Go to file
2019-10-02 08:22:22 +02:00
build Fix boost-install use; should only be issued once 2018-10-06 01:39:58 +03:00
doc docu: support for sanitizers 2019-10-02 08:22:06 +02:00
examples Remove non-source files. 2018-12-03 08:00:59 -05:00
include/boost/fiber call destructor for values in channel 2019-08-20 09:53:44 +02:00
meta fix meta infos 2016-11-22 19:59:10 +01:00
performance fix unsufficent synchronization of work-stealing algorithms 2018-08-21 09:53:37 +02:00
src Merge pull request #196 from romange/FixLockContention 2019-04-01 07:55:50 +02:00
test unbuffered_channel: resume fiber blocked in unbuffered_channel<>::push() 2018-10-06 08:28:43 +02:00
.gitignore exlcude CUDA binaries in .gitignore 2018-12-03 14:34:57 +01:00
.travis.yml Add Mac OS X jobs to Travis 2017-11-08 15:30:20 +02:00
index.html add index.htm 2016-06-07 08:14:02 +02:00
README.md Update README.md 2019-01-05 15:29:14 +05:30

Boost.fiber

Boost.fiber provides a framework for micro-/userland-threads (fibers) scheduled cooperatively. The API contains classes and functions to manage and synchronize fibers similar to boost.thread.

A fiber is able to store the current execution state, including all registers and CPU flags, the instruction pointer, and the stack pointer and later restore this state. The idea is to have multiple execution paths running on a single thread using a sort of cooperative scheduling (threads are preemptively scheduled) - the running fiber decides explicitly when it yields to allow another fiber to run (context switching).

A context switch between threads costs usually thousands of CPU cycles on x86 compared to a fiber switch with less than 100 cycles. A fiber can only run on a single thread at any point in time.

Boost.fiber requires C++11!