Commits · a2a1a5805fd617e7f3cc8be44dd79b50da07ebb9 · Rafael Antognolli / mesa

21 Jul, 2015 2 commits

gallium: replace INLINE with inline · a2a1a580

Ilia Mirkin authored Jul 20, 2015



Generated by running:
git grep -l INLINE src/gallium/ | xargs sed -i 's/\bINLINE\b/inline/g'
git grep -l INLINE src/mesa/state_tracker/ | xargs sed -i 's/\bINLINE\b/inline/g'
git checkout src/gallium/state_trackers/clover/Doxyfile

and manual edits to
src/gallium/include/pipe/p_compiler.h
src/gallium/README.portability

to remove mentions of the inline define.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Acked-by: Marek Olšák <marek.olsak@amd.com>

a2a1a580

nvc0: force cache flush when binding a new ubo · 958b5c31

Samuel Pitoiset authored Jul 21, 2015



This fixes the following piglit test:
  ext_transform_feedback-immediate-reuse-uniform-buffer
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>

958b5c31

20 Jul, 2015 2 commits

nouveau: use bool instead of boolean · cd0dec0d

Samuel Pitoiset authored Jul 20, 2015


Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Ilia Mirkin <imirkin@alum.mit.edu>

cd0dec0d

nvc0: add a missing parameter to nvc0_set_shader_images() · 5b7dd4d4

Samuel Pitoiset authored Jul 16, 2015

This fixes a compilation warning introduced in commit 05a12c53


(gallium: add interface for writable shader images).

While we are at it, fix indentation and rename parameters according to
the gallium interface.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>

5b7dd4d4

16 Jul, 2015 2 commits
- gallium: add interface for writable shader images · 05a12c53
  Marek Olšák authored Jul 05, 2015
```
PIPE_CAPs will be added some other time.
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
```
  05a12c53
- gallium: add PIPE_CAP_MAX_SHADER_PATCH_VARYINGS · 26222932
  Marek Olšák authored Jun 12, 2015
```
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
```
  26222932
11 Jul, 2015 1 commit

nv50, nvc0: enable at least one color RT if alphatest is enabled · 1bfa25e8

Ilia Mirkin authored Jul 10, 2015



Fixes the following piglits:
  fbo-alphatest-nocolor
  fbo-alphatest-nocolor-ff
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: mesa-stable@lists.freedesktop.org

1bfa25e8

08 Jul, 2015 2 commits

nvc0: fix wrong use of BLIT_SRC_Y_INT for 2D texture copy · ec151e2f

Samuel Pitoiset authored Jul 06, 2015



According to nv50, this should be src->ms_y instead of src->ms_x. This
code is here since 2012, so it's probably a typo error which has never
been detected since a long time. I didn't do a full piglit run to check
if it fixes some other weird issues.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>

ec151e2f

nvc0: turn sample counts off during blit · 38c2ec5f

Ilia Mirkin authored Jul 07, 2015



Fixes the following piglits:
  occlusion_query_meta_fragments
  occlusion_query_meta_no_fragments
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: mesa-stable@lists.freedesktop.org

38c2ec5f

02 Jul, 2015 1 commit

nvc0: tune PREFER_BLIT_BASED_TEXTURE_TRANSFER capability · 1087c566

Alexandre Courbot authored Jul 02, 2015 and

Ilia Mirkin committed Jul 01, 2015



Prefer blit-based texture transfers only if the chip has dedicated VRAM
since it would translate to a copy into the same memory on shared-memory
chips.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Reported-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>

1087c566

01 Jul, 2015 1 commit

nvc0: create screen fence objects with coherent attribute · e212a80d

Alexandre Courbot authored Jun 30, 2015 and

Martin Roukala committed Jul 02, 2015



This is required on non-coherent architectures to ensure the value of
the fence is correct at all times. Failure to do this results in the
display freezing for a few seconds every now and then on Tegra.

The NOUVEAU_BO_COHERENT is a no-op for coherent architectures, so behavior
on x86 should not be affected by this patch.

Also bump the required libdrm version to 2.4.62, which introduced this
flag.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Reviewed-by: Martin Peres <martin.peres@free.fr>

e212a80d

29 Jun, 2015 1 commit

gallium: add PIPE_COMPUTE_CAP_SUBGROUP_SIZE · 249a9df7

Grigori Goronzy authored May 28, 2015



We need this to implement OpenCL's
CL_KERNEL_PREFERRED_WORK_GROUP_SIZE_MULTIPLE.
Reviewed-by: Francisco Jerez <currojerez@riseup.net>

249a9df7

23 Jun, 2015 2 commits

nv50,nvc0: make sure to pushbuf_refn before putting bo into pushbuf_data · 78d58e64

Ilia Mirkin authored Jun 21, 2015



Without first running the bo through pushbuf_refn, the nouveau drm
library will have uninitialized structures regarding this bo, and will
insert incorrect data.

This fixes supertuxkart 0.9 crash on start (where it ends up doing a lot
of indirect draws).
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: "10.5 10.6" <mesa-stable@lists.freedesktop.org>

78d58e64

nvc0: always put all tfb bufs into bufctx · 9fcbf515

Ilia Mirkin authored Jun 21, 2015



Since we clear the TFB bufctx binding point above, we need to put all of
the active tfb's back in, even if they haven't changed since last time.
Otherwise the tfb may get moved into sysmem and the underlying mapping
will generate write errors.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: "10.5 10.6" <mesa-stable@lists.freedesktop.org>

9fcbf515

22 Jun, 2015 1 commit

nvc0: use NV_VRAM_DOMAIN() macro · da8300cb

Alexandre Courbot authored Oct 17, 2014 and

Ilia Mirkin committed Jun 22, 2015



Use the newly-introduced NV_VRAM_DOMAIN() macro to support alternative
VRAM domains for chips that do not have dedicated video memory.
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Martin Peres <martin.peres@free.fr>

da8300cb

15 Jun, 2015 1 commit

nv50,nvc0: clamp uniform size to 64k · 8b243886

Ilia Mirkin authored Jun 15, 2015



The state tracker will pass through requests from buggy applications
which will have the buffer size larger than the max allowed (64k). Clamp
the size to 64k so that we don't get errors when uploading the constbuf
data.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: "10.5 10.6" <mesa-stable@lists.freedesktop.org>

8b243886

05 Jun, 2015 1 commit

tgsi/ureg: don't emit in/out arrays if drivers don't support ranged declarations · b6ebe7ea

Marek Olšák authored May 25, 2015

Softpipe, llvmpipe, r300g, and radeonsi pass tests. Other drivers need testing.

Freedreno and nv30 are definitely broken. Other drivers seem to be alright.

b6ebe7ea

23 May, 2015 1 commit

nvc0: a geometry shader can have up to 1024 vertices output · 921917c8

Ilia Mirkin authored May 23, 2015



The 1024 is already reported everywhere, not sure where this 0x1ff came
from.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: "10.5 10.6" <mesa-stable@lists.freedesktop.org>

921917c8

14 May, 2015 2 commits

nvc0: remove unused nv50_tsc_wrap_mode() function · 175cbb44
Samuel Pitoiset authored May 12, 2015 and Ilia Mirkin committed May 14, 2015
```
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
```
175cbb44

nvc0: do not expose MP counters for nvf0 (GK110+) · 48c84a36

Samuel Pitoiset authored May 11, 2015 and

Ilia Mirkin committed May 14, 2015



This fixes a crash when trying to monitor MP counters because compute
support is not implemented for nvf0.
Reported-by: Ilia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>

48c84a36

12 May, 2015 2 commits

nvc0: switch mechanism for shader eviction to be a while loop · d06ce2f1

Ilia Mirkin authored May 10, 2015

This aligns it to work similarly to nv50. However there's no library
code there, so the whole thing can be freed. Here we end up with an
allocated node that's not attached to a specific program.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=86792

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: mesa-stable@lists.freedesktop.org

d06ce2f1

gallium: add PIPE_CAP_DEVICE_RESET_STATUS_QUERY · 79ffc08a
Marek Olšák authored Apr 29, 2015
```
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
```
79ffc08a

09 May, 2015 2 commits

nvc0: reset the instanced elements state when doing blit using 3d engine · 78922104

Ilia Mirkin authored May 09, 2015

Since we update num_vtxelts here, we could otherwise end up with stale
instancing information in the upper bits which wouldn't otherwise get
reset. (Also we run the risk of the previous draw having set the first
element as instanced.)

This appears as one of the causes for the test pointed out in fdo#90363
to fail on nvc0.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=90363

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: mesa-stable@lists.freedesktop.org

78922104

nvc0: keep track of PGRAPH state in nvc0_screen · e9b1ea29

Ilia Mirkin authored May 08, 2015



See identical commit for nv50. Destroying the current context and then
creating a new one or switching to another existing context would cause
the "current" state to not be properly initialized, so we save it off in
the screen.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: mesa-stable@lists.freedesktop.org

e9b1ea29

05 May, 2015 6 commits

nvc0: all queries use an unsigned 64-bits integer by default · cea910bc

Samuel Pitoiset authored Jul 08, 2014 and

Martin Roukala committed May 06, 2015


Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Martin Peres <martin.peres@free.fr>

cea910bc

nvc0: make begin_query return false when all MP counters are used · 35a9286b

Samuel Pitoiset authored Jul 05, 2014 and

Martin Roukala committed May 06, 2015


Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Martin Peres <martin.peres@free.fr>

35a9286b

nvc0: define driver-specific query groups · ed7d3886

Samuel Pitoiset authored Jul 04, 2014 and

Martin Roukala committed May 06, 2015



This patch defines "Driver statistics" and "MP counters" groups, but
only the latter will be exposed through GL_AMD_performance_monitor.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Martin Peres <martin.peres@free.fr>

ed7d3886

gallium: make pipe_context::begin_query return a boolean · 96f164f6

Samuel Pitoiset authored Jul 05, 2014 and

Martin Roukala committed May 06, 2015



GL_AMD_performance_monitor must return an error when a monitoring
session cannot be started.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Martin Peres <martin.peres@free.fr>

96f164f6

gallium: replace pipe_driver_query_info::max_value by a union · 546ec980

Samuel Pitoiset authored Jul 07, 2014 and

Martin Roukala committed May 06, 2015



This allows queries to return different numeric types.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset at gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Martin Peres <martin.peres@free.fr>

546ec980

gallium: add new fields to pipe_driver_query_info · b620829b

Samuel Pitoiset authored Jul 04, 2014 and

Martin Roukala committed May 06, 2015



According to the spec of GL_AMD_performance_monitor, valid type values
returned are UNSIGNED_INT, UNSIGNED_INT64_AMD, PERCENTAGE_AMD, FLOAT.
This also introduces the new field group_id in order to categorize
queries into groups.

v2: add PIPE_DRIVER_QUERY_TYPE_BYTES

v3: fix incorrect query type for radeon and svga drivers
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Martin Peres <martin.peres@free.fr>

b620829b

28 Apr, 2015 1 commit
- nvc0: expose GLSL version 410 · e312a699
  Ilia Mirkin authored Apr 26, 2015
```
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
```
  e312a699
07 Apr, 2015 1 commit

nv50,nvc0: limit the y-tiling of 3d textures to the first level's tiling · ae720c66

Ilia Mirkin authored Apr 05, 2015



We limit y-tiling to 0x20 when depth is involved. However the function is
run for each miplevel, and the hardware expects miplevel 0 to have the
highest tiling settings. Perform the y-tiling limit on all levels of a
3d texture, not just the ones that have depth.

Fixes:
  texelFetch fs sampler3D 98x129x1-98x129x9
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Tested-by: Nick Tenney <nick.tenney@gmail.com> # GT216
Cc: "10.4 10.5" <mesa-stable@lists.freedesktop.org>

ae720c66

16 Mar, 2015 1 commit

gallium: add FMA and DFMA opcodes (v3) · 216543ea

Marek Olšák authored Feb 28, 2015



Needed by ARB_gpu_shader5.

v2: select DMAD for FMA with double precision
v3: add and select DFMA
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>

216543ea

10 Mar, 2015 1 commit

nvc0: fix wrong max value for driver queries · e5cd42ed

Samuel Pitoiset authored Mar 08, 2015 and

Ilia Mirkin committed Mar 09, 2015



The maximum value of a Gallium HUD's panel is automatically adjusted
when the current value is greater than the max. If we set the
pipe_query_driver_info::max_value to UINT64_MAX, the maximum value is
never adjusted and this results in a flat line instead of a pretty curve
which is correctly scaled.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>

e5cd42ed

21 Feb, 2015 1 commit
- nvc0: enable double support · f8e4792b
  Ilia Mirkin authored Jul 23, 2014
```
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
```
  f8e4792b
20 Feb, 2015 2 commits

gallium: add shader cap for dldexp/dfracexp support · 924ee3f4

Ilia Mirkin authored Jul 25, 2014


Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Dave Airlie <airlied@redhat.com>

924ee3f4

gallium: add a cap to enable double rounding opcodes · 899d779c

Ilia Mirkin authored Jul 25, 2014


Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Dave Airlie <airlied@redhat.com>

899d779c

17 Feb, 2015 1 commit

gallium: add interface and state tracker support for GL_AMD_pinned_memory · 8b587ee7

Marek Olšák authored Feb 10, 2015



v2: add alignment restrictions to docs, fix indentation in headers
Reviewed-by: Christian König <christian.koenig@amd.com>

8b587ee7

14 Feb, 2015 2 commits

nvc0: allow holes in xfb target lists · 854eb06b

Ilia Mirkin authored Feb 14, 2015



Tested with a modified xfb-streams test which outputs to streams 0, 2,
and 3.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: "10.4 10.5" <mesa-stable@lists.freedesktop.org>

854eb06b

nvc0: bail out of 2d blits with non-A8_UNORM alpha formats · 68e4f3f5

Ilia Mirkin authored Feb 13, 2015



This fixes the teximage-colors uploads with GL_ALPHA format and
non-GL_UNSIGNED_BYTE type.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: "10.4 10.5" <mesa-stable@lists.freedesktop.org>

68e4f3f5