Intel® oneAPI Threading Building Blocks
Ask questions and share information about adding parallelism to your applications when using this threading library.
Announcements
Welcome to the Intel Community. If you get an answer you like, please mark it as an Accepted Solution to help others. Thank you!

Performance characteristics of tbb::concurrent_bounded_queue?

Tai__Zizheng
Beginner
96 Views

Hi all,

I just started evaluating TBB for a project at hand and I'm wondering what kind of performance should I expect from tbb::concurrent_bounded_queue. Some questions that I have not found answer to by glancing at the code:

  • Is it lock-based / lock-free / wait-free?
  • Is the fast-path lock-free / wait-free?
  • Is it suitable for single-producer / multi-producer / single-consumer / multi-consumer?
  • Is it NUMA-aware?

Sorry if this is somewhere in the documentation, but I haven't been able to find the answers after reading it carefully. Appreciate any help in advance!

0 Kudos
1 Reply
Aleksei_F_Intel
Employee
96 Views

Hi Zizheng,

Answering your questions: tbb::concurrent_bounded_queue is lock-based. It uses fine-grained locks. As far as I know, even the fast-path is not lock-free. It is suitable for multi-producer/consumer and it is not NUMA-aware.

Regards,

Aleksei

Reply