Hi All,

Are there currently any plans to expand the usage of Openmp parallel for
loops within the jsource engine?

I can see that they're currently used within gemm.c and the base64 code but
don't seem to be used anywhere else within j.

It seems like there could potentially be some good performance wins for a
lot of the embarrassingly parallel operations represented by the j
primitives on modern architectures.
Is this just something that is on the TODO list that hasn't become a
priority yet or is there something more to this than meets the eye at first
glance?

Cheers,
Aaron.
----------------------------------------------------------------------
For information about J forums see http://www.jsoftware.com/forums.htm

Reply via email to