Non-Blocking Algorithms for performance ...

[James Ladd]

If your serious about asynchronous, multi-threaded applications with great performance (as I am) then
you should read the following articles which I hope help you as much as they did me.

Simple, Fast and Practical Non-Blocking and Blocking Concurrent Queue Algorithms
http://www.google.com.au/url?sa=t&ct=res&cd=1&url=http%3A%2F%2Fwww.cogsci.rochester.edu%2Fu%2Fscott%2Fpapers%2F1996_PODC_queues.pdf&ei=xQ80RdjrM57kgQOS67zPAw&sig=__54mFjpXm84qAh2cZquOFRLsJb_g=&sig2=eGIjlhhJvnbJX29L46T-ng
An Optimistic Approach to Lock-Free FIFO Queues
http://www.google.com.au/url?sa=t&ct=res&cd=1&url=http%3A%2F%2Fpeople.csail.mit.edu%2Fedya%2Fpublications%2FOptimisticFIFOQueue-DISC2004.pdf&ei=YRA0RYf6FaSEgwOHlZCWCA&sig=__P0NDl1vraChjv1RFcOmnNSlXdxM=&sig2=43CprgztRXF2lBRqDZCcCw
Safe Memory Reclaimation for Dynamic Lock-Free Objects Using Atomic Reads and Writes
http://www.google.com.au/url?sa=t&ct=res&cd=1&url=http%3A%2F%2Fwww.research.ibm.com%2Fpeople%2Fm%2Fmichael%2Fpodc-2002.pdf&ei=oBA0RYANgryAA_iuvJUE&sig=__RYoPcv9IDqvnxQjXYgyZHh2NoNs=&sig2=eclwEngCmHUwVVc0Z5p7Og

If you only read one, make it this one: Safe Memory Reclaimation for Dynamic Lock-Free Objects Using Atomic Reads and Writes
http://www.google.com.au/url?sa=t&ct=res&cd=1&url=http%3A%2F%2Fwww.research.ibm.com%2Fpeople%2Fm%2Fmichael%2Fpodc-2002.pdf&ei=oBA0RYANgryAA_iuvJUE&sig=__RYoPcv9IDqvnxQjXYgyZHh2NoNs=&sig2=eclwEngCmHUwVVc0Z5p7Og

I am adding the algorithms mentioned above into the hyperserve project (libjlc) and will submit
a variation to GeneSys if I have time.

Rgs, James.