Re: Default compute dimensions (runtime)

ral 'dg-bogus' with XFAIL that you're proposing to add? We should think about that some more. So, the following is relevant right now: > --- a/gcc/doc/invoke.texi > +++ b/gcc/doc/invoke.texi > @@ -2167,8 +2167,12 @@ have support for @option{-pthread}. > @cindex OpenACC accelerator pr

Re: Default compute dimensions

w{@uref{http > implies @option{-pthread}, and thus is only supported on targets that > have support for @option{-pthread}. > > -[...] > +@item -fopenacc-dim=@var{geom} > +@opindex fopenacc-dim > +@cindex OpenACC accelerator programming > +Specify default compute dimensions [.

Re: Default compute dimensions (runtime)

ault-compile.c: New. commit a918a8739ae7652250c978b0ececa181a587b0c0 Author: Julian Brown Date: Fri Oct 5 11:11:47 2018 -0700 OpenACC default compute dimensions 20xx-xx-xx Nathan Sidwell Tom de Vries Thomas Schwinge Julian Brown gcc/ * d

[gomp4] runtime default compute dimensions

This patch interrogates the target device to determine default gemotry at runtime. This has the greatest difference on gang partitioning, where there's a noticeable sawtooth in the relationship between number of gangs and execution time. Picking the number of gangs as an exact multiple of

Default compute dimensions (runtime)

e.texi === --- gcc/doc/invoke.texi (revision 233084) +++ gcc/doc/invoke.texi (working copy) @@ -1969,7 +1969,12 @@ have support for @option{-pthread}. Specify default compute dimensions for parallel offload regions that do not explicitly specify. The @var{geom} value is a

Re: Default compute dimensions (runtime)

Hello, On Wed, 3 Feb 2016, Nathan Sidwell wrote: > 1) extend the -fopenacc-dim=X:Y:Z syntax to allow '-' indicating a runtime > choice. (0 also indicates that, but I thought best to have an explicit syntax > as well). Does it work when the user specifies one of the dimensions, so that

Re: Default compute dimensions (runtime)

On 02/03/16 11:10, Alexander Monakov wrote: Hello, On Wed, 3 Feb 2016, Nathan Sidwell wrote: 1) extend the -fopenacc-dim=X:Y:Z syntax to allow '-' indicating a runtime choice. (0 also indicates that, but I thought best to have an explicit syntax as well). Does it work when the user

Re: Default compute dimensions (runtime)

On Wed, 3 Feb 2016, Nathan Sidwell wrote: > You can only override at runtime those dimensions that you said you'd override > at runtime when you compiled your program. Ah, I see. That's not obvious to me, so perhaps added documentation can be expanded to explain that? (I now see that the plugin

Re: Default compute dimensions

On 02/01/16 13:42, Jakub Jelinek wrote: Your patch broke bootstrap on ILP32 hosts, I'm testing following fix. Supporting unsigned values from 0x8000U to 0xU only on LP64 hosts and not on ILP64 hosts sounds really weird, I think it is better to only support 1 to 0x7fffU. yes, I

Re: Default compute dimensions

On 01/29/16 10:18, Jakub Jelinek wrote: On Thu, Jan 28, 2016 at 10:38:51AM -0500, Nathan Sidwell wrote: This patch adds default compute dimension handling. Users rarely specify compute dimensions, expecting the toolchain to DTRT. More savvy users would like to specify global defaults. This

Re: Default compute dimensions

On 02/01/16 10:32, Jakub Jelinek wrote: On Mon, Feb 01, 2016 at 09:15:05AM -0500, Nathan Sidwell wrote: On 01/29/16 10:18, Jakub Jelinek wrote: On Thu, Jan 28, 2016 at 10:38:51AM -0500, Nathan Sidwell wrote: This patch adds default compute dimension handling. Users rarely specify compute

Re: Default compute dimensions

On Mon, Feb 01, 2016 at 11:15:13AM -0500, Nathan Sidwell wrote: > On 02/01/16 10:32, Jakub Jelinek wrote: > >On Mon, Feb 01, 2016 at 09:15:05AM -0500, Nathan Sidwell wrote: > >>On 01/29/16 10:18, Jakub Jelinek wrote: > >>>On Thu, Jan 28, 2016 at 10:38:51AM -0500, Nathan Sidwell wrote: > This

Re: Default compute dimensions

On Mon, Feb 1, 2016 at 8:15 AM, Nathan Sidwell wrote: > On 02/01/16 10:32, Jakub Jelinek wrote: >> >> On Mon, Feb 01, 2016 at 09:15:05AM -0500, Nathan Sidwell wrote: >>> >>> On 01/29/16 10:18, Jakub Jelinek wrote: On Thu, Jan 28, 2016 at 10:38:51AM -0500, Nathan Sidwell

Re: Default compute dimensions

On Mon, Feb 01, 2016 at 09:15:05AM -0500, Nathan Sidwell wrote: > On 01/29/16 10:18, Jakub Jelinek wrote: > >On Thu, Jan 28, 2016 at 10:38:51AM -0500, Nathan Sidwell wrote: > >>This patch adds default compute dimension handling. Users rarely specify > >>compute dimensions, expecting the toolchain

Re: Default compute dimensions

On Thu, Jan 28, 2016 at 10:38:51AM -0500, Nathan Sidwell wrote: > This patch adds default compute dimension handling. Users rarely specify > compute dimensions, expecting the toolchain to DTRT. More savvy users would > like to specify global defaults. This patch permits both. Isn't it better

Re: Default compute dimensions

On 01/29/16 10:18, Jakub Jelinek wrote: On Thu, Jan 28, 2016 at 10:38:51AM -0500, Nathan Sidwell wrote: This patch adds default compute dimension handling. Users rarely specify compute dimensions, expecting the toolchain to DTRT. More savvy users would like to specify global defaults. This

Default compute dimensions

to -change in future versions of GCC. See -@w{@uref{https://gcc.gnu.org/wiki/OpenACC}} for more information. +@item -fopenacc-dim=@var{geom} +@opindex fopenacc-dim +@cindex OpenACC accelerator programming +Specify default compute dimensions for parallel offload regions that do +not explicitly spec