High speed Internet routers and switches require fast packet buffer to hold packets during times of congestion. These buffers usually use a memory hierarchy that consist of expensive but fast SRAM and cheap but slow D...
详细信息
High speed Internet routers and switches require fast packet buffer to hold packets during times of congestion. These buffers usually use a memory hierarchy that consist of expensive but fast SRAM and cheap but slow DRAM to meet both, speed and capacity requirements. A challenge building these packet buffers is to provide deterministic bandwidth guarantee under any traffic condition. We propose a novel hybrid packet buffer architecture with parallel DRAMs. Our approach reduces the amount of required SRAM compared to state-of-the-art architectures significantly, e. g., the tail SRAM by 47% for a 100Gbps line card using DDR3 SDRAM. Our architecture also applies packet aggregation and thereby minimizes the required DRAM and SRAM bandwidth and eliminates fragmentation. We are currently implementing the architecture on an FPGA and provide first results.
In network design, the Optimal communication Spanning Tree (OCST) problem is to find a spanning tree that connects the network entities and satisfies their communication requirements with minimal total cost. In an emb...
详细信息
In network design, the Optimal communication Spanning Tree (OCST) problem is to find a spanning tree that connects the network entities and satisfies their communication requirements with minimal total cost. In an embedded Ethernet network, we organize the full duplex links into bundles and install these bundles into ducts. The traditional OCST problem does not take into account this fact. In this paper, we introduce a mathematical model of the communication cost of an embedded Ethernet network. We propose novel algorithms to find an OCST. Their principle idea is that they iteratively examine a set of neighboring trees that differ in one duct and choose the tree with the lowest cost. Finally, we evaluate the performance of the algorithms in terms of the quality of the solution found as well as the running time.
Parallel garbage collection seeks to exploit the inherent parallelism of graph tracing by evenly distributing the set of objects in the heap among all available processing resources. Any straightforward implementation...
详细信息
Parallel garbage collection seeks to exploit the inherent parallelism of graph tracing by evenly distributing the set of objects in the heap among all available processing resources. Any straightforward implementation, however, suffers from prohibitive overheads since each access to the worklist of objects and to the objects themselves needs to be protected by synchronization, especially so in the case of compacting collectors. For this reason, known parallel collectors sacrifice a great deal of work distribution granularity and scalability to keep the synchronization costs acceptable. In this paper, we present a case study of a different approach. Our parallel compacting collector is based on Cheney's copying algorithm, employs a single worklist and distributes garbage collection work on an object-by-object basis. This way, it achieves well balanced work distribution and good scalability. To solve the synchronization problem, we introduce a low-cost multi-core garbage collection coprocessor and take advantage of hardware-supported synchronization. We built an FPGA-based prototype with a single-core main processor supported by a multi-core garbage collection coprocessor. Measurement results show that an 8-core garbage collection coprocessor decreases the duration of garbage collection cycles by a factor of up to 7.4, while a 16-core configuration still achieves a factor of up to 12.1.
Trust, Accounting, Billing, Auditing and Charging (TABAC) are crucial functions of productive IT and telecommunication systems. However, they are often not considered in early stages of development, but have considera...
详细信息
Trust, Accounting, Billing, Auditing and Charging (TABAC) are crucial functions of productive IT and telecommunication systems. However, they are often not considered in early stages of development, but have considerable impact on commercial success at later stages. On the one hand, these functions are costly to be added after having a running prototype. On the other hand, they should not be burdens in early development stages. In order to solve this dilemma, we propose a framework for model-driven proposal and evaluation of TABAC strategies. This framework allows both: evaluating the possibilities to add TABAC functions at an early development stage and adding TABAC strategies to running prototypes by using existing interfaces and applying general models from a model pool. The framework not only proposes suitable strategies based on capabilities and requirements of the existing system. Moreover, it aims at instantiating the TABAC functions in a runtime environment for feeding them with real data from the existing system. This outstanding feature allows compiling a proposal for the best suiting strategy based on realistic interactions with the prototype.
Careful modeling of the radio channel characteristics is an important issue for system level simulations. While a number of detailed path loss, shadowing and fast fading models can be found in literature, many of them...
详细信息
ISBN:
(纸本)9781424425181;9781424425198
Careful modeling of the radio channel characteristics is an important issue for system level simulations. While a number of detailed path loss, shadowing and fast fading models can be found in literature, many of them entail large computational efforts and hence lead to long simulation times, or require huge amounts of memory. In this paper, we focus on shadowing models with two-dimensional correlation properties. We present handover performance evaluations as a use case from which requirements to the modeling of the shadow fading are derived. For different implementations of the shadow fading in system level simulations, we discuss their pros and cons and then focus on the sum of sinusoid model proposed by Cai and Giannakis. Our main contribution lies in a new frequency sampling method to determine the coefficients of the sinusoidal waveforms. We show that this new method, denoted as Power Sampling Method (PSM), allows for a significant reduction of the number of sinusoids while the correlation properties of the shadow fading channel are preserved.
In cellular OFDMA networks, there exists a fundamental trade-off between the achievable cell capacity and the degree of fairness among the users in the cell. Several scheduling algorithms have been proposed which try ...
详细信息
In cellular OFDMA networks, there exists a fundamental trade-off between the achievable cell capacity and the degree of fairness among the users in the cell. Several scheduling algorithms have been proposed which try to balance this tradeoff. The parameterization of these scheduling algorithms to achieve a certain desired fairness level is non-trivial. We show that the optimal fairness parameter settings depend on the system state, such as the current cell load. Our main contribution is a design of a self-optimizing scheduler architecture which includes a controller element that dynamically adjusts the fairness parameters of the scheduler. We demonstrate that with this design, an operator-defined reference fairness level is maintained in scenarios with fluctuating load and thus cell throughput can be improved. It is applicable for a class of proportional fair scheduling algorithms and can be adapted to other algorithms allowing to influence the fairness level.
作者:
Hong GuoWenzhuo TangYu LiuWei WeiCREAM Group
State Key Laboratory of Advanced Optical Communication Systems and Networks (Peking University) and Institute of Quantum Electronics School of Electronics Engineering and Computer Science Peking University Beijing 100871 China
We present a simple approach to realize truly random number generator based on measuring the phase noise of a single-mode vertical cavity surface emitting laser. The true randomness of the quantum phase noise originat...
详细信息
We present a simple approach to realize truly random number generator based on measuring the phase noise of a single-mode vertical cavity surface emitting laser. The true randomness of the quantum phase noise originates from the spontaneous emission of photons and the random bit generation rate is ultimately limited only by the laser linewidth. With the final bit generation rate of 20 Mbit/s, the truly random bit sequence guaranteed by the uncertainty principle of quantum mechanics passes the three standard randomness tests (ENT, Diehard, and NIST Statistical Test Suites). Moreover, a continuously generated random bit sequence, with length up to 14 Gbit, is verified by two additional criteria for its true randomness.
Multihop wireless access networks, where clients can access the Internet through Internet gateways by direct or multihop transmissions, are potential for future wireless data services and vehicular network application...
详细信息
Multihop wireless access networks, where clients can access the Internet through Internet gateways by direct or multihop transmissions, are potential for future wireless data services and vehicular network applications. In the context of multihop transmissions, less number of gateways is required for Internet access while a certain level of Internet connectivity still holds. In this paper, we investigate the Internet connectivity, which is the probability that all clients are Internet-reachable, in one-dimensional multihop wireless access networks. We show the relationship between the Internet connectivity and the deployment of Internet gateways. We also investigate the mean number of isolated clients, who are not Internet-reachable, in a multihop wireless access network. These results are useful for network operators to deploy Internet gateways, manage clients and design protocols for future vehicular network applications. The theoretical results are corroborated through extensive simulations.
In recent years, Identity Management (IdM) has gained a lot of attention in industry, standardisation and academia. In particular, a couple of research projects, like Daidalos or Prime, have invested considerable effo...
详细信息
暂无评论