Computing and Informatics (E-Journal - Institute of Informatics, SAS, Bratislava)
Not a member yet
1506 research outputs found
Sort by
Maximum Coverage Method for Feature Subset Selection for Neural Network Training
Full text linkEvery real object having certain properties can be described by a number of descriptors, visual or other, e.g. mechanical, chemical etc. A set of descriptors (features) characterizing a given object is described in the paper by a vector of descriptors, where each entry of the vector determines a value of some feature of the object. In general, it is important to describe the object as completely as possible, which means by a large number of descriptors. This paper deals with a problem of selection of a proper subset of descriptors, which have the most substantial influence on the properties of the object, so that irrelevant descriptors could be excluded. For this purpose, we introduce a new method, Maximum Coverage Method (MCM). This method has been combined with optimization by a classical genetic algorithm. The described method is used for a data pre-processing, with the resulting selected features serving as an input for a neural network
BP-NUCA: Cache Pressure-Aware Migration for High-Performance Caching in CMPs
Full text linkAs the momentum behind Chip Multi-Processors (CMPs) continues to grow, Last Level Cache (LLC) management becomes a crucial issue to CMPs because off-chip accesses often involve a big latency. Private cache design is distinguished by smaller local access latency, good performance isolation and easy scalability, thus is becoming an attractive design alternative for LLC of CMPs. This paper proposes Balanced Private Non-Uniform Cache Architecture (BP-NUCA), a new LLC architecture that starts from private cache design for smaller local access latency and good performance isolation, then introduces a low cost mechanism to dynamically migrate private blocks among peer private caches of LLC to improve the overall space utilization. BP-NUCA achieves this by measuring the cache access pressure level that each cache set experiences at runtime and then using the information to guide block migration among different private caches of LLC. A heavily accessed set, namely a set with high access pressure level, is allowed to migrate its evicted blocks to peer private caches, replacing blocks of sets which are with the same index and have low access pressure level. By migrating blocks from heavily accessed cache sets to less accessed cache sets, BP-NUCA effectively balances space utilization of LLC among different cores. Experimental results using a full system CMP simulator show that BP-NUCA improves the overall throughput by as much as 20.3 %, 12.4 %, 14.5 % and 18.0 % (on average 7.7 %, 4.4 %, 4.0 % and 6.1 %) over private cache, shared cache, shared cache management scheme UCP and private cache organization CC respectively on a 4-core CMP for SPEC CPU2006 benchmarks
Group-Based Key Management Protocol for Energy Efficiency in Long-Lived and Large-Scale Distributed Sensor Networks
Full text linkAs wireless sensor networks grow, so does the need for effective security mechanisms. We propose a cryptographic key-management protocol, called energy-efficient key-management (EEKM) protocol. Using a location-based group key scheme, the protocol supports the revocation of compromised nodes and energy-efficient rekeying. The design is motivated by the observation that unicast-based rekeying does not meet the security requirements of periodic rekeying in long-lived wireless sensor networks. EEKM supports broadcast-based rekeying for low-energy key management and high resilience. In addition, to match the increasing complexity of encryption keys, the protocol uses a dynamic composition key scheme. EEKM also provides group-management protocols for secure group communication. We analyzed the energy efficiency and security of EEKM and compared it to other key-management protocols using a network simulator
Deadlock-Free Fully-Adaptive Minimal Routing Algorithms: Limitations and Solutions
No full textIn previous papers, a theory for the design of deadlock-free adaptive routing algorithms as well as a design methodology have been proposed. In this paper, an adaptive routing algorithm, obtained from the application of this theory to the 3-D torus, is evaluated under different load conditions and compared with other algorithms. The results show that this algorithm is very fast, also increasing the network throughput considerably. Nevertheless, this adaptive algorithm has cycles in its channel dependency graph. Consequently, when the network is heavily loaded messages may temporarily block cyclically, drastically reducing the performance of the algorithm. Two mechanisms are proposed to avoid this problem
Independence and Domination in Path Graphs of Trees
Full text linkThe problems of determining the maximum cardinality of an independent set of vertices and the minimum cardinality of a maximal independent set of vertices of a graph are known to be NP-complete. We provide efficient algorithms for finding these values for path graphs of trees
A Topology-Independent Mapping Technique for Application-Specific Networks-on-Chip
Full text linkThe design of Networks-on-Chip (NoCs) involves several key issues, including the topological mapping, that is, the mapping of the processing elements or Intellectual Properties (IPs) to the network nodes. Although several proposals have been focused on topological mapping last years, this topic is still an open issue. In this paper, we propose, in an extended manner, a topology-independent mapping technique for application-specific NoCs that can be used with regular or irregular topologies, and with any routing algorithm. This technique globally matches the communication pattern generated by the IPs with the available network bandwidth in the different parts of the network. The evaluation results show that the proposed technique can provide better performance than other mapping techniques not only in terms of average latency and network throughput, but also in terms of power consumption