What's New? Intel® Threading Building Blocks 4.4 Update 2

Changes (w.r.t. Intel TBB 4.4 Update 1):

- Improved interoperability with Intel(R) OpenMP RTL (libiomp) on Linux:
    OpenMP affinity settings do not affect the default number of threads
    used in the task scheduler. Intel(R) C++ Compiler 16.0 Update 1
    or later is required.
- Added a new flow graph example with different implementations of the
    Cholesky Factorization algorithm.

Preview Features:

- Added template class opencl_node to the flow graph API. It allows a
    flow graph to offload computations to OpenCL* devices.
- Extended join_node to use type-specified message keys. It simplifies
    the API of the node by obtaining message keys via functions
    associated with the message type (instead of node ports).
- Added static_partitioner that minimizes overhead of parallel_for and
    parallel_reduce for well-balanced workloads.
- Improved template class async_node in the flow graph API to support
    user settable concurrency limits.

Bugs fixed:

- Fixed a possible crash in the GUI layer for library examples on Linux.

 

For more complete information about compiler optimizations, see our Optimization Notice.