External Matrix Operations for the STXXL
نویسندگان
چکیده
This thesis discusses the matrix container template I implemented as part of the STXXL library for very large data sets. Because it is designed for matrices too big to be held in internal memory, algorithms and data structures are chosen to be efficient for external memory operation. Transposition, addition, and scalar multiplication are easy; therefore their description is kept brief. Matrix multiplication is algorithmically interesting; several approaches and algorithms exist for matrix multiplication in general as well as for external matrix multiplication in effort to make it more efficient. For that reason, extensive discussion including theoretical analysis and practical tests focus on matrix multiplication.
منابع مشابه
Roman Dementiev Algorithm Engineering for Large Data Sets
In recent years, the development of theoretically I/O-efficient algorithms and data structures has received considerable attention. However, much less has been done to evaluate their performance, in particular with parallel disks or when running on large inputs with sizes that really require external memory. This thesis presents the software library Stxxl that enables practice-oriented experime...
متن کاملExternal Memory based Distributed Generation of Massive Scale Social Networks on Small Clusters
Small distributed systems are limited by their main memory to generate massively large graphs. Trivial extension to current graph generators to utilize external memory leads to large amount of random I/O hence do not scale with size. In this work we offer a technique to generate massive scale graphs on small cluster of compute nodes with limited main memory. We develop several distributed and e...
متن کاملSTXXL: standard template library for XXL data sets
We present the software library STXXL that is an implementation of the C++ standard template library STL for processing huge data sets that can fit only on hard disks. It supports parallel disks, overlapping between disk I/O and computation and it is the first I/O-efficient algorithm library that supports the pipelining technique that can save more than half of the I/Os. STXXL has been applied ...
متن کاملBreadth First Search on Massive Graphs
We consider the problem of Breadth First Search (BFS) traversal on massive sparse undirected graphs. Despite the existence of simple linear time algorithms in the RAM model, it was considered non-viable for massive graphs because of the I/O cost it incurs. Munagala and Ranade [29] and later Mehlhorn and Meyer [27] gave efficient algorithms (refered to as MR BFS and MM BFS, respectively) for com...
متن کاملInvestigation of Thermal Operational Regimes for Diamond Bit Drilling Operations (TECHNICAL NOTE)
This paper reviews existing studies and investigates thermal operational regimes of diamond bit during drilling operations. The operating temperature of the diamond core drill is studied under bench condition and an optimal thermal range are presented. Based on this study, it was noted that glazing of diamond tools is observed at temperatures less than 327°C, and normal wear of diamond tools is...
متن کامل