Sign Up to our social questions and Answers Engine to ask questions, answer people’s questions, and connect with other people.
Login to our social questions & Answers Engine to ask questions answer people’s questions & connect with other people.
Lost your password? Please enter your email address. You will receive a link and will create a new password via email.
Please briefly explain why you feel this question should be reported.
Please briefly explain why you feel this answer should be reported.
Please briefly explain why you feel this user should be reported.
I worked on implementing a reasoner, a complex stuff. I tried to improve performance by employing parallelized threads, but only gained overhead.
My question is whether there are other potential bottlenecks besides monitors (locks). I removed all such indicators as synchronized and volatile from my program.
I use java.util.concurrent utilities, and split data into standalone arrays for threads.
The most useful think you can do is ensure you thread are performing long sequences of independent work. These sequences need to be significantly longer than the overhead you are likely to incur (say 1 – 10 micro-seconds)
A common mistake is to break up the work too finely (creating a lot of overhead in the process). You only need one task per core to keep every core busy.
Without most details of what you are trying to do and how you are breaking up your work, its hard to suggest anything more specific.