a very challenging task because problems such as full-waveform inversion or least-squares imaging are algorithmically and computationally demanding due to the large number of unknown parameters and the fact that waves are propagated over many wavelengths. Therefore, software frameworks need to combine versatility and performance to provide geophysicists with the means and flexibility to implement complex algorithms that scale to exceedingly large 3D problems. Following these principles, we have developed the Julia Devito Inversion framework, an open-source software package in Julia for large-scale seismic modeling and inversion based on Devito, a domain-specific language compiler for automatic code generation. The framework consists of matrix-free linear operators for implementing seismic inversion algorithms that closely resemble the mathematical notation, a flexible resilient parallelization, and an interface to Devito for generating optimized stencil code to solve the underlying wave equations. In comparison with many manually optimized industry codes written in low-level languages, our software is built on the idea of independent layers of abstractions and user interfaces with symbolic operators. Through a series of numerical examples, we determined that this allows users to implement a series of increasingly complex algorithms for waveform inversion and imaging as simple Julia scripts that scale to large-scale 3D problems. This illustrates that software based on the paradigms of abstract user interfaces and automatic code generation and makes it possible to manage the complexity of the algorithms and performance optimizations, thus providing a high-performance research and production framework.


2011 ◽  
Vol 383-390 ◽  
pp. 308-314
Author(s):  
Lin Li ◽  
Zhi Ming Peng ◽  
Bi Cong Zhang ◽  
Zhang Tie

This paper presents a Rapid Control Prototyping (RCP) development platform based on Matlab/Simulink, Real-Time Workshop and Embedded Target for C2000 and DSP development board. It also designs TMS320F2812 DSP-based motion controller under the proposed RCP. The controller using saturated integral PID algorithm produces PWM signal to control DC motor. Experimental results show that the designed controller can control motor accurately. Engineers can complete all design tasks such as modeling, automatic code generation, and download, running and parameters adjustment on this RCP platform when developing DSP application system. Thus the proposed RCP can shorten the DSP development cycle and improve the portability and modularity of program.


2006 ◽  
Vol 104 (2) ◽  
pp. 211-228 ◽  
Author(s):  
Alexander A. Auer ◽  
Gerald Baumgartner ◽  
David E. Bernholdt ◽  
Alina Bibireata ◽  
Venkatesh Choppella ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document