Sorting with Asymmetric Read and Write Costs
arXiv:1603.03505 · doi:10.1145/2755573.2755604
Abstract
Emerging memory technologies have a significant gap between the cost, both in time and in energy, of writing to memory versus reading from memory. In this paper we present models and algorithms that account for this difference, with a focus on write-efficient sorting algorithms. First, we consider the PRAM model with asymmetric write cost, and show that sorting can be performed in writes, reads, and logarithmic depth (parallel time). Next, we consider a variant of the External Memory (EM) model that charges for writing a block of size to the secondary memory, and present variants of three EM sorting algorithms (multi-way mergesort, sample sort, and heapsort using buffer trees) that asymptotically reduce the number of writes over the original algorithms, and perform roughly block reads for every block write. Finally, we define a variant of the Ideal-Cache model with asymmetric write costs, and present write-efficient, cache-oblivious parallel algorithms for sorting, FFTs, and matrix multiplication. Adapting prior bounds for work-stealing and parallel-depth-first schedulers to the asymmetric setting, these yield parallel cache complexity bounds for machines with private caches or with a shared cache, respectively.
References in corpus (1)
Cited by in corpus (8)
- Parallel Write-Efficient Algorithms and Data Structures for Computational Geometry
- The Parallel Persistent Memory Model
- Efficient Algorithms with Asymmetric Read and Write Costs
- WiscSort: External Sorting For Byte-Addressable Storage
- Improved Parallel Cache-Oblivious Algorithms for Dynamic Programming and Linear Algebra
- Lessons learned from the early performance evaluation of Intel Optane DC Persistent Memory in DBMS
- Sage: Parallel Semi-Asymmetric Graph Algorithms for NVRAMs
- Implicit Decomposition for Write-Efficient Connectivity Algorithms