Learn More
Advances in hardware have enabled many long-running applications to execute entirely in main memory. As a result, these applications have increasingly turned to database techniques to ensure durability in the event of a crash. However, many of these applications, such as massively multiplayer online games and main-memory OLTP systems, must sustain extremely(More)
Network processors (NPs), a type of multicore, multithread system that exploits system-on-chip techniques, usually adopt a distributed, shared memory hierarchy to scale up network processing. Network applications running on NP often display distinct characteristics on memory subsystem compared with traditional processors with multilevel cache. As security,(More)
In this paper, a general fluid model is developed to study the performance and fairness of BitTorrent-like networks. The fluid model incorporates two important features previously isolated from system performance models, user settings with multiple groups and inter-group data exchange induced by the choking algorithm. Our numerical results point out some(More)
As an application-driven network, wireless sensor network generally requires data reliability to maintain detection and response capabilities. Although two approaches, namely, retransmission and redundancy, have been proposed to enhance data reliability, the theoretical work is required to evaluate their impact on transmission reliability and energy(More)
Axiom 4 (Collapsing) We can collapse two vertices into one without changing the rank of remaining vertices, if the outgoing edges of the two vertices lead to the same set of vertices, as in Figure 1. A B ! C Figure 1: Axiom 4: collapsing A and B into C does not change the rank of the remaining vertices. Axiom 5 (Proxy) If A, B and C have the same rank, and(More)
We talked about growth models in Lecture 12 (Feb 15), now we discuss adding edges by preferential attachment. To achieve this, we create the graph as follows: at each unit of time t i , 1 add a vertex, and label it with i 2 with probability δ add an edge from the new vertex to vertex picked with probability proportional to its degree. Let d i (t) be(More)