Compilation and Runtime-Optimizations for Software Distributed Shared Memory
作者： Kai Zhang , John Mellor-Crummey , Robert J. Fowler
关键词:
摘要: We present two novel optimizations for compiling High Performance Fortran (HPF) to page-based software distributed shared memory systems (SDSM). One technique, compiler-managed restricted consistency, uses compiler-derived knowledge delay the application of consistency operations data that is provably not in current synchronization interval, thus reducing false sharing. The other buffers, when combined with previous optimization, eliminates fragmentation. Together, techniques permit compiler-generated code efficiently apply multi-dimensional computation partitioning and wavefront parallelism execute on SDSM systems.
springer.com
core.ac.uk
sci-hub.st 参考文章(24)
Hwansoo Han, Chau-Wen Tseng, Pete Keleher, Eliminating Barrier Synchronization for Compiler-Parallelized Codes on Software DSMs languages and compilers for parallel computing. ,vol. 26, pp. 591- 612 ,(1998) , 10.1023/A:1018724631720
Eric Jul, Povl T. Koch, Robert J. Fowler, Message-driven relaxed consistency in a software distributed shared memory operating systems design and implementation. pp. 7- ,(1994) , 10.5555/1267638.1267645
Vikram Adve, John Mellor-Crummey, Using integer sets for data-parallel program analysis and optimization programming language design and implementation. ,vol. 33, pp. 186- 198 ,(1998) , 10.1145/277650.277721
Honghui Lu, Alan L. Cox, Sandhya Dwarkadas, Ramakrishnan Rajamony, Willy Zwaenepoel, Compiler and software distributed shared memory support for irregular applications acm sigplan symposium on principles and practice of parallel programming. ,vol. 32, pp. 48- 56 ,(1997) , 10.1145/263764.263772
Satish Chandra, James R. Larus, Optimizing communication in HPF programs on fine-grain distributed shared memory acm sigplan symposium on principles and practice of parallel programming. ,vol. 32, pp. 100- 111 ,(1997) , 10.1145/263764.263780
Ravi Mirchandaney, Seema Hiranandani, Ajay Sethi, Improving the performance of DSM systems via compiler involvement conference on high performance computing (supercomputing). pp. 763- 772 ,(1994) , 10.5555/602770.602894
Ioannis Schoinas, Babak Falsafi, Alvin R. Lebeck, Steven K. Reinhardt, James R. Larus, David A. Wood, Fine-grain access control for distributed shared memory architectural support for programming languages and operating systems. ,vol. 29, pp. 297- 306 ,(1994) , 10.1145/195473.195575
P. Keleher, A.L. Cox, S. Dwarkadas, W. Zwaenepoel, An evaluation of software-based release consistent protocols Journal of Parallel and Distributed Computing. ,vol. 29, pp. 126- 141 ,(1995) , 10.1006/JPDC.1995.1113
S.V. Adve, A.L. Cox, S. Dwarkadas, R. Rajamony, W. Zwaenepoel, A comparison of entry consistency and lazy release consistency implementations high-performance computer architecture. pp. 26- 37 ,(1996) , 10.1109/HPCA.1996.501171
Vikram Adve, Guohua Jin, John Mellor-Crummey, Qing Yi, High Performance Fortran Compilation Techniques for Parallelizing Scientific Codes conference on high performance computing (supercomputing). pp. 1- 23 ,(1998) , 10.5555/509058.509069