[Cplex] Cplex: suggested topics for discussion on the next teleconf.
triegel at redhat.com
Wed Jun 19 14:18:03 CEST 2013
On Tue, 2013-06-18 at 23:48 +0000, Herb Sutter wrote:
> How this impacts WG14 and WG21: IMO we cannot live with a long-term
> requirement that applications use multiple schedulers. Therefore we
> desperately need any Standard C and Standard C++ solutions to be able
> to use the same scheduler (and prototyped proof of this) while still
> surfacing a programming model appropriate for their users (i.e., not
> hamstringing the language design). It would be a disaster to try
> standardize a Standard C model and a Standard C++ model that cannot
> demonstrably share a scheduler -- and I'm pretty sure that would be a
> non-starter for SC22 standardization in an IS, though of course a TS
> can be more experimental.
I think the key point here is that the schedulers need to be able
coordinate their resource usage so that overall performance is good --
not whether they can use the _same_ (instance of a) scheduler.
So, one goal could be to ensure that reasonable implementations of
different schedulers on a particular platform can coordinate their
resource usage. That requires some level of compatibility between how
the schedulers work conceptually (e.g., how to (not) handle
thread-specific storage is an issue), but we would leave most of the
coordination work to the vendors.
Another, more ambitious goal would be to allow users to build their own
schedulers, or integrate their own scheduling/coordination policies or
scheduling inputs. This would require that we standardize how
schedulers can interact with one another.
More information about the Cplex