Compiler Optimizations for Industrial Unstructured Mesh CFD Applications on GPUs
Graphical Processing Units (GPUs) have shown acceleration factors over multicores for structured mesh-based Computational Fluid Dynamics (CFD). However, the value remains unclear for dynamic and irregular applications. Our motivating example is HYDRA, an unstructured mesh application used in production at Rolls-Royce for the simulation of turbomachinery components of jet engines. We describe three techniques for GPU optimization of unstructured mesh applications: a technique able to split a highly complex loop into simpler loops, a kernel specific alternative code synthesis, and configuration parameter tuning. Using these optimizations systematically on HYDRA improves the GPU performance relative to the multicore CPU. We show how these optimizations can be automated in a compiler, through user annotations. Performance analysis of a large number of complex loops enables us to study the relationship between optimizations and resource requirements of loops, in terms of registers and shared memory, which directly affect the loop performance.
KeywordsComputational Fluid Dynamics Unstructured Meshes Graphical Processing Units Compilers
Unable to display preview. Download preview PDF.
- 5.Strout, M.M., Carter, L., Ferrante, J.: Compile-time composition of run-time data and iteration reorderings. In: Procs. of the PLDI 2003 (June 2003)Google Scholar
- 6.DeVito, Z., Joubert, N., Palacios, F., Oakley, S., Medina, M., Barrientos, M., Elsen, E., Ham, F., Aiken, A., Duraisamy, K., Darve, E., Alonso, J., Hanrahan, P.: Liszt: a domain specific language for building portable mesh-based PDE solvers. In: Procs. of SC, pp. 9:1–9:12. ACM, New York (2011)Google Scholar
- 7.Giles, M.B.: OP2 User’s Manual (April 2012), http://people.maths.ox.ac.uk/gilesm/op2/user.pdf