Memory---Sequoia
Kayvon Fatahalian, W.J. Dally, Pat Hanrahan et al. · 2006
We present Sequoia, a programming language designed to facilitate the development of memory hierarchy aware parallel programs that remain portable across modern machines featuring different memory hierarchy configurations. Sequoia abstractly exposes hierarchical memory in the programming model and provides language mechanisms to describe communication vertically through the machine and to localize computation to particular memory locations within it. We have implemented a complete programming system, including a compiler and runtime systems for Cell processor-based blade systems and distributed memory clusters, and demonstrate efficient performance running Sequoia programs on both of these platforms.
Cited by 452 works. doi:10.1145/1188455.1188543
Authors
- Kayvon Fatahalian
- W.J. Dally
- Pat Hanrahan
- Daniel Reiter Horn
- Timothy J. Knight
- Larkhoon Leem
- Mike Houston
- Ji Young Park
- Mattan Erez
- Manman Ren
- Alex Aiken
References
- Compilers: Principles, Techniques, and Tools
- Brook for GPUs
- Cilk
- OpenMP: an industry standard API for shared-memory programming
- The design and implementation of a first-generation CELL processor
- Automated empirical optimizations of software and the ATLAS project
- Parallel programming in Split-C
- X10
- I/O complexity
- Co-array Fortran for parallel programming