Filters








32,074 Hits in 4.8 sec

The lock-free k-LSM relaxed priority queue

Martin Wimmer, Jakob Gruber, Jesper Larsson Träff, Philippas Tsigas
2015 Proceedings of the 20th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming - PPoPP 2015  
It is built from a logarithmic number of sorted arrays, similar to log-structured merge-trees (LSM).  ...  We compare to state-ofthe-art lock-free priority queues with both relaxed and non-relaxed semantics, showing high performance and good scalability of our approach.  ...  A log-structured merge-tree (LSM) is a priority queue that operates on a logarithmic number of sorted arrays of sizes padded to the next power of two.  ... 
doi:10.1145/2688500.2688547 dblp:conf/ppopp/0003GTT15 fatcat:t5g2mgajqfflpdmkqhe5afppxq

The lock-free k-LSM relaxed priority queue

Martin Wimmer, Jakob Gruber, Jesper Larsson Träff, Philippas Tsigas
2015 SIGPLAN notices  
It is built from a logarithmic number of sorted arrays, similar to log-structured merge-trees (LSM).  ...  We compare to state-ofthe-art lock-free priority queues with both relaxed and non-relaxed semantics, showing high performance and good scalability of our approach.  ...  A log-structured merge-tree (LSM) is a priority queue that operates on a logarithmic number of sorted arrays of sizes padded to the next power of two.  ... 
doi:10.1145/2858788.2688547 fatcat:emmtduqidvczhlmct56c6yphcu

Aether

Ryan Johnson, Ippokratis Pandis, Radu Stoica, Manos Athanassoulis, Anastasia Ailamaki
2010 Proceedings of the VLDB Endowment  
In this paper, we identify four logging-related impediments to database system scalability.  ...  c) extensive context switching overwhelms the OS scheduler with threads executing log I/Os, and (d) contention appears as transactions serialize accesses to in-memory log data structures.  ...  Fourth, we discuss about distributing the log and why it is very difficult to have an efficient and scalable distributed log implementation (Section A.5).  ... 
doi:10.14778/1920841.1920928 fatcat:2mkbokgsqbezxhk66vk7np6ieq

Scalable stability detection using logical hypercube

R. Friedman, S. Manor, K. Guo
2002 IEEE Transactions on Parallel and Distributed Systems  
This paper proposes to use a logical hypercube structure for detecting message stability in distributed systems.  ...  Scalability: Each nodes need to communicate with only log(n) nodes.  ...  However, to the best of our knowledge, we are the rst to suggest to use a logical hypercube structure in order to deal with scalability issues in distributed environments.  ... 
doi:10.1109/tpds.2002.1036070 fatcat:mvvetjawcbhltgzbzms7brjvqa

Scalability of write-ahead logging on multicore and multisocket hardware

Ryan Johnson, Ippokratis Pandis, Radu Stoica, Manos Athanassoulis, Anastasia Ailamaki
2011 The VLDB journal  
c) extensive context switching overwhelms the OS scheduler with threads executing log I/Os, and (d) contention appears as transactions serialize accesses to in-memory log data structures.  ...  In this paper, we identify four loggingrelated impediments to database system scalability.  ...  We note that the distributed log indeed eliminates contention, unlike the multisocket-optimized c-array.  ... 
doi:10.1007/s00778-011-0260-8 fatcat:xkwl2lxlvbc5fed6o2qzrwy554

LD-Sketch: A distributed sketching design for accurate and scalable anomaly detection in network data streams

Qun Huang, Patrick P. C. Lee
2014 IEEE INFOCOM 2014 - IEEE Conference on Computer Communications  
We propose LD-Sketch, a data structure designed for accurate and scalable traffic anomaly detection using distributed architectures.  ...  Our results demonstrate the accuracy and scalability of LD-Sketch over prior approaches.  ...  To improve scalability, anomaly detection needs to be performed on distributed packet streams in parallel.  ... 
doi:10.1109/infocom.2014.6848076 dblp:conf/infocom/HuangL14 fatcat:znw5jhbp5fbtznpdw5p2xploi4

Pursuing scalability for hypre's conceptual interfaces

Robert D. Falgout, Jim E. Jones, Ulrike Meier Yang
2005 ACM Transactions on Mathematical Software  
These interfaces include a stencil-based structured interface (Struct); a semi-structured interface (semiStruct), which is appropriate for applications that are mostly structured, e.g. block structured  ...  It is extremely important to provide an efficient, scalable implementation of these interfaces in order to support the scalable solvers of the library, especially when using tens of thousands of processors  ...  Figure 8 :Figure 9 : 89 An example block-structured grid, distributed across many processors.  ... 
doi:10.1145/1089014.1089018 fatcat:hir7sffnord3tnn6qk5coa2qmy

Highly scalable algorithm for distributed real-time text indexing

Ankur Narang, Vikas Agarwal, Monu Kedia, Vijay K Garg
2009 2009 International Conference on High Performance Computing (HiPC)  
Our algorithm uses group-based index construction and leverages novel index data structures that reduce load imbalance and make text indexing and merge process more scalable and efficient.  ...  We show analytically that the asymptotic parallel time complexity of our distributed indexing algorithm, is at least Ω(log(P )) factor better than typical indexing approaches, where P is the number of  ...  We establish theoretically that the asymptotic parallel time complexity of the distributed algorithm using our data-structures is at least Ω(log(P )) better than the same algorithm using the data-structures  ... 
doi:10.1109/hipc.2009.5433193 dblp:conf/hipc/NarangAKG09 fatcat:fepvpwqvtzffrg72rfjr7bkbaa

Achieving Memory Scalability in the Gysela Code to Fit Exascale Constraints [chapter]

Fabien Rozar, Guillaume Latu, Jean Roman
2014 Lecture Notes in Computer Science  
During a run of Gysela, each Mpi process is associated with a µ value (Section 2) and sees the distribution function as a 4D array and the electric field as a 3D array.  ...  The take and drop subroutines perform the allocation and deallocation of the array handled and they log their memory action in the dynamic memory trace file.  ... 
doi:10.1007/978-3-642-55195-6_17 fatcat:y7eyxezenvh6rikaz4fbf57acy

Lithium

Jacob Gorm Hansen, Eric Jul
2010 Proceedings of the 1st ACM symposium on Cloud computing - SoCC '10  
Lithium aims to be scalable, highly available, and compatible with commodity hardware and existing application software.  ...  data corruption and host failures, but also often faster than naïve approaches and, for a relatively small cluster of just eight hosts, performs well compared with an enterprise-class Fibre Channel disk array  ...  As such, Lithium may be considered a log-structured file system (LFS) [36] or a scalable collection of logical disks [14] .  ... 
doi:10.1145/1807128.1807134 dblp:conf/cloud/HansenJ10 fatcat:ampqjhtidjdylgwt74h7sjcwxe

Scalable virtual machine storage using local disks

Jacob Gorm Hansen, Eric Jul
2010 ACM SIGOPS Operating Systems Review  
Lithium aims to be scalable, highly available, and compatible with commodity hardware and existing application software.  ...  We are building Lithium, a distributed storage system designed specifically for virtualization workloads running in large-scale data centers and clouds.  ...  As such, Lithium may be considered a log-structured file system (LFS) [13] or a scalable collection of logical disks [4] .  ... 
doi:10.1145/1899928.1899936 fatcat:jv2qntgiuff6fpezjs4bipias4

The Lock-free k-LSM Relaxed Priority Queue [article]

Martin Wimmer, Jakob Gruber, Jesper Larsson Träff, Philippas Tsigas
2015 arXiv   pre-print
The priority queue is built from a logarithmic number of sorted arrays in a way similar to log-structured merge-trees.  ...  Lock-free data structures promise superior scalability by avoiding blocking synchronization primitives, but the delete-min operation is an inherent scalability bottleneck in concurrent priority queues.  ...  Log-structured Merge-tree We now present our new priority queue based on log-structured merge-trees (LSM).  ... 
arXiv:1503.05698v1 fatcat:7g5wbzeyo5eypffi266wr4ta7e

An Energy Scalable Functional Unit for Sensor Signal Processing

Liping Guo, Mackenzie Scott, Rajeevan Amirtharajah
2007 2007 IEEE International Conference on Acoustics, Speech and Signal Processing - ICASSP '07  
The array maximizes operating life by matching system power consumption to available energy through power scalable approximate signal processing [1].  ...  This paper presents the detailed architecture and implementation of the functional unit in the array.  ...  We have proposed an energy scalable computational array for such sensor signal processing [1] which consists of functional units embedded in an island-style interconnect structure.  ... 
doi:10.1109/icassp.2007.366175 dblp:conf/icassp/GuoSA07 fatcat:ibxmsd3k4bdknkmrd4tp5z6xty

A hybrid local and distributed sketching design for accurate and scalable heavy key detection in network data streams

Qun Huang, Patrick P.C. Lee
2015 Computer Networks  
We propose LD-Sketch, a data structure designed for accurate and scalable traffic anomaly detection using distributed architectures.  ...  LD-Sketch combines the classical counter-based and sketch-based techniques, and performs detection in two phases: local detection, which guarantees zero false negatives, and distributed detection, which  ...  To improve scalability, anomaly detection needs to be performed on distributed packet streams in parallel.  ... 
doi:10.1016/j.comnet.2015.08.025 fatcat:q5xb2k5sujfvfj3ujrjgmexhr4

Analysis of Parallel Algorithms for Energy Conservation in Scalable Multicore Architectures

Vijay Anand Korthikanti, Gul Agha
2009 2009 International Conference on Parallel Processing  
This paper analyzes energy characteristics of parallel algorithms executed on scalable multicore processors.  ...  The results suggest that power and performance scalability of a parallel algorithm can be quite different.  ...  Sequential quicksort algorithm performs on average O(N log(N )) comparisons for sorting an array of size N .  ... 
doi:10.1109/icpp.2009.74 dblp:conf/icpp/KorthikantiA09 fatcat:qy6b7gwjbfai3a6whdxjn7jusi
« Previous Showing results 1 — 15 out of 32,074 results