On Fri, Nov 15, 2019 at 12:38:06PM +0000, Andrew Stubbs wrote:
> On 15/11/2019 12:21, Jakub Jelinek wrote:
> > On Thu, Nov 14, 2019 at 04:36:38PM +0000, Andrew Stubbs wrote:
> > > This patch adds some necessary bits to enable OpenACC testings for amdgcn
> > > offloading.
> > >
> > > The two "check_effective" procedures are not actually needed yet, but
> > > later
> > > patches to test cases will use them.
> > >
> > > OK to commit?
> >
> > I'm surprised by the set acc_mem_shared 0, I thought gcn is a shared memory
> > offloading target.
>
> APUs, such as Carizzo are shared memory. DGPUs, such as Fiji and Vega, have
> their own memory. A DGPU can access host memory, provided that it has been
> set up just so, but that is very slow, and I don't know of a way to do that
> without still having to copy the program data into that special region.
Ah, that is going to be interesting e.g. for
#pragma omp requires unified_shared_memory
My plan was that for this the TU constructor would call some libgomp
library function that in the end would when loading plugins ensure that
only shared memory supporting plugins are loaded. If the gcn plugin
will support shared memory only conditionally, we'll need some interfaces to
ensure that.
Jakub
