The IEEE 802.11ac standard introduces new downlink multi-user MIMO (DL-MU-MIMO) transmissions to up to four users in order to increase spatial reuse in wireless local area networks (WLANs). We argue that even better WLAN performance can be achieved by slightly modifying the DL-MU-MIMO scheduling. To this end we propose a new queuing mechanism based on the decoupling of EDCA and DL-MU-MIMO sched...

To meet the growing computation-intensive applications and the needs of low-power, highperformance systems, and the number of computing resources in single-chip has enormously increased, because current VLSI technology can support such an extensive integration of transistors. This paper presents adaptive routing selection strategies suitable for network-on-chip (NoC). The main prototype present...

In this paper, we focus on the practical issues of designing e cient complete exchange algorithms on a commodity cluster interconnected by a non-blocking crossbar switch. Four complete exchange algorithms, including, shift exchange, pairwise exchange, group shu e exchange and synchronous shu e exchange algorithms are studied and tested on a cluster platform. These algorithms feature their own c...

The Cray XT is an MPP system that scales up to 32K nodes using a bidirectional 3-dimensional torus interconnection network. Four virtual channels are used to provide point-to-point flow control and deadlock avoidance. Using virtual channels avoids unnecessary head-of-line (HoL) blocking for different network traffic flows, however, the extent to which virtual channels improves network utilizati...

Input buffered switches have the strong advantage of efficient crossbar usage. Virtual Output Queueing (VOQ) has to be established to circumvent the head-of-line (HOL) blocking which limits the throughput to 58.6%. Arbitration algorithms control the access to the switch fabric in each time slot. Weighted algorithms achieve 100% throughput with lowest delays under all admissible traffic even und...

This paper evaluates the gain in throughput achieved by the use of a shared buffer to realize the output queues of switching elements in the presence of self-similar multimedia traffic. Unlike previous studies, we focus on credit-based systems typical of networks used in parallel multimedia servers. It is generally believed that buffer sharing improves performance in the presence of non-uniform...

High speed packet switches are inevitable for ultra high data rate networking systems. The throughput of these switches has to be ideally 100% for effective utilization of the network. While Output Queued (OQ) switches have the optimal delay-throughput performance for all traffic distributions, they require N-times speed up in the fabric that limits the scalability of this architecture. An Inpu...

The input-queued switching architecture is becoming the alternative architecture for high speed switches owing to its scalability. Tremendous amount of effort has been made to overcome the throughput problem caused by head of line blocking and the contentions occurred at input and output sides of a switch. Existing algorithms only aim at improving throughput but inadvertently ignore undesired e...

Managing increasing traffic from Instant Messengers and P2P applications is becoming more important nowadays. We present an inkernel architecture of management gateway, namely kP2PADM, built upon open-source packages with several modifications and design techniques. First, the in-kernel design streamlines the data path through the gateway. Second, the dual-queue buffer eliminates head-of-line b...

The effects of background line opacity (line-blocking) in statistical equilibrium calculations for Fe in late-type stellar atmospheres have been investigated using an extensive and up-to-date model atom with radiative data primarily from the  Project. The background metal line opacities have been computed using data from the  stellar model atmospheres. While accounting for this line op...