Re: Which OpenACC 'acc_device_t' to use for AMD GPU offloading

2019-12-03 Thread Tobias Burnus
Regarding theĀ  acc_device_, I want to observe that there is no fundamental reason that one cannot have multiple names which resolve to the same constant. Thus, one could add acc_device_radeon while keeping acc_device_gcn. Whether this makes sense or causes even more confusion is another questi

Re: Which OpenACC 'acc_device_t' to use for AMD GPU offloading

2019-12-03 Thread Thomas Schwinge
Hi! On 2019-12-03T14:20:13+, Julian Brown wrote: > On Tue, 3 Dec 2019 10:32:57 +0100 > Thomas Schwinge wrote: >> On 2019-12-02T14:50:42+, Julian Brown >> wrote: >> > On Mon, 2 Dec 2019 15:43:29 +0100 >> > Thomas Schwinge wrote: >> > >> >> > --- a/libgomp/openacc.h >> >> > +++ b/libgo

Re: Which OpenACC 'acc_device_t' to use for AMD GPU offloading (was: [PATCH 4/7 libgomp,amdgcn] GCN libgomp port)

2019-12-03 Thread Julian Brown
On Tue, 3 Dec 2019 10:32:57 +0100 Thomas Schwinge wrote: > Hi! > > On 2019-12-02T14:50:42+, Julian Brown > wrote: > > On Mon, 2 Dec 2019 15:43:29 +0100 > > Thomas Schwinge wrote: > > > >> > --- a/libgomp/openacc.h > >> > +++ b/libgomp/openacc.h > >> > @@ -55,6 +55,7 @@ typedef enum acc_d

Which OpenACC 'acc_device_t' to use for AMD GPU offloading (was: [PATCH 4/7 libgomp,amdgcn] GCN libgomp port)

2019-12-03 Thread Thomas Schwinge
Hi! On 2019-12-02T14:50:42+, Julian Brown wrote: > On Mon, 2 Dec 2019 15:43:29 +0100 > Thomas Schwinge wrote: > >> > --- a/libgomp/openacc.h >> > +++ b/libgomp/openacc.h >> > @@ -55,6 +55,7 @@ typedef enum acc_device_t { >> >/* acc_device_host_nonshm = 3 removed. */ >> >acc_device_n