Christian König [Thu, 9 Dec 2010 23:29:59 +0000 (00:29 +0100)]
[g3dvl] move frame predition handling vom fragment into vertex shader
Christian König [Thu, 9 Dec 2010 23:13:32 +0000 (00:13 +0100)]
[g3dvl] avoid some ELSE blocks
Christian König [Thu, 9 Dec 2010 21:34:43 +0000 (22:34 +0100)]
[g3dvl] try a different buffer aproach
Christian König [Thu, 9 Dec 2010 21:28:31 +0000 (22:28 +0100)]
[g3dvl] fix buffer handling in mc code
Christian König [Thu, 9 Dec 2010 21:27:03 +0000 (22:27 +0100)]
[g3dvl] fix idct matrix upload
Christian König [Wed, 8 Dec 2010 22:37:57 +0000 (23:37 +0100)]
[g3dvl] split mc code into state and buffer
Christian König [Wed, 8 Dec 2010 21:35:30 +0000 (22:35 +0100)]
[g3dvl] move buffer mapping/unmapping out of flush
Christian König [Wed, 8 Dec 2010 20:28:38 +0000 (21:28 +0100)]
[g3dvl] replace IF THEN ELSE with CMP statement
Christian König [Wed, 8 Dec 2010 19:48:34 +0000 (20:48 +0100)]
[g3dvl] remove shadow buffering of vertex buffers
Christian König [Wed, 8 Dec 2010 18:41:01 +0000 (19:41 +0100)]
[g3dvl] remove mb type handler structure
Christian König [Wed, 8 Dec 2010 18:18:55 +0000 (19:18 +0100)]
[g3dvl] move macro block type handling into shaders part 3
Christian König [Wed, 8 Dec 2010 17:42:48 +0000 (18:42 +0100)]
[g3dvl] moving macroblock type handling into shaders part 2
Christian König [Wed, 8 Dec 2010 17:26:58 +0000 (18:26 +0100)]
[g3dvl] start moving macroblock type handling into shaders
Christian König [Wed, 8 Dec 2010 15:11:29 +0000 (16:11 +0100)]
[g3dvl] allways use all motion vectors
reprogramming the vertex buffers takes more time than pumping
all motion vectors through the vertex shader
Christian König [Wed, 8 Dec 2010 13:50:28 +0000 (14:50 +0100)]
[g3dvl] split empty block handling
Empty block handling is split between vertex shader (x-axis)
and fragment shader (y-axis).
Christian König [Wed, 8 Dec 2010 01:12:24 +0000 (02:12 +0100)]
[g3dvl] split idct code into state and buffers
Christian König [Tue, 7 Dec 2010 20:23:14 +0000 (21:23 +0100)]
[g3dvl] use buffer width instead of texture size or vs constants
Christian König [Tue, 7 Dec 2010 19:13:37 +0000 (20:13 +0100)]
[g3dvl] move vertex buffer handling into vl_vertex_buffer.c
Christian König [Mon, 6 Dec 2010 23:29:02 +0000 (00:29 +0100)]
[g3dvl] rework pot buffer handling and flushing
Christian König [Sun, 5 Dec 2010 21:30:38 +0000 (22:30 +0100)]
[g3dvl] move mapping/unmapping of buffers one layer up
Christian König [Sun, 5 Dec 2010 16:57:52 +0000 (17:57 +0100)]
[g3dvl] move vertex handling into vl_vb object
Christian König [Sun, 5 Dec 2010 15:46:10 +0000 (16:46 +0100)]
[g3dvl] cleanup empty block handling
doing empty block handling in the mc code is indeed faster
Christian König [Fri, 3 Dec 2010 17:57:23 +0000 (18:57 +0100)]
move empty block handling back into mc for testing
Christian König [Wed, 1 Dec 2010 17:47:11 +0000 (18:47 +0100)]
add rasterizer state
Christian König [Tue, 30 Nov 2010 20:15:47 +0000 (21:15 +0100)]
use CMP also for referenz frame fetch
Christian König [Tue, 30 Nov 2010 19:41:26 +0000 (20:41 +0100)]
cleanup and use CMP instead of IF ELSE ENDIF
Christian König [Mon, 29 Nov 2010 23:14:59 +0000 (00:14 +0100)]
move to four component calculation for idct code
Christian König [Mon, 29 Nov 2010 00:02:37 +0000 (01:02 +0100)]
copy only mv really needed to vb
Christian König [Sun, 28 Nov 2010 23:09:22 +0000 (00:09 +0100)]
use vertex buffer also for mc code
Christian König [Sun, 28 Nov 2010 20:09:53 +0000 (21:09 +0100)]
give each vertex element its own buffer
Christian König [Sun, 28 Nov 2010 19:20:47 +0000 (20:20 +0100)]
use vl_vb_upload_quads also for mc
Christian König [Sun, 28 Nov 2010 19:08:40 +0000 (20:08 +0100)]
move vertex elemt states into mb type handlers
Christian König [Sun, 28 Nov 2010 17:49:57 +0000 (18:49 +0100)]
move macroblock type handling into its own structure
Christian König [Sun, 28 Nov 2010 13:48:31 +0000 (14:48 +0100)]
use a shadow buffer for vertex data to optimize memory access
Christian König [Sun, 28 Nov 2010 11:23:36 +0000 (12:23 +0100)]
make nr of render targets configureable for testing
Christian König [Sun, 28 Nov 2010 00:21:41 +0000 (01:21 +0100)]
[g3dvl] join empty blocks to get larger slices
Christian König [Sat, 27 Nov 2010 17:20:38 +0000 (18:20 +0100)]
[g3dvl] use 8 zslices for idct
Christian König [Sat, 27 Nov 2010 13:08:15 +0000 (14:08 +0100)]
[g3dvl] some more bugfixing
Christian König [Sat, 27 Nov 2010 13:01:01 +0000 (14:01 +0100)]
[g3dvl] idividual vs for each stage and a bunch of bugsfixes
Christian König [Sat, 27 Nov 2010 10:24:24 +0000 (11:24 +0100)]
[g3dvl] give idct stage 1 & 2 its own sb_state and viewport
Christian König [Fri, 26 Nov 2010 20:50:14 +0000 (21:50 +0100)]
[g3dvl] use four component fetch also for idct source
Christian König [Fri, 26 Nov 2010 20:44:22 +0000 (21:44 +0100)]
r600g: disable hardware blit for stream texture
Christian König [Fri, 26 Nov 2010 19:25:00 +0000 (20:25 +0100)]
[g3dvl] split matrix mul into seperate functions
Christian König [Fri, 26 Nov 2010 18:14:55 +0000 (19:14 +0100)]
[g3dvl] use inline constants instead of vs_const for idct
Christian König [Thu, 25 Nov 2010 21:10:21 +0000 (22:10 +0100)]
[g3dvl] no need to keep the idct matrix multiple times
Christian König [Thu, 25 Nov 2010 20:23:48 +0000 (21:23 +0100)]
[g3dvl] add dump option to xvmc
Christian König [Thu, 25 Nov 2010 18:37:12 +0000 (19:37 +0100)]
[g3dvl] also use four elemets on right side multiplikation
Christian König [Wed, 24 Nov 2010 22:54:21 +0000 (23:54 +0100)]
[g3dvl] use four elements in matrix texture fetch
Christian König [Wed, 24 Nov 2010 22:44:30 +0000 (23:44 +0100)]
r600g: disable not working formats
Christian König [Wed, 24 Nov 2010 20:40:50 +0000 (21:40 +0100)]
r600g: reenable texture uploads, but keep R16_SNORM disabled
Christian König [Wed, 24 Nov 2010 20:36:54 +0000 (21:36 +0100)]
r600g: disable R32 float also in r600_translate_colorformat
Christian König [Wed, 24 Nov 2010 19:00:52 +0000 (20:00 +0100)]
[g3dvl] no need for all samplers at all stages
Christian König [Wed, 24 Nov 2010 18:46:51 +0000 (19:46 +0100)]
[g3dvl] remove flushing between stages
Christian König [Wed, 24 Nov 2010 18:40:47 +0000 (19:40 +0100)]
[g3dvl] spread scaling between idct stages
Christian König [Tue, 23 Nov 2010 21:43:29 +0000 (22:43 +0100)]
[g3dvl] remove invalid use of assert
Christian König [Tue, 23 Nov 2010 20:26:26 +0000 (21:26 +0100)]
[g3dvl] switch to r32 float for idct matrix
Christian König [Mon, 22 Nov 2010 23:19:02 +0000 (00:19 +0100)]
[g3dvl] add some error handling
Christian König [Sun, 21 Nov 2010 18:40:52 +0000 (19:40 +0100)]
Merge remote branch 'origin/master' into pipe-video
Conflicts:
src/gallium/auxiliary/Makefile
src/gallium/auxiliary/SConscript
Brian Paul [Sun, 21 Nov 2010 17:05:47 +0000 (10:05 -0700)]
mesa: fix get_texture_dimensions() for texture array targets
Fixes http://bugs.freedesktop.org/show_bug.cgi?id=31779
Brian Paul [Sun, 21 Nov 2010 16:31:19 +0000 (09:31 -0700)]
docs: update some GL 3.0 status
Brian Paul [Sun, 21 Nov 2010 16:19:23 +0000 (09:19 -0700)]
mesa: hook up GL 3.x entrypoints
Fix up some details in the xml files and regenerate dispatch files.
Brian Paul [Sun, 21 Nov 2010 16:13:59 +0000 (09:13 -0700)]
glapi: rename GL3.xml to GL3x.xml as it covers all GL 3.x versions
Brian Paul [Fri, 19 Nov 2010 21:34:07 +0000 (14:34 -0700)]
mesa: fix error msg typo
Daniel Vetter [Fri, 19 Nov 2010 22:38:23 +0000 (23:38 +0100)]
i915g: kill idws->pool
The drm winsys only ever handles one gem memory manager. Rip out
the unnecessary complication.
Reviewed-by: Jakob Bornecrantz <wallbraker@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jakob Bornecrantz <wallbraker@gmail.com>
Daniel Vetter [Fri, 19 Nov 2010 22:38:22 +0000 (23:38 +0100)]
i915g: kill buf->map_gtt
Not using the gtt is considered harmful for performance. And for
partial uploads there's always drm_intel_bo_subdata.
Reviewed-by: Jakob Bornecrantz <wallbraker@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jakob Bornecrantz <wallbraker@gmail.com>
Daniel Vetter [Fri, 19 Nov 2010 22:38:21 +0000 (23:38 +0100)]
i915g: kill RGBA/X formats
It's intel, so always little endian!
Reviewed-by: Jakob Bornecrantz <wallbraker@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jakob Bornecrantz <wallbraker@gmail.com>
Daniel Vetter [Fri, 19 Nov 2010 22:38:20 +0000 (23:38 +0100)]
i915g: add pineview pci ids
Reviewed-by: Jakob Bornecrantz <wallbraker@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jakob Bornecrantz <wallbraker@gmail.com>
Daniel Vetter [Fri, 19 Nov 2010 22:38:19 +0000 (23:38 +0100)]
i915g: s/hw_tiled/tiling
More in line with other intel drivers.
Change to use enum by Jakob Bornecrantz.
Reviewed-by: Jakob Bornecrantz <wallbraker@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jakob Bornecrantz <wallbraker@gmail.com>
Daniel Vetter [Fri, 19 Nov 2010 22:38:18 +0000 (23:38 +0100)]
i915g: rip out ->sw_tiled
It looks like this was meant to facilitate unfenced access to textures/
color/renderbuffers. It's totally incomplete and fundamentally broken
on a few levels:
- broken: The kernel needs to about every tiled bo to fix up bit17
swizzling on swap-in.
- unflexible: fenced/unfenced relocs from execbuffer2 do the same, much
simpler.
- unneeded: with relaxed fencing tiled gem bos are as memory-efficient
as this trick.
Hence kill it.
Reviewed-by: Jakob Bornecrantz <wallbraker@gmail.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>
Signed-off-by: Jakob Bornecrantz <wallbraker@gmail.com>
Joakim Sindholt [Sun, 21 Nov 2010 12:24:03 +0000 (13:24 +0100)]
r300g: silence guard band cap errors
Somebody should find out what these are. It can be found on Windows
getting a D3DCAPS9 from IDirect3D9::GetCaps() and reading the
GuardBand* values.
Christian König [Sun, 21 Nov 2010 13:34:38 +0000 (14:34 +0100)]
[g3dvl] inverse check for iDCT
Christian König [Sun, 21 Nov 2010 13:19:40 +0000 (14:19 +0100)]
[g3dvl] first working version of idct code
Christian König [Sun, 21 Nov 2010 12:58:23 +0000 (13:58 +0100)]
r600g: disable staging upload for now
Christian König [Sun, 21 Nov 2010 12:57:02 +0000 (13:57 +0100)]
r600g: remove accidentally added r32 float format
Chia-I Wu [Sun, 21 Nov 2010 10:58:47 +0000 (18:58 +0800)]
st/vega: Fix vgReadPixels with a subrectangle.
Fix a crash when the subrectangle is not inside the fb. Fix wrong
pipe transfer when sx > 0 or sy + height != fb->height.
This fixes "readpixels" demo.
Chia-I Wu [Sun, 21 Nov 2010 10:46:57 +0000 (18:46 +0800)]
st/vega: Set wrap_r for mask and blend samplers.
These two samplers use non-normalized texture coordinates. wrap_r
cannot be PIPE_TEX_WRAP_REPEAT (the default).
This fixes
sp_tex_sample.c:1790:get_linear_unorm_wrap: Assertion `0' failed
assertion failure.
Chia-I Wu [Sun, 21 Nov 2010 10:44:21 +0000 (18:44 +0800)]
st/vega: vegaLookupSingle should validate the state.
Fix "lookup" demo crash.
Chia-I Wu [Sun, 21 Nov 2010 10:36:41 +0000 (18:36 +0800)]
tgsi: Add STENCIL to text parser.
Fix OpenVG "filter" demo
Program received signal SIGSEGV, Segmentation fault.
0xb7153dc9 in str_match_no_case (pcur=0xbfffe564, str=0x0) at
tgsi/tgsi_text.c:86
86 while (*str != '\0' && *str == uprcase( *cur )) {
Vinson Lee [Sun, 21 Nov 2010 06:44:33 +0000 (22:44 -0800)]
mesa: Clean up header file inclusion in stencil.h.
Vinson Lee [Sun, 21 Nov 2010 06:30:27 +0000 (22:30 -0800)]
mesa: Clean up header file inclusion in shared.h.
Vinson Lee [Sun, 21 Nov 2010 06:17:28 +0000 (22:17 -0800)]
mesa: Clean up header file inclusion in shaderapi.h.
Vinson Lee [Sun, 21 Nov 2010 06:01:30 +0000 (22:01 -0800)]
mesa: Clean up header file inclusion in scissor.h.
Vinson Lee [Sun, 21 Nov 2010 05:32:07 +0000 (21:32 -0800)]
mesa: Clean up header file inclusion in renderbuffer.h.
Vinson Lee [Sun, 21 Nov 2010 05:23:35 +0000 (21:23 -0800)]
mesa: Clean up header file inclusion in readpix.h.
Vinson Lee [Sun, 21 Nov 2010 05:14:06 +0000 (21:14 -0800)]
mesa: Clean up header file inclusion in rastpos.h.
Vinson Lee [Sun, 21 Nov 2010 05:06:09 +0000 (21:06 -0800)]
mesa: Clean up header file inclusion in polygon.h.
Vinson Lee [Sun, 21 Nov 2010 04:13:50 +0000 (20:13 -0800)]
intel: Remove unnecessary header.
Vinson Lee [Sun, 21 Nov 2010 03:04:30 +0000 (19:04 -0800)]
r600: Remove unnecesary header.
Vinson Lee [Sun, 21 Nov 2010 03:00:18 +0000 (19:00 -0800)]
swrast: Remove unnecessary header.
Vinson Lee [Sun, 21 Nov 2010 02:48:09 +0000 (18:48 -0800)]
st/mesa: Remove unnecessary headers.
Chia-I Wu [Sun, 21 Nov 2010 01:47:11 +0000 (17:47 -0800)]
scons: Define IN_DRI_DRIVER.
The define is required for DRI drivers. It is not needed for
libgl-xlib, but the overhead it introduces should be minor.
Xavier Chantry [Sat, 20 Nov 2010 21:51:12 +0000 (22:51 +0100)]
nvfx: only expose one rt on nv30
We do not know how to use more, GL_ARB_draw_buffers is not exposed on blob.
Christian König [Sat, 20 Nov 2010 21:24:42 +0000 (22:24 +0100)]
[g3dvl] move empty block handling into idct code
Christian König [Sat, 20 Nov 2010 20:08:12 +0000 (21:08 +0100)]
[g3dvl] enable stage 1&2 buffers in idct code
Christian König [Sat, 20 Nov 2010 20:06:42 +0000 (21:06 +0100)]
r600g: add support for signed normalized frame buffers
Owen W. Taylor [Sat, 20 Nov 2010 17:18:56 +0000 (12:18 -0500)]
r600g: Fix location for clip plane registers
The stride between the different clip plane registers was incorrect.
https://bugs.freedesktop.org/show_bug.cgi?id=31788
agd5f: fix evergreen as well.
Marek Olšák [Sun, 14 Nov 2010 17:57:14 +0000 (18:57 +0100)]
r300g: fix rendering with no vertex elements
Fixes glsl-vs-point-size, although I meant to fix glsl-novertexdata.
Since swrast fails glsl-novertexdata too, I guess it's a core issue.
Eric Anholt [Fri, 19 Nov 2010 07:57:05 +0000 (15:57 +0800)]
i965: Remove duplicate MRF writes in the FS backend.
This is quite common for multitexture sampling, and not only cuts down
on the second and later set of MOVs, but typically also allows
compute-to-MRF on the first set.
No statistically siginficant performance difference in nexuiz (n=3),
but it reduces instruction count in one of its shaders and seems like
a good idea.
Eric Anholt [Thu, 18 Nov 2010 07:03:50 +0000 (15:03 +0800)]
i965: Improve compute-to-mrf.
We were skipping it if the instruction producing the value we were
going to compute-to-mrf used its result reg as a source reg. This
meant that the typical "write interpolated color to fragment color" or
"texture from interpolated texcoord" shader didn't compute-to-MRF.
Just don't check for the interference cases until after we've checked
if this is the instruction we wanted to compute-to-MRF.
Improves nexuiz high-settings performance on my laptop 0.48% +- 0.08%
(n=3).
Eric Anholt [Fri, 19 Nov 2010 10:50:05 +0000 (18:50 +0800)]
ir_to_mesa: Detect and emit MOV_SATs for saturate constructs.
The goal here is to avoid regressing performance on ir_to_mesa drivers
for fixed function fragment shaders requiring saturates.