mesa.git
11 years agovl: use a template for create_video_decoder
Christian König [Mon, 15 Jul 2013 07:50:24 +0000 (01:50 -0600)]
vl: use a template for create_video_decoder

Signed-off-by: Christian König <christian.koenig@amd.com>
11 years agoglsl: don't eliminate texcoords that can be set by GL_COORD_REPLACE
Marek Olšák [Fri, 9 Aug 2013 20:34:45 +0000 (22:34 +0200)]
glsl: don't eliminate texcoords that can be set by GL_COORD_REPLACE

Tested by examining generated TGSI shaders from piglit/glsl-routing.

Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Henri Verbeet <hverbeet@gmail.com>
Tested-by: Henri Verbeet <hverbeet@gmail.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
11 years agonv50: allow non-nv12 buffers to be created, just pass them through to vl
Ilia Mirkin [Sat, 17 Aug 2013 14:53:09 +0000 (10:53 -0400)]
nv50: allow non-nv12 buffers to be created, just pass them through to vl

Since we expose non-NV12 formats as supported when there is no decoer
profile selected, make sure that those formats are actually allowed to
be allocated.

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Tested-by: Emil Velikov <emil.l.velikov@gmail.com>
Cc: "9.2" <mesa-stable@lists.freedesktop.org>
11 years agodri: Choose a decent global driNConfigOptions.
Eric Anholt [Wed, 26 Jun 2013 22:22:13 +0000 (15:22 -0700)]
dri: Choose a decent global driNConfigOptions.

Previously, we were asserting that each driver specified an NConfigOptions
exactly equal to the number of options they supplied, leading to frequent
bugs when people would forget to adjust the value when adjusting driver
options.  Instead, just overallocate the table by a bit and leave sanity
checking to the assert in findOption().

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
11 years agoi965: Improve comments for driver hooks in intel_buffer_object.c.
Kenneth Graunke [Thu, 1 Aug 2013 23:53:54 +0000 (16:53 -0700)]
i965: Improve comments for driver hooks in intel_buffer_object.c.

Consistently using a "The ___ driver hook." line at the the top of each
function's comment block makes it easy to see at a glance what function
is being implemented.

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
11 years agoi965: Split intel_upload code out into a separate file.
Kenneth Graunke [Thu, 1 Aug 2013 23:14:17 +0000 (16:14 -0700)]
i965: Split intel_upload code out into a separate file.

This code upload performs batched uploads via a BO.  By moving it out to
a separate file, intel_buffer_objects.c only provides the core buffer
object functionality.

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
11 years agoi965: Move GL_APPLE_object_purgeable functionality into a new file.
Kenneth Graunke [Thu, 1 Aug 2013 22:35:35 +0000 (15:35 -0700)]
i965: Move GL_APPLE_object_purgeable functionality into a new file.

GL_APPLE_object_purgeable creates a mechanism for marking OpenGL objects
as "purgeable" so they can be thrown away when system resources become
scarce.  It specifically applies to buffer objects, textures, and
renderbuffers.

The intel_buffer_objects.c file provides core functionality for GL
buffer objects, such as MapBufferRange and CopyBufferSubData.  Having
texture and renderbuffer functionality in that file is a bit strange.

The 2010 copyright on the new file is because Chris Wilson first added
this code in January 2010 (commit 755915fa).

v2: Actually remember to call the new dd table setup function.

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
11 years agoradeonsi: fix feature support reporting
Marek Olšák [Sat, 17 Aug 2013 00:47:21 +0000 (02:47 +0200)]
radeonsi: fix feature support reporting

broken by 21d9a1b5ef51ce449e9a82641d0d605c5448b41c

11 years agoclover: Fix linkage of libOpenCL
Niels Ole Salscheider [Wed, 7 Aug 2013 15:48:48 +0000 (17:48 +0200)]
clover: Fix linkage of libOpenCL

Clover needs the option component of llvm.

Reviewed-by: Tom Stellard <tom@stellard.net>
Signed-off-by: Niels Ole Salscheider <niels_ole@salscheider-online.de>
11 years agoradeonsi: require LLVM 3.4 for MSAA
Marek Olšák [Fri, 16 Aug 2013 13:21:45 +0000 (15:21 +0200)]
radeonsi: require LLVM 3.4 for MSAA

11 years agoradeonsi: don't make scanout resources linear except for cursors
Marek Olšák [Fri, 9 Aug 2013 22:08:45 +0000 (00:08 +0200)]
radeonsi: don't make scanout resources linear except for cursors

The surface allocator understands the scanout flag just fine.

This seems to improve performance for Ubuntu Unity on top of st/xorg
and it fixes the cursor.

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agoradeonsi: remove useless code from tex_fetch_args
Marek Olšák [Wed, 7 Aug 2013 01:20:34 +0000 (03:20 +0200)]
radeonsi: remove useless code from tex_fetch_args

The array slice has already been added to "address".

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agoradeonsi: disable unbound colorbuffers
Marek Olšák [Tue, 6 Aug 2013 22:14:26 +0000 (00:14 +0200)]
radeonsi: disable unbound colorbuffers

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agoradeonsi: port texture improvements from r600g
Marek Olšák [Tue, 6 Aug 2013 19:30:59 +0000 (21:30 +0200)]
radeonsi: port texture improvements from r600g

This started as an attempt to add support for MSAA texture transfers and
MSAA depth-stencil decompression for the DB->CB copy path.
It has gotten a bit out of control, but it's for the greater good.

Some changes do not make much sense, they are there just to make it look
like the other driver.

With a few cosmetic modifications, r600_texture.c can be shared with
a symlink.

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agoradeonsi: implement texture fetching for compressed MSAA textures (v2)
Marek Olšák [Tue, 6 Aug 2013 13:08:54 +0000 (15:08 +0200)]
radeonsi: implement texture fetching for compressed MSAA textures (v2)

v2: use resource slots 16..31 for FMASK textures

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agoradeonsi: add FMASK texture binding slots and resource setup (v2)
Marek Olšák [Tue, 6 Aug 2013 06:53:27 +0000 (08:53 +0200)]
radeonsi: add FMASK texture binding slots and resource setup (v2)

v2: bind FMASK textures to shader resource slots 16..31

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agoradeonsi: implement FMASK decompression for MSAA texturing
Marek Olšák [Tue, 6 Aug 2013 06:48:07 +0000 (08:48 +0200)]
radeonsi: implement FMASK decompression for MSAA texturing

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agoradeonsi: scanout buffers cannot be a destination of MSAA resolve
Marek Olšák [Sat, 10 Aug 2013 16:51:12 +0000 (18:51 +0200)]
radeonsi: scanout buffers cannot be a destination of MSAA resolve

Resolving to scanout buffers just doesn't work.

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agoradeonsi: implement MSAA colorbuffer compression for rendering
Marek Olšák [Thu, 1 Aug 2013 23:44:15 +0000 (01:44 +0200)]
radeonsi: implement MSAA colorbuffer compression for rendering

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agoradeonsi: implement uncompressed MSAA texturing
Marek Olšák [Tue, 30 Jul 2013 20:29:30 +0000 (22:29 +0200)]
radeonsi: implement uncompressed MSAA texturing

This is glBlitFramebuffer support for MSAA surfaces as required by GL 3.0
and texturing as required by GL 3.2 and GL_ARB_texture_multisample.

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agoradeonsi: disable alpha-to-coverage for integer colorbuffers
Marek Olšák [Wed, 7 Aug 2013 22:26:02 +0000 (00:26 +0200)]
radeonsi: disable alpha-to-coverage for integer colorbuffers

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agoradeonsi: implement GL_SAMPLE_ALPHA_TO_ONE
Marek Olšák [Tue, 30 Jul 2013 20:29:29 +0000 (22:29 +0200)]
radeonsi: implement GL_SAMPLE_ALPHA_TO_ONE

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agoradeonsi: implement uncompressed MSAA rendering and color resolving
Marek Olšák [Tue, 30 Jul 2013 20:29:28 +0000 (22:29 +0200)]
radeonsi: implement uncompressed MSAA rendering and color resolving

This is basic MSAA support which should work with most apps.
Some features are missing, those will be implemented by other commits.

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agoradeonsi: add flexible shader descriptor management and use it for sampler views
Marek Olšák [Tue, 6 Aug 2013 04:42:22 +0000 (06:42 +0200)]
radeonsi: add flexible shader descriptor management and use it for sampler views

It moves all sampler view descriptors to a buffer.
It supports partial resource updates and it can also unbind resources
(required for FMASK texturing).

The buffer contains all sampler view descriptors for one shader stage,
represented as an array. On top of that, there are N arrays in the buffer,
which are used to emulate context registers as implemented by the previous
ASICs (each array is a context).

This uses the RCU synchronization approach to avoid read-after-write hazards
as discussed in the thread:
"radeonsi: add FMASK texture binding slots and resource setup"

CP DMA is used to clear the descriptors at context initialization and to copy
the descriptors from one context to the next.

v2: - use PKT3_DMA_DATA on CIK (I'll test CIK later)
    - turn the bool CP DMA parameters into self-explanatory flags
    - add a nice simple API for packet emission to radeon_winsys.h
    - use 256 contexts, 128 causes texture corruption in openarena

11 years agoradeonsi/compute: Let the state tracker do all the flushing
Tom Stellard [Fri, 16 Aug 2013 21:38:40 +0000 (17:38 -0400)]
radeonsi/compute: Let the state tracker do all the flushing

It shouldn't be necessary to call radeon_winsys::cs_flush() from
radeonsi_launch_grid(), because the state tracker is responsible for
flushing the pipeline at the appropriate time.  The current behavior is
also wrong, because radeonsi_launch_grid() submits packets to the
compute ring, but when the state tracker calls pipe->flush() everything
is submitted to the graphics ring.  This has the potential to create a
race condition.

The downside of removing this flush is that the compute dispatch packets
will be sent to the graphics ring rather than the compute ring.
In the future we will need to come up with a way to detect 'compute'
command streams and submit them to the appropriate ring.

Signed-off-by: Marek Olšák <marek.olsak@amd.com>
11 years agoi965: Dump more information about batch buffer usage.
Kenneth Graunke [Wed, 14 Aug 2013 23:07:51 +0000 (16:07 -0700)]
i965: Dump more information about batch buffer usage.

Previously, INTEL_DEBUG=bat would dump messages like:

intel_mipmap_tree.c:1643: Batchbuffer flush with 456b used

This only reported the space used for command packets, and didn't
report any information on the space used for indirect state.

Now it dumps:

intel_context.c:366: Batchbuffer flush with 6128b (pkt) + 4288b (state)
= 10416b (31.8%)

This conveniently shows the breakdown of space used for packets vs.
state, as well as the percentage of batchbuffer space.

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
11 years agoi965: Add Gen7 depth stall flushes before disabling depth in BLORP.
Kenneth Graunke [Tue, 13 Aug 2013 18:37:32 +0000 (11:37 -0700)]
i965: Add Gen7 depth stall flushes before disabling depth in BLORP.

We emit these before configuring depth in the normal path, or actually
using the depth buffer in BLORP - we just failed to emit them when
disabling depth altogether.

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Chad Versace <chad.versace@linux.intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
11 years agoi965: Add Gen6 depth stall flushes before disabling depth in BLORP.
Kenneth Graunke [Tue, 13 Aug 2013 18:34:01 +0000 (11:34 -0700)]
i965: Add Gen6 depth stall flushes before disabling depth in BLORP.

We emit these before configuring depth in the normal path, or actually
using the depth buffer in BLORP - we just failed to emit them when
disabling depth altogether.

On Sandybridge, this also requires the post_sync_nonzero flush.

Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Chad Versace <chad.versace@linux.intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
11 years agoi965: Don't copy propagate bitcasts with source modifiers.
Matt Turner [Thu, 8 Aug 2013 23:41:48 +0000 (16:41 -0700)]
i965: Don't copy propagate bitcasts with source modifiers.

Previously, copy propagation would cause bitcast_f2u(abs(float)) to
be performed in a single step, but the application of source modifiers
(abs, neg) happens after type conversion, leading to incorrect results.

That is, for bitcast_f2u(abs(float)) we would in fact generate code to
do abs(bitcast_f2u(float)).

For example, whereas bitcast_f2u(abs(float)) might result in a register
argument such as
   (abs)g2.2<0,1,0>UD

v2: Set interfered = true and break in register_coalesce instead of
    returning false.

Reviewed-by: Paul Berry <stereoytpe441@gmail.com>
11 years agoi965: Emit MOVs for neg/abs.
Matt Turner [Thu, 8 Aug 2013 20:50:01 +0000 (13:50 -0700)]
i965: Emit MOVs for neg/abs.

Necessary to avoid combining a bitcast and a modifier into a single
operation. Otherwise if safe, the MOV should be removed by
copy-propagation or register coalescing.

With this and the next patch, there are only four changes in shader-db:
all a single extra instruction. The code does something like
   mov a.w, -b.x
and copy propagation doesn't work because it only handles no-op
swizzles. Seems acceptable, given the known limitation of our copy
propagation.

Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Paul Berry <stereoytpe441@gmail.com>
11 years agoi965/blorp: Add support for single sample scaled blit with bilinear filter
Anuj Phogat [Thu, 18 Jul 2013 01:38:50 +0000 (18:38 -0700)]
i965/blorp: Add support for single sample scaled blit with bilinear filter

Currently single sample scaled blits with GL_LINEAR filter falls
back to meta path. Patch removes this limitation in BLORP engine
and implements single sample scaled blit with bilinear filter.
No piglit, gles3 regressions are observed with this patch on Ivybridge.

V2: Use "sample" message to utilize the linear filtering functionality
built in to hardware.
V3: Define a bool variable (bilinear_filter) to handle the conditions
for GL_LINEAR blits.

Signed-off-by: Anuj Phogat <anuj.phogat@gmail.com>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
11 years agoi965/blorp: Define a function to clamp texture coordinates
Anuj Phogat [Thu, 18 Jul 2013 21:59:29 +0000 (14:59 -0700)]
i965/blorp: Define a function to clamp texture coordinates

New function clamp_tex_coords() clamps the texture coordinates
to texture boundaries.  This function will also be utilized later
for the BLORP implementation of single-sample scaled blit with
bilinear filter.

Signed-off-by: Anuj Phogat <anuj.phogat@gmail.com>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
11 years agoi965/blorp: Use more appropriate variable names
Anuj Phogat [Thu, 18 Jul 2013 02:04:54 +0000 (19:04 -0700)]
i965/blorp: Use more appropriate variable names

When we talk about both multi-sample and single-sample scaled blits,
rect_grid_{x1, y1} are more appropriate variable names as compared
to sample_grid_{x1, y1}. There are no functional changes in this patch.
It just prepares for the BLORP implementation of single-sample scaled
blit with bilinear filter.

Signed-off-by: Anuj Phogat <anuj.phogat@gmail.com>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
11 years agometa: Fix blitting a framebuffer with renderbuffer attachment
Anuj Phogat [Mon, 5 Aug 2013 21:27:47 +0000 (14:27 -0700)]
meta: Fix blitting a framebuffer with renderbuffer attachment

This patch fixes a case of framebuffer blitting with renderbuffer
as color attachment and GL_LINEAR filter. Meta implementation of
glBlitFrambuffer() converts source color buffer to a texture and
uses it to do the scaled blitting in to destination buffer. Using
the exact source rectangle to create the texture does incorrect
linear filtering along the edges. This patch makes the changes to
extend the texture edges by one pixel in x, y directions. This
ensures correct linear filtering.
It fixes failing piglit fbo-attachments-blit-scaled-linear test.

Signed-off-by: Anuj Phogat <anuj.phogat@gmail.com>
CC: "9.2" <mesa-stable@lists.freedesktop.org>
CC: "9.1" <mesa-stable@lists.freedesktop.org>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
11 years agonv50: add vp3/vp4 support for mpeg2/vc1
Ilia Mirkin [Sun, 11 Aug 2013 00:19:24 +0000 (20:19 -0400)]
nv50: add vp3/vp4 support for mpeg2/vc1

h264/mpeg4 remain disabled for pre-nvc0, there's some minor
bug/difference which causes the decoding to hang after some frames.

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
11 years agonv50: separate video logic from noalloc
Ilia Mirkin [Sat, 10 Aug 2013 22:53:15 +0000 (18:53 -0400)]
nv50: separate video logic from noalloc

The upcoming vp3 logic will want the video layout, but allocated by the
miptree.

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
11 years agonv30: remove no-longer-used formats from table
Ilia Mirkin [Thu, 15 Aug 2013 23:52:48 +0000 (19:52 -0400)]
nv30: remove no-longer-used formats from table

Commit 14ee790df77 removed the formats from the vtxfmt_table but forgot
to also update the info_table.

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: "9.2 and 9.1" <mesa-stable@lists.freedesktop.org>
11 years agomesa: Update the BGRA vertex array error handling
Fredrik Höglund [Fri, 12 Apr 2013 15:36:06 +0000 (17:36 +0200)]
mesa: Update the BGRA vertex array error handling

The error code was changed from INVALID_VALUE to INVALID_OPERATION
in OpenGL 3.3. We should also generate an error when size is BGRA
and normalized is FALSE.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
11 years agoi965/fs: Fix Sandybridge regressions from SEL optimization.
Kenneth Graunke [Tue, 13 Aug 2013 23:07:56 +0000 (16:07 -0700)]
i965/fs: Fix Sandybridge regressions from SEL optimization.

Sandybridge is the only platform that supports an IF instruction
with an embedded comparison.  In this case, we need to emit a CMP
to go along with the SEL.

Fixes regressions in Piglit's glsl-fs-atan-3, fs-unpackHalf2x16,
fs-faceforward-float-float-float, isinf-and-isnan fs_basic, and
isinf-and-isnan fs_fbo.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=68086
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Anuj Phogat <anuj.phogat@gmail.com>
Tested-by: lu hua <huax.lu@intel.com>
11 years agoi965: Force X-tiling for 128 bpp formats on Sandybridge.
Kenneth Graunke [Tue, 13 Aug 2013 22:03:12 +0000 (15:03 -0700)]
i965: Force X-tiling for 128 bpp formats on Sandybridge.

128 bpp formats are not allowed to be Y-tiled on any architectures
except Gen7.

+11 Piglits on Sandybridge (mostly regression fixes since the
switch to Y-tiling).

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=63867
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=64261
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Chad Versace <chad.versace@linux.intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Cc: "9.2" <mesa-stable@lists.freedesktop.org>
11 years agomesa/vbo: Fix handling of attribute 0 in non-compatibilty contexts
Ian Romanick [Wed, 7 Aug 2013 18:15:41 +0000 (11:15 -0700)]
mesa/vbo: Fix handling of attribute 0 in non-compatibilty contexts

It is only in OpenGL compatibility-style contexts where generic
attribute 0 and GL_VERTEX_ARRAY have a bizzare, aliasing relationship.
Moreover, it is only in OpenGL compatibility-style contexts and OpenGL
ES 1.x where one of these attributes provokes the vertex.  In all other
APIs each implicit call to glArrayElement provokes a vertex regardless
of which attributes are enabled.

Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Robert Bragg <robert@sixbynine.org>
Cc: "9.0 9.1 9.2" <mesa-stable@lists.freedesktop.org>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=55503
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=66292
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=67548

11 years agodraw: handle nan clipdistance
Zack Rusin [Thu, 15 Aug 2013 17:10:22 +0000 (13:10 -0400)]
draw: handle nan clipdistance

If clipdistance for one of the vertices is nan (or inf) then the
entire primitive should be discarded.

Signed-off-by: Zack Rusin <zackr@vmware.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
11 years agoi915,i965: Fix memory leak in try_pbo_upload (v2)
Vinson Lee [Fri, 2 Aug 2013 06:04:27 +0000 (23:04 -0700)]
i915,i965: Fix memory leak in try_pbo_upload (v2)

Fixes "Resource leak" defect reported by Coverity.
Tested on Haswell, no Piglit regressions.

v2: Apply to i965, not just i915. (chadv)

CC: "9.2, 9.1" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Vinson Lee <vlee@freedesktop.org>
Reviewed-by: Chad Versace <chad.versace@linux.intel.com>
11 years agogallivm: revert accidentally commited hunk
Roland Scheidegger [Thu, 15 Aug 2013 17:26:39 +0000 (19:26 +0200)]
gallivm: revert accidentally commited hunk

That magic wasn't meant to be commited, need to work on some proper fix.

11 years agogallivm: do per-sample depth comparison instead of doing it post-filter
Roland Scheidegger [Thu, 15 Aug 2013 16:40:32 +0000 (18:40 +0200)]
gallivm: do per-sample depth comparison instead of doing it post-filter

Doing the comparisons pre-filter is highly recommended by OpenGL (and d3d9)
and definitely required by d3d10.
This actually doesn't do it pre-filter but more "in-filter" as otherwise
need to push the comparisons even further down into fetch code and this
also trivially allows using a somewhat cheaper lerp.
Doing it pre-filter would actually have some performance advantage for UNORM
formats (because the comparisons should be done in texture format, we'd only
need to convert the shadow ref coord to texture format once, but in turn would
save converting the per-sample texture values to floats) but this gets a bit
messy as this has implications for border color handling as well (which needs
to be done prior to depth comparisons, hence would also need to convert border
color to texture format too or use some other tricks like doing separate border
color / shadow ref comparison and simply using that result directly when doing
border replacement).
Should make no difference for nearest filtering, and performance for linear
filtering should be mostly the same too (essentially have one more comparison
instruction per sample, and replace the sub/mul/add lerp with a sub/and/and/add
special "lerp" which all in all shouldn't be much of a difference).

v2: get rid of old code completely

Reviewed-by: Zack Rusin <zackr@vmware.com>
11 years agoradeonsi: Pixel shaders pre-load one more SGPR
Michel Dänzer [Fri, 9 Aug 2013 16:36:31 +0000 (18:36 +0200)]
radeonsi: Pixel shaders pre-load one more SGPR

Acked-by: Marek Olšák <maraeo@gmail.com>
11 years agoradeonsi: TGSI_SEMANTIC_CLIPVERTEX doesn't use any parameters
Michel Dänzer [Wed, 7 Aug 2013 09:30:50 +0000 (11:30 +0200)]
radeonsi: TGSI_SEMANTIC_CLIPVERTEX doesn't use any parameters

11 years agoradeonsi: Don't export unused clip distance vectors from vertex shader
Michel Dänzer [Thu, 8 Aug 2013 14:58:00 +0000 (16:58 +0200)]
radeonsi: Don't export unused clip distance vectors from vertex shader

E.g. the Source engine seems to always write to gl_ClipVertex, but normally
doesn't enable any GL_CLIP_DISTANCEn states. This change removes some
irrelevant parts from the generated vertex shader code in such cases.

Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
11 years agoradeonsi: Don't leave gaps between position exports from vertex shader
Michel Dänzer [Wed, 7 Aug 2013 16:14:16 +0000 (18:14 +0200)]
radeonsi: Don't leave gaps between position exports from vertex shader

If the vertex shader exports clip distances but not point size, use
position exports 1/2 instead of 2/3 for the clip distances. Fixes
geometry corruption in that case.

Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=66974

Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Tom Stellard <thomas.stellard@amd.com>
11 years agollvmpipe: fix stencil bug if we have both stencil and depth tests
Roland Scheidegger [Thu, 15 Aug 2013 14:50:27 +0000 (16:50 +0200)]
llvmpipe: fix stencil bug if we have both stencil and depth tests

This is a very well hidden bug found by accident (only the fixed glean
tstencil2 test so far seems to hit it).
We must use new mask with combined s_pass values and orig_mask values
for zpass/zfail stencil ops, otherwise both the sfail op and one of
zpass/zfail op are applied (probably not hit in most tests because
some of the ops tend to be KEEP usually).

Note: this is a candidate for the 9.2 branch.

Reviewed-by: Zack Rusin <zackr@vmware.com>
11 years agost/mesa: use new float comparison opcodes if native integers are supported
Roland Scheidegger [Wed, 14 Aug 2013 23:05:03 +0000 (01:05 +0200)]
st/mesa: use new float comparison opcodes if native integers are supported

Should get rid of some float-to-int conversions (with negation).
No piglit regressions (with llvmpipe).

v2: fix bogus formatting spotted by Brian.

Reviewed-by: Brian Paul <brianp@vmware.com>
11 years agonvc0: move video param and format support functions to nouveau
Ilia Mirkin [Sat, 10 Aug 2013 22:02:49 +0000 (18:02 -0400)]
nvc0: move video param and format support functions to nouveau

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
11 years agonvc0: move firmware loading functions to nouveau
Ilia Mirkin [Sat, 10 Aug 2013 21:51:01 +0000 (17:51 -0400)]
nvc0: move firmware loading functions to nouveau

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
11 years agonvc0: move some of the simpler decoder functions into nouveau
Ilia Mirkin [Sat, 10 Aug 2013 21:10:26 +0000 (17:10 -0400)]
nvc0: move some of the simpler decoder functions into nouveau

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
11 years agonvc0: move vp param filling logic into nouveau
Ilia Mirkin [Sat, 10 Aug 2013 20:43:06 +0000 (16:43 -0400)]
nvc0: move vp param filling logic into nouveau

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
11 years agonvc0: move bsp param-filling logic into nouveau
Ilia Mirkin [Sat, 10 Aug 2013 20:07:17 +0000 (16:07 -0400)]
nvc0: move bsp param-filling logic into nouveau

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
11 years agonvc0: move nvc0_decoder into nouveau, rename to nouveau_vp3_decoder
Ilia Mirkin [Sat, 10 Aug 2013 19:42:19 +0000 (15:42 -0400)]
nvc0: move nvc0_decoder into nouveau, rename to nouveau_vp3_decoder

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
11 years agonvc0: standardize on using #if for NVC0_DEBUG_FENCE
Ilia Mirkin [Sat, 10 Aug 2013 19:27:49 +0000 (15:27 -0400)]
nvc0: standardize on using #if for NVC0_DEBUG_FENCE

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
11 years agonvc0: refactor video buffer management logic into nouveau_vp3
Ilia Mirkin [Sat, 10 Aug 2013 17:27:47 +0000 (13:27 -0400)]
nvc0: refactor video buffer management logic into nouveau_vp3

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
11 years agonv50: allow forcing PMPEG use, for ease of testing
Ilia Mirkin [Mon, 29 Jul 2013 23:28:45 +0000 (19:28 -0400)]
nv50: allow forcing PMPEG use, for ease of testing

This also allows people who don't want to install the binary blobs
required for VP2 to still get MPEG decoding.

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
11 years agonv30: hook up PMPEG support via nouveau_video, enables XvMC to work
Ilia Mirkin [Tue, 2 Jul 2013 21:33:41 +0000 (17:33 -0400)]
nv30: hook up PMPEG support via nouveau_video, enables XvMC to work

Force the format to be the reasonable format that doesn't require an
inverse z-scan.

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
11 years agonouveau: set buffer format of video buffer
Ilia Mirkin [Sat, 10 Aug 2013 08:10:28 +0000 (04:10 -0400)]
nouveau: set buffer format of video buffer

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
11 years agonouveau: fix number of surfaces in video buffer, use defines
Ilia Mirkin [Sat, 10 Aug 2013 07:49:21 +0000 (03:49 -0400)]
nouveau: fix number of surfaces in video buffer, use defines

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
11 years agonv30: U8_USCALED only works for size 4
Ilia Mirkin [Wed, 14 Aug 2013 05:08:38 +0000 (01:08 -0400)]
nv30: U8_USCALED only works for size 4

See https://bugs.freedesktop.org/show_bug.cgi?id=61635 for a sample
program. Changing it to use a vec4 makes it work. Remove the unsupported
formats.

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: "9.2 and 9.1" <mesa-stable@lists.freedesktop.org>
11 years agoi965: allow 8 user clip planes on CTG+
Chris Forbes [Sun, 7 Jul 2013 10:51:02 +0000 (22:51 +1200)]
i965: allow 8 user clip planes on CTG+

There's no need to use a clip flag for NEGW on these gens, so
no reason we can't just enable 8 planes.

V2: - Bump (and document!) MAX_VERTS in the clip code.
    - Fix clip flag masks in the clip unit state and in the shader
      prolog
    - Move this to the end of the series for less breakage.

Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
11 years agoi965: get rid of clip plane compaction
Chris Forbes [Sun, 7 Jul 2013 15:46:55 +0000 (03:46 +1200)]
i965: get rid of clip plane compaction

Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
11 years agoi965/clip: Support clip distances for line clipping
Chris Forbes [Sun, 4 Aug 2013 16:18:22 +0000 (04:18 +1200)]
i965/clip: Support clip distances for line clipping

This does the same thing as we do for triangle clipping -- select the
appropriate source (either dot(hpos,fixed plane) or a clipdistance
slot).

Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
11 years agoi965/clip: remove spurious clipvertex param
Chris Forbes [Sun, 4 Aug 2013 06:32:48 +0000 (18:32 +1200)]
i965/clip: remove spurious clipvertex param

Nothing in the clipper uses gl_ClipVertex any more, so we don't care
where it is.

V2: Don't bother fishing out the clipvertex offset either.

Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
11 years agoi965/clip: Use clip distances for all user clipping
Chris Forbes [Sun, 4 Aug 2013 06:31:56 +0000 (18:31 +1200)]
i965/clip: Use clip distances for all user clipping

V2: Adjust explanation of load_clip_distance()

Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
11 years agoi956/clip: push dp4 into load_clip_distance
Chris Forbes [Sat, 3 Aug 2013 17:47:34 +0000 (05:47 +1200)]
i956/clip: push dp4 into load_clip_distance

Soon the dp4 is only going to be used for fixed clip planes.

V2: Remove old inaccurate comment about the behavior of this function;
add a better explanation above.

Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
11 years agoi965/clip: Track offset into the vertex for clipdistance
Chris Forbes [Sat, 3 Aug 2013 17:20:17 +0000 (05:20 +1200)]
i965/clip: Track offset into the vertex for clipdistance

Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
11 years agoi965/Gen4-5: Set clip flags from clip distances
Chris Forbes [Sat, 3 Aug 2013 15:32:34 +0000 (03:32 +1200)]
i965/Gen4-5: Set clip flags from clip distances

V2: - Use the new VS_OPCODE_UNPACK_FLAGS_SIMD4X2 to correctly split the
      flags for the two vertices being processed together.
    - Don't apply bogus masking of clip flags. The set of plane enables
      aren't included in the shader key, and we wouldn't want the
      recompiles anyway.

V3: - Tidy up spurious instructions, name temps properly.

Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
[V2] Reviewed-by: Paul Berry <stereotype441@gmail.com>

11 years agoi965: add new VS_OPCODE_UNPACK_FLAGS_SIMD4X2
Chris Forbes [Wed, 7 Aug 2013 18:31:33 +0000 (06:31 +1200)]
i965: add new VS_OPCODE_UNPACK_FLAGS_SIMD4X2

Splits the bottom 8 bits of f0.0 for further wrangling
in a SIMD4x2 program. The 4 bits corresponding to the channels in each
program flow are copied to the LSBs of dst.x visible to each flow.

This is useful for working with clipping flags in the VS.

V3: - Fixup immediate types
    - Teach scheduler about the hidden dep on flags

Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
V2: Reviewed-by: Paul Berry <stereotype441@gmail.com>

11 years agoi965/vs: add vec4_instruction::depends_on_flags
Chris Forbes [Thu, 15 Aug 2013 18:54:30 +0000 (06:54 +1200)]
i965/vs: add vec4_instruction::depends_on_flags

We're about to have an instruction that depends on the flags but isn't
predicated. This lays the groundwork.

Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
11 years agoi965/clip: Enable interpolation of clip distances
Chris Forbes [Sun, 7 Jul 2013 16:48:52 +0000 (04:48 +1200)]
i965/clip: Enable interpolation of clip distances

Previously we had disabled interpolation of the clip distances as a
special case, since they were unused.

Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
11 years agoi965/vs: Do legacy clip lowering earlier
Chris Forbes [Sun, 7 Jul 2013 16:21:08 +0000 (04:21 +1200)]
i965/vs: Do legacy clip lowering earlier

We need to produce clip flags for the vertex header on Gen4/5, so
clip plane lowering has to be done before we try to emit the flags/psiz
attribute.

Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
11 years agoi965/Gen4-5: ensure VUE slots for clipdistance are valid if user clipping is enabled.
Chris Forbes [Sun, 7 Jul 2013 15:44:58 +0000 (03:44 +1200)]
i965/Gen4-5: ensure VUE slots for clipdistance are valid if user clipping is enabled.

V2: We don't particularly care where they fall in the VUE map, as long
as they are allocated somewhere, and occupy two contiguous slots. Don't
fiddle with the SF layout at all -- there's no need.

Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
11 years agoilo: fix fragment shaders that use PCB on GEN7+
Chia-I Wu [Thu, 15 Aug 2013 03:14:05 +0000 (11:14 +0800)]
ilo: fix fragment shaders that use PCB on GEN7+

Missed this commit when preparing PCB changes for upstreaming.

11 years agonouveau: Fix variable name.
Vinson Lee [Thu, 15 Aug 2013 00:27:53 +0000 (17:27 -0700)]
nouveau: Fix variable name.

Fixes build error introduced with commit
d1ba1055d98c246d1ee9d9c14706bb9fba6a98c7.

  CC     nouveau_video.lo
nouveau_video.c: In function 'nouveau_screen_get_video_param':
nouveau_video.c:866:33: error: 'screen' undeclared (first use in this function)
nouveau_video.c:866:33: note: each undeclared identifier is reported only once for each function it appear

Signed-off-by: Vinson Lee <vlee@freedesktop.org>
11 years agoglsl: Add i2b() and b2i() to ir_builder.
Matt Turner [Wed, 7 Aug 2013 20:00:48 +0000 (13:00 -0700)]
glsl: Add i2b() and b2i() to ir_builder.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Chad Versace <chad.versace@linux.intel.com>
11 years agoglsl: Add nequal() to ir_builder.
Matt Turner [Sun, 4 Aug 2013 21:09:35 +0000 (14:09 -0700)]
glsl: Add nequal() to ir_builder.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Chad Versace <chad.versace@linux.intel.com>
11 years agoglsl: Add abs() to ir_builder.
Matt Turner [Sun, 4 Aug 2013 21:09:09 +0000 (14:09 -0700)]
glsl: Add abs() to ir_builder.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Chad Versace <chad.versace@linux.intel.com>
11 years agoglsl: Add bitcast_i2f() to ir_builder.
Matt Turner [Sat, 3 Aug 2013 18:33:49 +0000 (11:33 -0700)]
glsl: Add bitcast_i2f() to ir_builder.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Chad Versace <chad.versace@linux.intel.com>
11 years agoradeonsi: unduplicate code in create_context
Marek Olšák [Tue, 6 Aug 2013 04:33:22 +0000 (06:33 +0200)]
radeonsi: unduplicate code in create_context

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agoradeonsi: initialize the radeon_surface structure
Marek Olšák [Tue, 6 Aug 2013 04:23:52 +0000 (06:23 +0200)]
radeonsi: initialize the radeon_surface structure

this fixes valgrind warnings

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agoradeonsi: correct sampler function names
Marek Olšák [Tue, 6 Aug 2013 04:31:17 +0000 (06:31 +0200)]
radeonsi: correct sampler function names

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agoradeonsi: rename r600_texture::dirty_db_mask to dirty_level_mask
Marek Olšák [Mon, 5 Aug 2013 12:40:43 +0000 (14:40 +0200)]
radeonsi: rename r600_texture::dirty_db_mask to dirty_level_mask

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agoradeonsi: rename r600_resource_texture to r600_texture
Marek Olšák [Mon, 5 Aug 2013 01:42:11 +0000 (03:42 +0200)]
radeonsi: rename r600_resource_texture to r600_texture

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agotgsi: add info about MSAA samplers to tgsi_shader_info
Marek Olšák [Tue, 6 Aug 2013 04:35:23 +0000 (06:35 +0200)]
tgsi: add info about MSAA samplers to tgsi_shader_info

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agotgsi: fix the location of sample index
Marek Olšák [Tue, 6 Aug 2013 04:21:11 +0000 (06:21 +0200)]
tgsi: fix the location of sample index

The sample index is always in W.

Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
11 years agor600/radeonsi: implement new float comparison instructions
Roland Scheidegger [Tue, 13 Aug 2013 16:59:35 +0000 (18:59 +0200)]
r600/radeonsi: implement new float comparison instructions

Also use ordered comparisons for old cmp instructions.

Tested-by: Michel Dänzer <michel@daenzer.net>
Reviewed-by: Tom Stellard <tom@stellard.net>
11 years agonv50: implement new float comparison instructions
Roland Scheidegger [Tue, 13 Aug 2013 16:54:15 +0000 (18:54 +0200)]
nv50: implement new float comparison instructions

untested.

Reviewed-by: Christoph Bumiller <e0425955@student.tuwien.ac.at>
11 years agoilo: implement new float comparison instructions
Roland Scheidegger [Tue, 13 Aug 2013 16:53:49 +0000 (18:53 +0200)]
ilo: implement new float comparison instructions

untested.

Reviewed-by: Chia-I Wu <olvaffe@gmail.com>
11 years agogallivm: already pass coords in the right place in the sampler interface
Roland Scheidegger [Wed, 14 Aug 2013 16:35:00 +0000 (18:35 +0200)]
gallivm: already pass coords in the right place in the sampler interface

This makes things a bit nicer, and more importantly it fixes an issue
where a "downgraded" array texture (due to view reduced to 1 layer and
addressed with (non-array) samplec instruction) would use the wrong
coord as shadow reference value. (This could also be fixed by passing
target through the sampler interface much the same way as is done for
size queries, might do this eventually anyway.)
And if we'd ever want to support (shadow) cube map arrays, we'd need
5 coords in any case.

v2: fix bugs (texel fetch using wrong layer coord for 1d, shadow tex
using wrong shadow coord for 2d...). Plus need to project the shadow
coord, and just for fun keep projecting the layer coord too.

Reviewed-by: Zack Rusin <zackr@vmware.com>
11 years agogallivm: change coordinate handling throughout functions
Roland Scheidegger [Wed, 14 Aug 2013 22:18:20 +0000 (00:18 +0200)]
gallivm: change coordinate handling throughout functions

Instead of passing s,t,r coordinates pass a coord array - the reason is that
I need to pass more coords (in particular for shadow "coord", future will also
need another one for cube map arrays) so just pass them as an array.
Also, to simplify things, use fixed location for the shadow reference value I
want to get rid of the silly "where is the right coord value" game.
Keep old-style however for aos sampling (which is not going to need shadow
coord, though for cube map arrays it still would need fixing).
(Next patch will pass those through using the new arrangement directly from
sampler interface.)

v2: fix up soa split path (unreachable currently but still...)

Reviewed-by: Zack Rusin <zackr@vmware.com>
11 years agogallivm: fix border color with normalized texture formats
Roland Scheidegger [Wed, 14 Aug 2013 00:13:18 +0000 (02:13 +0200)]
gallivm: fix border color with normalized texture formats

We need to put border color into texture format color space which
essentially means clamping for non-float, normalized formats (not entirely
sure if we're also meant to quantize the float but it's probably ok not to
do it thankfully).
For OpenGL we could do this easily outside generated code due to the
1:1 sampler/texture correspondence but not for d3d10 which is terrible
(as we recalculate a constant over and over again per shader invocation).
Fortunately border color should be rare enough that we don't care THAT much.

Reviewed-by: Zack Rusin <zackr@vmware.com>
11 years agollvmpipe: fix pipeline statistics with a null ps
Zack Rusin [Tue, 13 Aug 2013 05:42:37 +0000 (01:42 -0400)]
llvmpipe: fix pipeline statistics with a null ps

If the fragment shader is null then pixel shader invocations have
to be equal to zero. And if we're running a null ps then clipper
invocations and primitives should be equal to zero but only
if both stancil and depth testing are disabled.

Signed-off-by: Zack Rusin <zackr@vmware.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
11 years agodraw: make sure that the stages setup outputs
Zack Rusin [Fri, 9 Aug 2013 14:11:31 +0000 (10:11 -0400)]
draw: make sure that the stages setup outputs

Calling the prepare outputs cleans up the slot assignments
for outputs, unfortunately aapoint and aaline didn't have
code to reset their slots after the initial setup, this
was messing up our slot assignments. The unfilled stage
was just missing the initial assignment of the face slot.
This fixes all of the reported piglit failures.

Signed-off-by: Zack Rusin <zackr@vmware.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
11 years agoglsl: Fix incorrect pattern matching in ir_set_program_inouts
Paul Berry [Fri, 9 Aug 2013 14:58:43 +0000 (07:58 -0700)]
glsl: Fix incorrect pattern matching in ir_set_program_inouts

In commit 8fc41df (glsl: Modify ir_set_program_inouts to handle
geometry shaders), when attempting to pattern match the "foo" part of
expressions such as:

   foo[i][j]
   foo[i]

I incorrectly called as_dereference_variable() on the subexpression
foo[i] instead of foo.  As a result, the pattern never matched, so
ir_set_program_inouts would fall back on marking the entire variable
as used, rather than just the portion indexed by the array.

This didn't result in incorrect behaviour, but it could have resulted
in inefficiency by causing the back-end to allocate resources for
unused parts of an input or output array.

Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
11 years agovl: Add support for max level query v2
Rico Schüller [Wed, 14 Aug 2013 11:17:22 +0000 (13:17 +0200)]
vl: Add support for max level query v2

This patch adds the level query support to the video decoders
and uses some more reasonable defaults.

v2: (ck) add commit message

Reviewed-by: Christian König <christian.koenig@amd.com>