search for: tgsi_file_memori

Hi, Here are patches which implement the support for OpenCL kernel input parameters we discussed. They also add the tgsi parsing bits for adding support for global / local mem, but no implementation yet. Regards, Hans

When support for decl.Atomic and .Shared was added, tgsi_build_declaration was not updated to propagate these properly. Signed-off-by: Hans de Goede <hdegoede at redhat.com> Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu> --- Changes in v2: -Add Reviewed-by: Ilia Mirkin <imirkin at alum.mit.edu> --- src/gallium/auxiliary/tgsi/tgsi_build.c | 6 ++++++ 1 file changed, 6

This little "hack" fixes the use of OpenCL global memory buffers with nouveau, but clearly the #if 0 is not a solution as it breaks buffers with GLSL. The reason I'm posting this as an RFC patch is to discuss how to solve this properly, 2 solutions come to mind: 1) Use separate nv50_ir::FILE_MEMORY_xxx values for buffers versus TGSI_FILE_MEMORY with TGSI_MEMORY_TYPE_GLOBAL,

On Thu, Mar 10, 2016 at 9:14 AM, Hans de Goede <hdegoede at redhat.com> wrote: > Extend the MEMORY file support to differentiate between global, local > and shared memory, as well as "input" memory. > > "MEMORY[x], INPUT" is intended to access OpenCL kernel parameters, a > special memory type is added for this, since the actual storage of these > (e.g.

On 03/16/2016 10:23 AM, Hans de Goede wrote: > Commit c3083c7082 ("nv50/ir: add support for BUFFER accesses") disabled / > commented out some of the old resource handling code, but not all of it. > > Effectively all of it is dead already, if we ever enter the old code > paths in handeLOAD / handleSTORE / handleATOM we will get an exception > due to trying to access the

Hi, On 14-03-16 16:05, Ilia Mirkin wrote: > There's a less hacky and more hacky way forward. The more hacky solution is > to set file index to -1 or something and then not do the lowering when you > see that. > > The less hacky solution is the one you proposed as #1 - introduce a new > file for "buffer" memory and lower it to the global file by adding a base >

Extend the MEMORY file support to differentiate between global, local and shared memory, as well as "input" memory. "MEMORY[x], INPUT" is intended to access OpenCL kernel parameters, a special memory type is added for this, since the actual storage of these (e.g. UBO-s) may differ per implementation. The uploading of kernel parameters is handled by launch_grid,

Extend the MEMORY file support to differentiate between global, private and shared memory, as well as "input" memory. "MEMORY[x], INPUT" is intended to access OpenCL kernel parameters, a special memory type is added for this, since the actual storage of these (e.g. UBO-s) may differ per implementation. The uploading of kernel parameters is handled by launch_grid,

Hi, On 10-03-16 16:35, Aaron Watry wrote: > On Thu, Mar 10, 2016 at 9:14 AM, Hans de Goede <hdegoede at redhat.com> wrote: > >> Extend the MEMORY file support to differentiate between global, local >> and shared memory, as well as "input" memory. >> >> "MEMORY[x], INPUT" is intended to access OpenCL kernel parameters, a >> special

Hi, On 14-03-16 16:41, Samuel Pitoiset wrote: > > > On 03/14/2016 04:28 PM, Hans de Goede wrote: >> Hi, >> >> On 14-03-16 16:05, Ilia Mirkin wrote: >>> There's a less hacky and more hacky way forward. The more hacky >>> solution is >>> to set file index to -1 or something and then not do the lowering when >>> you >>> see

On Thu, Mar 10, 2016 at 10:14 AM, Hans de Goede <hdegoede at redhat.com> wrote: > Add support for clover / OpenCL kernel input parameters. > > Signed-off-by: Hans de Goede <hdegoede at redhat.com> > --- > .../drivers/nouveau/codegen/nv50_ir_from_tgsi.cpp | 18 +++++++++++++++--- > 1 file changed, 15 insertions(+), 3 deletions(-) > > diff --git

Commit c3083c7082 ("nv50/ir: add support for BUFFER accesses") disabled / commented out some of the old resource handling code, but not all of it. Effectively all of it is dead already, if we ever enter the old code paths in handeLOAD / handleSTORE / handleATOM we will get an exception due to trying to access the now always zero-sized resources vector. Make non buffer / memory file

On Thu, Mar 10, 2016 at 10:27 AM, Samuel Pitoiset <samuel.pitoiset at gmail.com> wrote: > > > On 03/10/2016 04:23 PM, Ilia Mirkin wrote: >> >> On Thu, Mar 10, 2016 at 10:14 AM, Hans de Goede <hdegoede at redhat.com> >> wrote: >>> >>> Add support for clover / OpenCL kernel input parameters. >>> >>> Signed-off-by: Hans de

There's a less hacky and more hacky way forward. The more hacky solution is to set file index to -1 or something and then not do the lowering when you see that. The less hacky solution is the one you proposed as #1 - introduce a new file for "buffer" memory and lower it to the global file by adding a base offset. Right now the meaning of global is overloaded - before lowering it

Hi, On 16-03-16 11:45, Samuel Pitoiset wrote: > > > On 03/16/2016 10:23 AM, Hans de Goede wrote: >> Commit c3083c7082 ("nv50/ir: add support for BUFFER accesses") disabled / >> commented out some of the old resource handling code, but not all of it. >> >> Effectively all of it is dead already, if we ever enter the old code >> paths in handeLOAD /

On 03/14/2016 04:28 PM, Hans de Goede wrote: > Hi, > > On 14-03-16 16:05, Ilia Mirkin wrote: >> There's a less hacky and more hacky way forward. The more hacky >> solution is >> to set file index to -1 or something and then not do the lowering when >> you >> see that. >> >> The less hacky solution is the one you proposed as #1 - introduce a

On 03/14/2016 08:50 PM, Hans de Goede wrote: > Hi, > > On 14-03-16 16:41, Samuel Pitoiset wrote: >> >> >> On 03/14/2016 04:28 PM, Hans de Goede wrote: >>> Hi, >>> >>> On 14-03-16 16:05, Ilia Mirkin wrote: >>>> There's a less hacky and more hacky way forward. The more hacky >>>> solution is >>>> to set

Could you please get rid of the cosmetic changes (eg. the switch ones)? Because this doesn't really improve readability and in my opinion these changes should be eventually done in a separate patch. Other than that, this patch is : Reviewed-by: Samuel Pitoiset <samuel.pitoiset at gmail.com> Yes, this probably won't work as is for atomic operations but the lowering pass is

Commit c3083c7082 ("nv50/ir: add support for BUFFER accesses") disabled / commented out some of the old resource handling code, but not all of it. Effectively all of it is dead already, if we ever enter the old code paths in handeLOAD / handleSTORE / handleATOM we will get an exception due to trying to access the now always zero-sized resources vector. Disable all the dead code.

Add support for OpenCL global memory buffers, note this has only been tested with regular load and stores and likely needs more work for e.g. atomic ops. Signed-off-by: Hans de Goede <hdegoede at redhat.com> --- src/gallium/drivers/nouveau/codegen/nv50_ir.h | 1 + .../drivers/nouveau/codegen/nv50_ir_emit_gk110.cpp | 31 +++++++++++++++++-----