Performance of a Speculative Transmission Schemefor Scheduling-Latency Reduction
Project Team Members:
Latency is the amount of time a message takes to traverse a system.
Low latency is a critical requirement in some switching applications , specifically in parallel computer interconnection networks.
In this latency comprises two components, namely.
We introduce a speculative transmission scheme to significantly reduce the average control-path latency by allowing cells to proceed without waiting for a grant, under certain conditions.
the control-path latency can be almost entirely eliminated for loads up to 50%
The component of parallel computing systems is the interconnection network (ICTN).
To achieve a good system balance between computation and communication,
The ICTN must provide low latency, bandwidth, low error rates, and scalability, node with low latency being the most important requirement.
Control and data path-latencies comprise serialization and de-serialization delays, propagation delay, processing delay between request and response.
We propose a novel method to combine speculative and scheduled transmission in a cross bar switch.
Speculative modes of operation reduced latency at low utilization.
Scheduled modes of operation achieve high maximum throughput.
PROCESSOR : PENTIUM IV 2.6 GHz
RAM : 512 MB DD RAM
MONITOR : 15 COLOR
HARD DISK : 20 GB
CDDRIVE : LG 52X
KEYBOARD : STANDARD 102 KEYS
MOUSE : 3 BUTTONS
Tools Used : JFrameBuilder
Operating System : Windowâ„¢s XP
Back End : SQL Server 2000
Front End : Java, Swing
The speculative transmission that does not have to wait for grant hence low latency.
The scheduled transmission achieve high maximum throughput.
Bibliography or References
 R. Hemenway, R. Grzybowski, C. Minkenberg, and R. Luijten, Optical-packet-switched interconnect for supercomputer applications,OSA J. Opt. Netw., vol. 3, no. 12, pp. 900â€œ913, Dec. 2004.
 C. Minkenberg, F. Abel, P. MÃƒÂ¼ller, R. Krishnamurthy, M. Gusat, P.Dill, I. Iliadis, R. Luijten, B. R. Hemenway, R. Grzybowski, and E.Schiattarella, Designing a crossbar scheduler for HPC applications,IEEE Micro, vol. 26, no. 3, pp. 58â€œ71, May/Jun. 2006.
 E. Oki, R. Rojas-Cessa, and H. Chao, A pipeline-based approach formaximal-sized matching scheduling in input-buffered switches, IEEE Commun. Lett., vol. 5, no. 6, pp. 263â€œ265, Jun. 2001.
 C. Minkenberg, I. Iliadis, and F. Abel, Low-latency pipelined crossbar arbitration, in Proc. IEEE GLOBECOM 2004, Dallas, TX, Dec. 2004, vol. 2, pp. 1174â€œ1179.
 C. Minkenberg, R. Luijten, F. Abel, W. Denzel, and M. Gusat, Current issues in packet switch design, ACM Comput. Commun. Rev., vol. 33, no. 1, pp. 119â€œ124, Jan. 2003.
 C. Minkenberg, F. Abel, P. MÃƒÂ¼ller, R. Krishnamurthy, and M. Gusat,Control path implementation of a low-latency optical HPC switch, inProc. Hot Interconnects 13, Stanford, CA, Aug. 2005, pp. 29â€œ35.
 C.-S. Chang, D.-S. Lee, and Y.-S. Jou, Load-balanced Birkhoff-von Neumann switches, part I: One-stage buffering, Elsevier Comput.Commun., vol. 25, pp. 611â€œ622, 2002.
 A. Tanenbaum, Computer Networks, 3rd ed. Englewood Cliffs, NJ: Prentice Hall, 1996.
 R. Krishnamurthy and P. MÃƒÂ¼ller, An input queuing implementation for low-latency speculative optical switches, in Proc. 2007 Int. Conf.Parallel Processing Techniques and Applications (PDPTAâ„¢07), Las Vegas, NV, Jun. 2007, vol. 1, pp. 161â€œ167.
 H. Takagi, Queueing Analysis, Volume 3: Discrete-Time Systems. Amsterdam: North-Holland, 1993.
Query session ?