AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
84,346 Commits 1 Branch 0 Tags
8cd5c3cfe75114d2725b5fdf86e44d9ea4cb5b6b
Commit Graph

84346 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ian Romanick 8cd5c3cfe7 docs: Update GL3.txt for OpenGL 4.x on i965-ish hardware 
v2: Note that GL_KHR_blend_equation_advanced and
GL_KHR_blend_equation_advanced_coherent are done.

Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
 2016-08-26 15:03:14 -07:00
Nicholas Bishop d0a4c36dd6 docs: add links to clarify patch mailing section 
* Changed "Mesa mailing list" to "mesa-dev mailing list" to clarify
  which list patches should be sent to

* Added an explicit link to
  https://lists.freedesktop.org/mailman/listinfo/mesa-dev to show
  where to subscribe to the list

* Added a link to https://git-scm.com/docs/git-send-email to help new
  users of that command

v2: add signed-off-by

Signed-off-by: Nicholas Bishop <nicholasbishop@gmail.com>
Reviewed-by: Eric Engestrom <eric.engestrom@imgtec.com>
Reviewed-by: Chad Versace <chadversary@chromium.org>
 2016-08-26 14:54:26 -07:00
Brian Paul ea33df7b58 svga: minor whitespace, etc clean-ups in svga_pipe_misc.c 
Reviewed-by: Neha Bhende <bhenden@vmware.com>
 2016-08-26 14:20:19 -06:00
Brian Paul 8433b43337 svga: move some code in svga_propagate_surface() 
Move computation of zslice, layer inside the conditional where they're
used.

Reviewed-by: Neha Bhende <bhenden@vmware.com>
 2016-08-26 14:20:19 -06:00
Brian Paul 1a10b37ac3 svga: simplify surface propagation code in svga_set_framebuffer_state() 
Rewrite the comment too.

Reviewed-by: Neha Bhende <bhenden@vmware.com>
 2016-08-26 14:20:19 -06:00
Brian Paul bb7f094b37 svga: add some comments in the svga_surface struct 
Give more info about backing resources/surfaces.

Reviewed-by: Neha Bhende <bhenden@vmware.com>
 2016-08-26 14:20:19 -06:00
Brian Paul dcf63339e7 svga: use new svga_check_sampler_framebuffer_resource_collision() 
Reviewed-by: Neha Bhende <bhenden@vmware.com>
 2016-08-26 14:20:19 -06:00
Brian Paul ff500ed5a1 svga: add new svga_check_sampler_framebuffer_resource_collision() 
Reviewed-by: Neha Bhende <bhenden@vmware.com>
 2016-08-26 14:20:19 -06:00
Brian Paul d3d20d650d svga: remove assertions in svga_surface cast wrappers 
We don't do this for other cast wrappers.  And this will simplify some
code at call sites.

Reviewed-by: Neha Bhende <bhenden@vmware.com>
 2016-08-26 14:20:19 -06:00
Brian Paul c6e89fa215 svga: minor code simplification in svga_texture_transfer_unmap() 
Use the tex variable instead of using svga_texture() again.

Reviewed-by: Neha Bhende <bhenden@vmware.com>
 2016-08-26 14:20:19 -06:00
Brian Paul fe5a2704ec svga: reformat some expressions in svga_texture_transfer_map() 
Reviewed-by: Neha Bhende <bhenden@vmware.com>
 2016-08-26 14:20:19 -06:00
Brian Paul 10ef6ddcf9 svga: remove duplicated variable in svga_texture_transfer_map() 
tex was already declared at the function body scope.

Reviewed-by: Neha Bhende <bhenden@vmware.com>
 2016-08-26 14:20:19 -06:00
Brian Paul 09d2780b39 svga: move some assignments in svga_texture_transfer_map() 
Put near other assignments to the svga_transfer variable.

Reviewed-by: Neha Bhende <bhenden@vmware.com>
 2016-08-26 14:20:18 -06:00
Brian Paul 4a52512666 svga: minor simplifications in svga_texture_transfer_map() 
Use local vars instead of jumping through a pointer.

Reviewed-by: Neha Bhende <bhenden@vmware.com>
 2016-08-26 14:20:18 -06:00
Brian Paul 088dd8f45e svga: minor reformatting of svga_texture() cast wrapper 
Reviewed-by: Neha Bhende <bhenden@vmware.com>
 2016-08-26 14:20:18 -06:00
Brian Paul e206f67261 svga: rewrite svga_buffer() cast wrapper 
To make it symmetric with the svga_texture() cast wrapper.

Reviewed-by: Neha Bhende <bhenden@vmware.com>
 2016-08-26 14:20:18 -06:00
Brian Paul c72dcd9a71 svga: remove local variable in create_backed_surface_view() 
To simplify the code a bit.

Reviewed-by: Neha Bhende <bhenden@vmware.com>
 2016-08-26 14:20:18 -06:00
Kenneth Graunke bc13e5f42a docs: Add GL_KHR_blend_equation_advanced to relnotes. 2016-08-26 13:17:22 -07:00
Mario Kleiner 2cc880cba5 r600: increase performance for DRI PRIME offloading if 2nd GPU is Evergreen+ 
This is a direct port of Marek Olšáks patch
"radeonsi: increase performance for DRI PRIME
offloading if 2nd GPU is CIK or VI" to r600.

It uses SDMA for the detiling blit from renderoffload VRAM
to GTT, as SDMA is much faster for tiled->linear blits from
VRAM to GTT.

Testing on a dual Radeon HD-5770 setup reduced the time
for the render offload gpu to get its rendering into
system RAM from approximately 16 msecs for simple rendering
at 1920x1080 pixel 32 bpp to 5 msecs, a > 3x speedup!

This was measured using ftrace to trace the time the radeon kms
driver waited on the dmabuf fence of the renderoffload gpu to
complete.

All in all this brought the time for a flip down from 20 msecs
to 9 msecs, so the prime setup can display at full 60 fps instead
of barely 30 fps vsync'ed.

The current r600 implementation supports SDMA on Evergreen and
later, but not R600/R700 due to some bugs apparently present
in their SDMA implementation.

Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Cc: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Marek Olšák <marek.olsak@amd.com>
 2016-08-26 19:57:21 +02:00
Jordan Justen 7970238fcf docs: Update stencil texturing & ES 3.1 status for i965 Haswell 
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
 2016-08-26 10:09:22 -07:00
Jordan Justen 93f5eb7ae7 i965: Enable OpenGLES 3.1 for Haswell 
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
 2016-08-26 10:09:22 -07:00
Jordan Justen 116b6e12d4 i965: Enable ARB_texture_stencil8 for Haswell 
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
 2016-08-26 10:09:22 -07:00
Jordan Justen f20f616324 i965: Enable ARB_stencil_texturing for Haswell 
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
 2016-08-26 10:09:22 -07:00
Jordan Justen 751682434e i965/gen7: Use R8_UINT stencil copy when sampling the stencil texture 
v2:
 * Check gen <= 7, rather than gen == 7. (Ian)

Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
 2016-08-26 10:09:22 -07:00
Jordan Justen 8d78b096f8 i965/gen7: Copy stencil when sampling the stencil texture 
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
 2016-08-26 10:09:22 -07:00
Jordan Justen 7af51b8f03 i965: Add function to copy a stencil miptree to an R8_UINT miptree 
v2:
 * Cleanups suggested by Ian, Matt and Topi

Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
 2016-08-26 10:09:22 -07:00
Jordan Justen c8194dc737 i965: Track that the stencil data was updated when using Tex*Image 
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
 2016-08-26 10:09:22 -07:00
Jordan Justen 101b56bab2 i965: Track that the stencil data was updated when rendering 
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
 2016-08-26 10:09:22 -07:00
Jordan Justen 7bd87c1e6e i965: Track that the stencil data was updated when clearing 
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
 2016-08-26 10:09:22 -07:00
Jordan Justen 2a9c65a01d i965/gen7: Add R8_UINT stencil miptree copy for sampling 
For gen < 8, we can't sample from the stencil buffer, which is
required for the ARB_stencil_texturing extension. We'll make a copy of
the stencil data into a new texture that we can sample using the
R8_UINT surface type.

Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
 2016-08-26 10:09:22 -07:00
Jordan Justen 91627d1956 i965: Fix assert with multisampling and cubemaps 
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
 2016-08-26 10:09:22 -07:00
Jordan Justen b82bb98441 i965/hsw: Adjust uploading default color for stencil surfaces 
v2:
 * has_component (Ken); const bits_per_channel (Topi)

Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
 2016-08-26 10:09:22 -07:00
Jordan Justen 30fee52036 i965/hsw: Don't advertise more than 64 threads for compute shaders 
thread_width_max in the GPGPU walker command limits us to a maximum of
64 threads.

This fixes a crash on Haswell in the OpenGLES 3.1 conformance test
suite which tests the advertised limits of the max invocation counts.

Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
 2016-08-26 10:09:22 -07:00
Jordan Justen 861c9cbee3 main: Add MESA_VERBOSE=api support for glClearStencil 
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
 2016-08-26 10:09:22 -07:00
Jordan Justen 9a1f950bef main: Add MESA_VERBOSE=api support for glTexImage 
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
 2016-08-26 10:09:22 -07:00
Charmaine Lee 0035f7f136 svga: add guest statistic gathering interface 
This file was supposed to be added with the previous "svga: add guest
statistic gathering interface" patch but went MIA for some reason.

Reviewed-by: Brian Paul <brianp@vmware.com>
 2016-08-26 08:04:02 -06:00
Marek Olšák 49c798e902 radeonsi: disable CE on SI + AMDGPU 
Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
 2016-08-26 15:50:10 +02:00
Marek Olšák 281f1a5980 winsys/amdgpu: disable IB chaining on SI 
Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
 2016-08-26 15:50:10 +02:00
Marek Olšák a6869e7c06 winsys/amdgpu: finish up SI addrlib integration 
Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net>
 2016-08-26 15:50:10 +02:00
Ronie Salgado 97b55243fb winsys/amdgpu: initial SI support 
Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Edward O'Callaghan <funfunctor@folklore1984.net>
 2016-08-26 15:50:10 +02:00
Marek Olšák 971ef7518f gallium/radeon: add a driver query for AMDGPU_INFO_NUM_EVICTIONS 
If the kernel driver doesn't support it, it returns 0.

Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
 2016-08-26 15:50:10 +02:00
Marek Olšák 7172906c0c radeonsi: fix printing shaders and states on a VM fault 
This was missed while rewriting the PIPE_DUMP flags.

Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
 2016-08-26 15:50:10 +02:00
Marek Olšák 5ee3cac138 radeonsi: increase performance for DRI PRIME offloading if 2nd GPU is CIK or VI 
SDMA is much faster for tiled->linear blits from VRAM to GTT.
I have Bonaire in my second PCIe slot.

$ glxinfo | grep OpenGL.renderer
OpenGL renderer string: Gallium 0.4 on AMD TONGA ...

$ DRI_PRIME=1 glxinfo | grep OpenGL.renderer
OpenGL renderer string: Gallium 0.4 on AMD BONAIRE ...

Without SDMA:
$ DRI_PRIME=1 glxgears
8796 frames in 5.0 seconds = 1759.074 FPS
8899 frames in 5.0 seconds = 1779.672 FPS

With SDMA:
$ DRI_PRIME=1 glxgears
12765 frames in 5.0 seconds = 2552.788 FPS
12888 frames in 5.0 seconds = 2577.495 FPS

The 1st GPU is irrelevant. The improvement should be much lower at 60 fps,
but definitely measurable.

SI will get this once we add SDMA blit support for it.

Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
 2016-08-26 15:50:10 +02:00
Marek Olšák 0241d8300f radeonsi: enable SDMA on CIK 
It passes R600_DEBUG=testdma on Bonaire/radeon.

Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
 2016-08-26 15:50:10 +02:00
Marek Olšák bcfd49e511 gallium/radeon: increase priority for shader binaries 
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
 2016-08-26 15:50:10 +02:00
Marek Olšák c3f716fe67 gallium/radeon: merge USER_SHADER and INTERNAL_SHADER priority flags 
there's no reason to separate these

Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
 2016-08-26 15:50:10 +02:00
Miklós Máté b9ac72b511 vbo: set draw_id 
Fixes conditional jump depending on uninitialized value
in si_state_draw.c:593

Cc: <mesa-stable@lists.freedesktop.org>
Signed-off-by: Miklós Máté <mtmkls@gmail.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
 2016-08-26 07:34:22 -06:00
Neha Bhende 10f6e08549 svga: fix regression related to srgb 
This regression is caused because of commit 3190c7ee97
Regression caused by following OpenGL 4.4 spec rules relates to
GL_FRAMEBUFFER_SRGB in Mesa.

Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Charmaine Lee <charmainel@vmware.com>
 2016-08-26 06:19:52 -06:00
Neha Bhende 3b7341d547 svga: use local variable blit instead of pointer 
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Charmaine Lee <charmainel@vmware.com>
 2016-08-26 06:19:52 -06:00
Brian Paul b09e4ab13c svga: s/INDEX_0D/INDEX_IMMEDIATE32/ 
Both are zero, but the later is the right token.
 2016-08-26 06:19:52 -06:00