Abstract

It's important to hit a space-time balance for a real-world algorithm to achieve high performance on modern shared-memory multi-core or many-core systems. However, a large class of dynamic programs with more than $O(1)$ dependency achieve optimality either in space or time, but not both. In the literature, the problem is known as the fundamental space-time tradeoff. By exploiting properly on the runtime system, we show that our STAR (Space-Time Adaptive and Reductive) technique can help these dynamic programs to achieve sublinear parallel time bounds while still maintaining work-, space-, and cache-optimality in a processor- and cache-oblivious fashion.
- D. Dinh, H. V. Simhadri, and Y. Tang. Extending the nested parallel model to the nested dataflow model with provably efficient schedulers. In SPAA'16, Pacific Grove, CA, USA, 11--13 2016. Google Scholar
Digital Library
- Z. Galil and K. Park. Parallel algorithms for dynamic programming recurrences with more than O(1) dependency. Journal of Parallel and Distributed Computing, 21:213--222, 1994. Google Scholar
Digital Library
- Y. Tang, R. You, H. Kan, J. J. Tithi, P. Ganapathi, and R. A. Chowdhury. Cache-oblivious wavefront: Improving parallelism of recursive dynamic programming algorithms without losing cache-efficiency. In PPoPP'15, San Francisco, CA, USA, Feb.7-11 2015.Google Scholar
Digital Library
Index Terms
POSTER: STAR (Space-Time Adaptive and Reductive) Algorithms for Real-World Space-Time Optimality
Recommendations
POSTER: STAR (Space-Time Adaptive and Reductive) Algorithms for Real-World Space-Time Optimality
PPoPP '17: Proceedings of the 22nd ACM SIGPLAN Symposium on Principles and Practice of Parallel ProgrammingIt's important to hit a space-time balance for a real-world algorithm to achieve high performance on modern shared-memory multi-core or many-core systems. However, a large class of dynamic programs with more than $O(1)$ dependency achieve optimality ...
Brief Announcement: STAR (Space-Time Adaptive and Reductive) Algorithms for Dynamic Programming Recurrences with more than O(1) Dependency
SPAA '17: Proceedings of the 29th ACM Symposium on Parallelism in Algorithms and ArchitecturesIt's important to hit a space-time balance for a real-world algorithm to achieve high performance on modern shared-memory multi-core and many-core systems. However, a large class of dynamic programs with more than O(1) dependency achieved optimality ...
The pochoir stencil compiler
SPAA '11: Proceedings of the twenty-third annual ACM symposium on Parallelism in algorithms and architecturesA stencil computation repeatedly updates each point of a d-dimensional grid as a function of itself and its near neighbors. Parallel cache-efficient stencil algorithms based on "trapezoidal decompositions" are known, but most programmers find them ...







Comments