Exploring a Novel Gathering Method for Finite Element Codes on the Cell/B.E. Architecture
Authors:
- Mohammad JowkarMJMohammad Jowkar
- Raul de la CruzRCRaul de la Cruz
- Jose M. CelaJCJose M. Cela
- 1 November 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 21674329,p. 1-11
Abstract
Indirect addressing is known for being slow on conventional architectures, due to the extra step of gathering data before computations can be done. There have been proposed many methods for optimizing indirect addressing. However, these almost exclusively, merely try to change the order in which data is accessed, so as to better utilize the cache. Furthermore, vector instructions can not be used, since data is not accessed continuously, and therefore valuable processing power can not be exploited. The Cell/B.E. architecture has multiple powerful DMA engines, suitable for gathering scattered data. Unfortunately, at fine data granularity, they have several constraints which make them inefficient. In this paper, a novel solution called DMA list Interlacing (DLI) is explored, which overcomes the DMA constraints and enables the usage of vector instructions, without any extra effort. It is shown that DLI can achieve speedups of several orders of magnitude, compared to conventional processors.Keywords
This publication has 19 references indexed in Scilit:
- Applications of Space-Filling-Curves to Cartesian Methods for CFD2004
- Localizing non-affine array references2003
- Improving Locality for Adaptive Irregular Scientific Codes2001
- A Comparison of Locality Transformations for Irregular Codes2000
- Improving cache performance in dynamic applications through data and computation reorganization at run time1999
- Improving memory hierarchy performance for irregular applications1999
- A Fast and High Quality Multilevel Scheme for Partitioning Irregular GraphsSIAM Journal on Scientific Computing, 1998
- Introduction to the S-adaptivity methodFinite Elements in Analysis and Design, 1997
- Data prefetching and multilevel blocking for linear algebra operations1996
- A Partitioning Strategy for Nonuniform Problems on MultiprocessorsIEEE Transactions on Computers, 1987