Data distribution support on distributed shared memory multiprocessors
Rohit Chandra, Ding-Kai Chen, Robert Cox et al. · Proceedings of the ACM SIGPLAN Conference on Programming Language Design and Implementation · 1997
Cache-coherent multiprocessors with distributed shared memory are becoming increasingly popular for parallel computing. However, obtaining high performance on these machines mquires that an application execute with good data locality. In addition to making efiective use of caches, it is often necessary to distribute data structures across the local memories of the processing nodes, thereby reducing the latency of cache misses.We have designed a set of abstractions for performing data distribution in the context of explicitly parallel programs and implemented them within the SGI MIPSpro compiler system. Our system incorporates many unique features to enhance both programmability and performance. We address the former by providing a very simple programmming model with extensive support for error detection. Regarding performance, we carefully design the user abstractions with the underlying compiler optimizations in mind, we incorporate several optimization techniques to generate efficient code for accessing distributed data, and we provide a tight integration of these techniques with other optimizations within the compiler Our initial experience suggests that the directives are easy to use and can yield substantial performance gains, in some cases by as much as a factor of 3 over the same codes without distribution.
Cited by 63 works. doi:10.1145/258915.258945
Authors
References
- The High Performance Fortran Handbook
- The SGI Origin
- The Design and Evolution of C
- Performance analysis using the MIPS R10000 performance counters
- Operating system support for improving data locality on CC-NUMA compute servers
- Global optimizations for parallelism and locality on scalable parallel machines
- Programming in Vienna Fortran
- High performance Fortran
- Demonstration of automatic data partitioning techniques for parallelizing compilers on multicomputers
- Data and computation transformations for multiprocessors