Photonic Interconnection Networks for Multicore Architectures

 
Thread Tools Search this Thread
Special Forums News, Links, Events and Announcements UNIX and Linux RSS News Photonic Interconnection Networks for Multicore Architectures
# 1  
Old 12-23-2010
Photonic Interconnection Networks for Multicore Architectures

HPL-2010-204 Photonic Interconnection Networks for Multicore Architectures - Binkert, Nathan; Fiorentino, Marco
Keyword(s): Nanophotonic Architecture, Networking, Optics
Abstract: Silicon nanophotonics provides computer architects with the ability to solve pin bandwidth and cross-chip communication problems. Furthermore, ring resonators can be used to create simple optical circuits to implement low-latency global arbitration. ...
Full Report

More...
Login or Register to Ask a Question

Previous Thread | Next Thread

5 More Discussions You Might Find Interesting

1. Programming

Best reference for understanding core file and debugging for different architectures

Hi , could someone suggest best reference for core file understanding , analysis , debugging for different architectures like what registers represent what in a architecture specific core .. how to get maximum information out of corrupted core different tools and how they work and how to... (1 Reply)
Discussion started by: Gopi Krishna P
1 Replies

2. Shell Programming and Scripting

How give tasks to individual processors in a multicore processor ?

Hi all, Using shell script, how to assign tasks to individual processors in a multicore processor ? For example: If I have 4 processors, I want to give one job to each of the processors. (When I give multiple jobs, it's assigning all the load to a single processor. ) Thanks R (5 Replies)
Discussion started by: habzone2007
5 Replies

3. IP Networking

interconnection

hai i want to access my office server from my pc at home , i know the ip add subnetmask and gate way , where i should configure (1 Reply)
Discussion started by: sasiprabu
1 Replies

4. HP-UX

How do I detect multicore processors?

I'm fairly new to HP-UX, and I need to know how to identify the number of cores on a PA-8800 processor from the command line. Any help here would be appreciated. (11 Replies)
Discussion started by: Midcain
11 Replies

5. HP-UX

Multicore from a different angle

Everyone seemed to be a little stumped by the multicore question I asked earlier this week, so I decided I'd try a different angle. Turns out that on a multicore system HP-UX reports every core as a seperate processor. All the usual commands (ioscan, top, etc.) report two processors for every... (7 Replies)
Discussion started by: Midcain
7 Replies
Login or Register to Ask a Question
CC_CHD(4)						   BSD Kernel Interfaces Manual 						 CC_CHD(4)

NAME
cc_chd -- CHD Congestion Control Algorithm DESCRIPTION
CHD enhances the HD algorithm implemented in cc_hd(4). It provides tolerance to non-congestion related packet loss and improvements to coex- istence with traditional loss-based TCP flows, especially when the bottleneck link is lightly multiplexed. Like HD, the algorithm aims to keep network queuing delays below a particular threshold (queue_threshold) and decides to reduce the conges- tion window (cwnd) probabilistically based on its estimate of the network queuing delay. It differs from HD in three key aspects: o The probability of cwnd reduction due to congestion is calculated once per round trip time instead of each time an acknowledgement is received as done by cc_hd(4). o Packet losses that occur while the queuing delay is less than queue_threshold do not cause cwnd to be reduced. o CHD uses a shadow window to help regain lost transmission opportunities when competing with loss-based TCP flows. MIB Variables The algorithm exposes the following tunable variables in the net.inet.tcp.cc.chd branch of the sysctl(3) MIB: queue_threshold Queueing congestion threshold (qth) in ticks. Default is 20. pmax Per RTT maximum backoff probability as a percentage. Default is 50. qmin Minimum queuing delay threshold (qmin) in ticks. Default is 5. loss_fair If 1, cwnd is adjusted using the shadow window when a congestion related loss is detected. Default is 1. use_max If 1, the maximum RTT seen within the measurement period is used as the basic delay measurement for the algorithm, otherwise a sampled RTT measurement is used. Default is 1. SEE ALSO
cc_cubic(4), cc_hd(4), cc_htcp(4), cc_newreno(4), cc_vegas(4), h_ertt(4), mod_cc(4), tcp(4), khelp(9), mod_cc(9) D. A. Hayes and G. Armitage, "Improved coexistence and loss tolerance for delay based TCP congestion control", in 35th Annual IEEE Conference on Local Computer Networks, 24-31, October 2010. ACKNOWLEDGEMENTS
Development and testing of this software were made possible in part by grants from the FreeBSD Foundation and Cisco University Research Pro- gram Fund at Community Foundation Silicon Valley. HISTORY
The cc_chd congestion control module first appeared in FreeBSD 9.0. The module was first released in 2010 by David Hayes whilst working on the NewTCP research project at Swinburne University of Technology's Centre for Advanced Internet Architectures, Melbourne, Australia. More details are available at: http://caia.swin.edu.au/urp/newtcp/ AUTHORS
The cc_chd congestion control module and this manual page were written by David Hayes <david.hayes@ieee.org>. BSD
September 15, 2011 BSD