Paul Berry [Fri, 8 Mar 2013 20:03:10 +0000 (12:03 -0800)]
i965: Apply depthstencil alignment workaround when doing fast clears.
Fast depth clears have the same depth/stencil alignment requirements
as other drawing operations. Therefore, we need to call
brw_workaround_depthstencil_alignment() from both the clear and
drawing paths.
Without this fix, we get image corruption if the following conditions
hold: (a) the first ever drawing operation to a depth miplevel (or the
first drawing operation after having used the texture for sampling) is
a clear, (b) the depth miplevel has a size that is eligible for fast
depth clears, and (c) the depth miplevel has an offset within the
miptree that isn't 8x8 aligned.
Fixes piglit "depthstencil-render-miplevels" tests with size 273.
NOTE: This is a candidate for stable branches
Reviewed-by: Chad Versace <chad.versace@linux.intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Paul Berry [Sat, 23 Feb 2013 17:00:58 +0000 (09:00 -0800)]
Replace gl_frag_attrib enum with gl_varying_slot.
This patch makes the following search-and-replace changes:
gl_frag_attrib -> gl_varying_slot
FRAG_ATTRIB_* -> VARYING_SLOT_*
FRAG_BIT_* -> VARYING_BIT_*
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Tested-by: Brian Paul <brianp@vmware.com>
Paul Berry [Sat, 23 Feb 2013 16:36:40 +0000 (08:36 -0800)]
Get rid of _mesa_frag_attrib_to_vert_result().
Now that there is no difference between the enums that represent
vertex outputs and fragment inputs, there's no need for a conversion
function.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Tested-by: Brian Paul <brianp@vmware.com>
Paul Berry [Sat, 23 Feb 2013 16:28:18 +0000 (08:28 -0800)]
Get rid of _mesa_vert_result_to_frag_attrib().
Now that there is no difference between the enums that represent
vertex outputs and fragment inputs, there's no need for a conversion
function. But we still need to be able to detect when a given vertex
output has no corresponding fragment input. So it is replaced by a
new function, _mesa_varying_slot_in_fs(), which tells whether the
given varying slot exists as an FS input or not.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Tested-by: Brian Paul <brianp@vmware.com>
Paul Berry [Sat, 23 Feb 2013 16:09:27 +0000 (08:09 -0800)]
mtypes.h: Modify gl_frag_attrib to refer to new gl_varying_slot enum.
This paves the way for eliminating the gl_frag_attrib enum entirely.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Tested-by: Brian Paul <brianp@vmware.com>
Paul Berry [Sat, 23 Feb 2013 15:49:04 +0000 (07:49 -0800)]
Replace gl_geom_result enum with gl_varying_slot.
This patch makes the following search-and-replace changes:
gl_geom_result -> gl_varying_slot
GEOM_RESULT_* -> VARYING_SLOT_*
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Tested-by: Brian Paul <brianp@vmware.com>
Paul Berry [Sat, 23 Feb 2013 15:45:07 +0000 (07:45 -0800)]
mtypes.h: Modify gl_geom_result to refer to new gl_varying_slot enum.
This paves the way for eliminating the gl_geom_result enum entirely.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Tested-by: Brian Paul <brianp@vmware.com>
Paul Berry [Sat, 23 Feb 2013 15:34:06 +0000 (07:34 -0800)]
Replace gl_geom_attrib enum with gl_varying_slot.
This patch makes the following search-and-replace changes:
gl_geom_attrib -> gl_varying_slot
GEOM_ATTRIB_* -> VARYING_SLOT_*
GEOM_BIT_* -> VARYING_BIT_*
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Tested-by: Brian Paul <brianp@vmware.com>
Paul Berry [Sat, 23 Feb 2013 15:31:33 +0000 (07:31 -0800)]
mtypes.h: Modify gl_geom_attrib to refer to new gl_varying_slot enum.
This paves the way for eliminating the gl_geom_attrib enum entirely.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Tested-by: Brian Paul <brianp@vmware.com>
Paul Berry [Sat, 23 Feb 2013 15:22:01 +0000 (07:22 -0800)]
Replace gl_vert_result enum with gl_varying_slot.
This patch makes the following search-and-replace changes:
gl_vert_result -> gl_varying_slot
VERT_RESULT_* -> VARYING_SLOT_*
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Tested-by: Brian Paul <brianp@vmware.com>
Paul Berry [Fri, 22 Feb 2013 19:49:44 +0000 (11:49 -0800)]
mtypes.h: Modify gl_vert_result to refer to new gl_varying_slot enum.
This paves the way for eliminating the gl_vert_result enum entirely.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Tested-by: Brian Paul <brianp@vmware.com>
Paul Berry [Fri, 22 Feb 2013 19:32:54 +0000 (11:32 -0800)]
mtypes.h: Add new gl_varying_slot enum, and bitfield defines.
Future patches will make use of the enum. It will eventually take the
place of the existing enums gl_vert_result, gl_geom_attrib,
gl_geom_result, and gl_frag_attrib, all of which represent essentially
the same information but using inconsistent values.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Tested-by: Brian Paul <brianp@vmware.com>
Paul Berry [Sun, 24 Feb 2013 18:53:35 +0000 (10:53 -0800)]
i965: Change fragment input related bitfields to 64-bit.
This patch updates the bitfields brw_context::wm.input_size_masks,
tracker::size_masks, and brw_wm_prog_key::proj_attrib_mask, all of
which are indexed by gl_frag_attrib, from 32-bit to 64-bit.
This paves the way for supporting geometry shaders, and for merging
the gl_frag_attrib and gl_vert_result enums. The combination of these
two will require at least 55 bits in the bitfields.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Tested-by: Brian Paul <brianp@vmware.com>
Alex Deucher [Fri, 8 Mar 2013 18:52:37 +0000 (13:52 -0500)]
r600g: add Richland APU pci ids
Note: this is a candidate for the stable branches.
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
Brian Paul [Thu, 14 Mar 2013 02:24:05 +0000 (20:24 -0600)]
st/dri: add support for the always_have_depth_buffer option
This involved adding another driOptionCache to dri_screen. The
existing one just held the default values. But now we also need
to have the values from the DRI config file so that we can get at
the always_have_depth_buffer config option, which is per-screen.
Brian Paul [Thu, 14 Mar 2013 02:19:44 +0000 (20:19 -0600)]
driconf: add a miscellaneous section and always_have_depth_buffer option
This option is needed for some applications that neglect to request
a depth buffer when choosing a visual/fbconfig.
The Linux app Topogun is an example of this problem.
Brian Paul [Wed, 13 Mar 2013 18:08:48 +0000 (12:08 -0600)]
driconf: reorder options, reformat comments, etc
Move the options into the proper section (Debug, Quality, Performance,
etc).
Update comments and add some whitespace to improve readability.
Philipp Brüschweiler [Fri, 8 Mar 2013 20:32:36 +0000 (21:32 +0100)]
wayland: fix segfault when using software rendering
wayland_roundtrip() was given an incorrect parameter.
Fixes https://bugs.freedesktop.org/show_bug.cgi?id=62362
Note: This is a candidate for the stable branches.
Signed-off-by: Brian Paul <brianp@vmware.com>
Brian Paul [Thu, 14 Mar 2013 13:45:59 +0000 (07:45 -0600)]
softpipe: fix up NUM_ENTRIES confusion
There were two different NUM_ENTRIES #defines for the framebuffer
tile cache and the texture tile cache. Rename the later to fix
the warnings:
In file included from sp_flush.c:40:0:
sp_tex_tile_cache.h:76:0: warning: "NUM_ENTRIES" redefined
sp_tile_cache.h:78:0: note: this is the location of the previous definition
In file included from sp_context.c:50:0:
sp_tex_tile_cache.h:76:0: warning: "NUM_ENTRIES" redefined
sp_tile_cache.h:78:0: note: this is the location of the previous definition
Also, replace occurances of NUM_ENTRIES with Element() macro to
be safer.
Reviewed-by: José Fonseca <jfonseca@vmware.com>
Brian Paul [Wed, 13 Mar 2013 14:43:04 +0000 (08:43 -0600)]
st/osmesa: silence some optimized build warnings
Brian Paul [Wed, 13 Mar 2013 14:35:39 +0000 (08:35 -0600)]
draw: init pre_clip_pos = NULL to fix optimized build warning
Brian Paul [Wed, 13 Mar 2013 14:35:21 +0000 (08:35 -0600)]
glx: init screen = 0 to fix optimized build warning
Kenneth Graunke [Thu, 7 Feb 2013 07:26:36 +0000 (23:26 -0800)]
i965: Make INTEL_DEBUG=shader_time use the RAW surface format.
Untyped Atomic Operation messages are illegal for non-RAW formats. The
IVB hardware proceeds happily (after all, who cares what the format of the
surface is if you're doing untyped ops on it?), but later hardware
apparently doesn't. The simulator for gen7 does complain, though.
v2: Rebase against updates to previous patches. (by anholt)
NOTE: This is a candidate for the 9.1 branch.
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Kenneth Graunke [Thu, 7 Feb 2013 07:26:35 +0000 (23:26 -0800)]
i965: Specialize SURFACE_STATE creation for shader time.
This is basically a copy and paste of gen7_create_constant_surface, but
with the parameters filled in to offer a simpler interface.
It will diverge shortly.
I didn't bother adding it to the vtable for now since shader time is only
exposed on Gen7+.
v2: Replace tabs in the new code (by anholt)
Add back dropped memset() and add a comment about HSW channel selects.
NOTE: This is a candidate for the 9.1 branch.
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Kenneth Graunke [Thu, 7 Feb 2013 07:26:34 +0000 (23:26 -0800)]
i965: Fix INTEL_DEBUG=shader_time for Haswell.
Haswell's "Data Cache" data port is a single unit, but split into two
SFIDs to allow for more message types without adding more bits in the
message descriptor.
Untyped Atomic Operations are now message 0010 in the second data cache
data port, rather than 6 in the first.
v2: Use the #defines from the previous commit. (by anholt)
NOTE: This is a candidate for the 9.1 branch.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net> (v1)
Eric Anholt [Mon, 11 Mar 2013 21:56:38 +0000 (14:56 -0700)]
i965: Add definitions for gen7+ data cache messages.
We were sparsely using some of these message types, but I'll just fill
them all in now. It will be used for fixing shader_time on HSW.
v2: Add missing MEDIA_BLOCK_READ.
NOTE: This is a candidate for the 9.1 branch.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Eric Anholt [Mon, 11 Mar 2013 19:59:06 +0000 (12:59 -0700)]
i965: Split shader_time entries into separate cachelines.
This avoids some snooping overhead between EUs processing separate shaders
(so VS versus FS).
Improves performance of a minecraft trace with shader_time by 28.9% +/-
18.3% (n=7), and performance of my old GLSL demo by 93.7% +/- 0.8% (n=4).
v2: Add a define for the stride with a comment explaining its units and
why.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
José Fonseca [Thu, 14 Mar 2013 17:40:14 +0000 (17:40 +0000)]
scons: Define _ALLOW_KEYWORD_MACROS on MSVC builds.
scons/llvm.py defines inline globally to workaround issues with LLVM C
binding headers, so the only way to is to avoid
aggravating xkeycheck.h errors is to set _ALLOW_KEYWORD_MACROS.
This fixes MSVC 2012 build with LLVM.
Reviewed-by: Brian Paul <brianp@vmware.com>
José Fonseca [Thu, 14 Mar 2013 11:44:21 +0000 (11:44 +0000)]
softpipe: Shrink context size.
- each softpipe_tex_tile_cache 50*64*64*4*4 = 3,276,800 bytes
- each softpipe_context has 3*32 softpipe_tex_tile_cache, i.e, each softpipe
context is 314,572,800 bytes, i.e, 300MB
That is, in a 32bits process (around 3GB virtual memory max), we can
only fit 10 contexts.
This change is a short-term hack to shrink the context size. Longer
term we'll need to change how the texture cache works.
Reviewed-by: Brian Paul <brianp@vmware.com>
Christian König [Thu, 14 Mar 2013 11:37:02 +0000 (12:37 +0100)]
radeon/llvm: fix LLVM dependencies
Since commit
1c4f283151b191c51cbd76d7f304cc1fe7be3019 we obvious depend on this.
Signed-off-by: Christian König <christian.koenig@amd.com>
Anuj Phogat [Thu, 7 Mar 2013 22:05:38 +0000 (14:05 -0800)]
mesa: Fix FB blitting in case of zero size src or dst rect
Framebuffer blitting operation should be skipped if any of the
dimensions (width/height) of src/dst rect is zero.
V2: Move the dimension check after error checking in _mesa_BlitFramebuffer.
Fixes: fbblit(negative.nullblit.zeroSize) in Intel oglconform
https://bugs.freedesktop.org/show_bug.cgi?id=59495
Note: Candidate for all the stable branches.
Signed-off-by: Anuj Phogat <anuj.phogat@gmail.com>
Reviewed-by: Paul Berry <stereotype441@gmail.com>
Roland Scheidegger [Wed, 13 Mar 2013 21:10:18 +0000 (22:10 +0100)]
tgsi: fix sample_d emit for arrays
Those cases were apparently forgotten.
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Roland Scheidegger [Wed, 13 Mar 2013 20:23:18 +0000 (21:23 +0100)]
llvmpipe: don't assert when trying to render to surfaces with multiple layers
instead just warn when creating the surface, rendering will simply happen
to first layer.
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Roland Scheidegger [Wed, 13 Mar 2013 20:19:20 +0000 (21:19 +0100)]
softpipe: don't assert when creating surfaces with multiple layers
We can't handle them yet, however we can safely just warn (we will
just render to first layer, which is fine since we can't handle
rendertarget system value neither).
Also make behavior more predictable with buffer surfaces
(it would sometimes hit bogus asserts because of the union in the surface,
instead create the surface but assert when trying to set a buffer
in the framebuffer).
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
José Fonseca [Wed, 13 Mar 2013 21:21:17 +0000 (21:21 +0000)]
llvmpipe: Fix geometry shader token leak.
Trivial. Matches softpipe's code.
Tom Stellard [Thu, 7 Mar 2013 21:51:14 +0000 (16:51 -0500)]
radeon/llvm: Add missing license headers
Signed-off-by: Tom Stellard <thomas.stellard@amd.com>
Tom Stellard [Thu, 7 Mar 2013 21:51:13 +0000 (16:51 -0500)]
radeon/llvm: Make radeon_llvm_util.cpp a C file
All the functions in this file are now implemented in C.
Tom Stellard [Thu, 7 Mar 2013 21:51:12 +0000 (16:51 -0500)]
radeon/llvm: Optimize radeon_llvm_strip_unused_kernels()
Just delete unused kernels rather than marking them as internal and
running the GlobalDCE pass.
Also implement this function in C and inline it into
radeon_llvm_get_kernel_module()
Tom Stellard [Thu, 7 Mar 2013 21:51:11 +0000 (16:51 -0500)]
radeon/llvm: Implement radeon_llvm_get_kernel_module() using the C API
Tom Stellard [Thu, 7 Mar 2013 21:51:10 +0000 (16:51 -0500)]
radeon/llvm: Implement radeon_llvm_get_num_kernels() using the C API
Tom Stellard [Thu, 7 Mar 2013 21:51:09 +0000 (16:51 -0500)]
radeon/llvm: Implement radeon_llvm_parse_bitcode() using C API
Also make the function static since it is not used anywhere else.
Tom Stellard [Thu, 7 Mar 2013 21:51:08 +0000 (16:51 -0500)]
r600g/llvm: Move llvm wrapper functions into the radeon directory
Jon TURNEY [Wed, 27 Feb 2013 15:32:37 +0000 (15:32 +0000)]
Properly check GLX_INDIRECT_RENDERING in glapi/tests/check_table
Actually use $DEFINES, so we can see if GLX_INDIRECT_RENDERING is defined
If GLX_INDIRECT_RENDERING is defined, _GLAPI_SKIP_PROTO_ENTRY_POINTS will
be defined, and libglapi won't contain the 'protocol entry points', so we
should provide stubs in check_table.cpp
Jon TURNEY [Wed, 27 Feb 2013 12:58:17 +0000 (12:58 +0000)]
Fix glapi/tests/check_table.cpp for standardized OpenGL function names
It looks like this has been broken since commit
1a1db1746db82efc7f0643508886dfc78a15eb71 "Standardize names of OpenGL
functions."
Signed-off-by: Jon TURNEY <jon.turney@dronecode.org.uk>
Jon TURNEY [Tue, 26 Feb 2013 16:02:13 +0000 (16:02 +0000)]
Fix out-of-tree build of 'make check' in src/mapi/glapi/tests/
Signed-off-by: Jon TURNEY <jon.turney@dronecode.org.uk>
José Fonseca [Wed, 13 Mar 2013 13:13:08 +0000 (13:13 +0000)]
scons: Define PACKAGE_VERSION/BUGREPORT globally.
Fixes the scons build.
Vinson Lee [Wed, 13 Mar 2013 05:32:47 +0000 (22:32 -0700)]
tests: Add $(top_srcdir)/include to AM_CPPFLAGS.
Fixes this build error with make check.
CC collision.o
In file included from ../../../../../src/mesa/main/hash_table.h:34:0,
from collision.c:31:
../../../../../src/mesa/main/compiler.h:51:53: fatal error: c99_compat.h: No such file or directory
Signed-off-by: Vinson Lee <vlee@freedesktop.org>
José Fonseca [Wed, 13 Mar 2013 01:25:30 +0000 (01:25 +0000)]
scons: Define PACKAGE_xxx
Should get the builds going again.
Brian Paul [Tue, 12 Mar 2013 00:31:22 +0000 (18:31 -0600)]
docs: rewrite the OSMesa info / instructions
Reviewed-by: José Fonseca <jfonseca@vmware.com>
Brian Paul [Tue, 12 Mar 2013 00:31:21 +0000 (18:31 -0600)]
configure: wire-up new OSMesa gallium state tracker and target
Reviewed-by: José Fonseca <jfonseca@vmware.com>
Brian Paul [Tue, 12 Mar 2013 00:31:21 +0000 (18:31 -0600)]
target/osmesa: add new Makefile.am
Reviewed-by: José Fonseca <jfonseca@vmware.com>
Brian Paul [Tue, 12 Mar 2013 00:31:21 +0000 (18:31 -0600)]
targets/osmesa: new OSMesa gallium target
Reviewed-by: José Fonseca <jfonseca@vmware.com>
Brian Paul [Tue, 12 Mar 2013 00:31:21 +0000 (18:31 -0600)]
st/osmesa: add new Makefile.am
Reviewed-by: José Fonseca <jfonseca@vmware.com>
Brian Paul [Tue, 12 Mar 2013 00:31:21 +0000 (18:31 -0600)]
st/osmesa: new OSMesa gallium state tracker
Reviewed-by: José Fonseca <jfonseca@vmware.com>
Brian Paul [Tue, 12 Mar 2013 00:31:21 +0000 (18:31 -0600)]
st/mesa: add PIPE_FORMAT_R16G16B16A16_UNORM renderbuffer support
To allow rendering in 16-bit/channel RGBA buffers.
Reviewed-by: José Fonseca <jfonseca@vmware.com>
José Fonseca [Wed, 13 Mar 2013 00:31:03 +0000 (00:31 +0000)]
scons: Re-add ','
José Fonseca [Wed, 13 Mar 2013 00:16:24 +0000 (00:16 +0000)]
autotools: Add missing top-level include dir.
Fixes autotools build failure. Not sure if there are more, as I have
difficulties in building the full tree.
Matt Turner [Wed, 13 Mar 2013 00:09:55 +0000 (17:09 -0700)]
configure.ac: Alphabetize freedreno makefiles.
Matt Turner [Fri, 22 Feb 2013 00:51:19 +0000 (16:51 -0800)]
build: Get rid of dead MESA_ASM_FILES variable
Reviewed-by: Eric Anholt <eric@anholt.net>
Matt Turner [Fri, 22 Feb 2013 00:51:03 +0000 (16:51 -0800)]
mesa/build: Get rid of dead ALL_FILES variable
Reviewed-by: Eric Anholt <eric@anholt.net>
Matt Turner [Fri, 22 Feb 2013 01:03:18 +0000 (17:03 -0800)]
xmlpool/.gitignore: Remove 'Makefile'
Handled by top level .gitignore.
Reviewed-by: Eric Anholt <eric@anholt.net>
Matt Turner [Sat, 9 Mar 2013 08:28:09 +0000 (00:28 -0800)]
mesa: Use PACKAGE_BUGREPORT macro.
Reviewed-by: Eric Anholt <eric@anholt.net>
Matt Turner [Sat, 9 Mar 2013 08:23:20 +0000 (00:23 -0800)]
mesa: Remove unused version #defines from version.h.
Reviewed-by: Eric Anholt <eric@anholt.net>
Matt Turner [Sat, 9 Mar 2013 08:25:45 +0000 (00:25 -0800)]
mesa: Replace MESA_VERSION with PACKAGE_VERSION.
One fewer place to have to update.
Reviewed-by: Eric Anholt <eric@anholt.net>
Zack Rusin [Tue, 12 Mar 2013 20:41:35 +0000 (13:41 -0700)]
draw/so: Fix stream output with geometry shaders
If geometry shader is present its stream output info should
be used instead of the vs and we shouldn't use the pre-clipped
corrdinates.
Signed-off-by: Zack Rusin <zackr@vmware.com>
Reviewed-by: José Fonseca <jfonseca@vmware.com>
José Fonseca [Tue, 12 Mar 2013 20:37:47 +0000 (20:37 +0000)]
include: Fix build with VS 11 (i.e, 2012).
NOTE: Candidate for the stable branches.
Reviewed-by: Brian Paul <brianp@vmware.com>
José Fonseca [Tue, 12 Mar 2013 11:17:49 +0000 (11:17 +0000)]
mesa,gallium,egl,mapi: One definition of C99 inline/__func__ to rule them all.
We were in four already...
NOTE: Candidate for the stable branches.
Reviewed-by: Brian Paul <brianp@vmware.com>
José Fonseca [Tue, 12 Mar 2013 20:33:38 +0000 (20:33 +0000)]
scons: Allows choosing VS 10 or 11.
NOTE: Candidate for the stable branches.
Reviewed-by: Brian Paul <brianp@vmware.com>
Michel Dänzer [Tue, 12 Mar 2013 11:34:37 +0000 (12:34 +0100)]
radeonsi: Fix off-by-one for maximum vertex element index in some cases
In cases where the vertex element size is smaller than the vertex buffer
stride, the previous calculation could end up 1 too low. This would result
in the GPU using index 0 instead of the maximum index for those elements,
which would be visible as intermittent distorted triangles.
NOTE: This is a candidate for the 9.1 branch.
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Christoph Bumiller [Mon, 11 Mar 2013 19:53:25 +0000 (20:53 +0100)]
nvc0: avoid crash on updating RASTERIZE_ENABLE state
When doing a blit with the 3D engine, the rasterizer or zsa cso may
be NULL.
Christoph Bumiller [Fri, 1 Mar 2013 15:45:47 +0000 (16:45 +0100)]
gallium/tests: check format in compute tests, make selectable
Christoph Bumiller [Sat, 9 Mar 2013 16:17:14 +0000 (17:17 +0100)]
nvc0: add MP trap handler for nve4
Christoph Bumiller [Sat, 9 Mar 2013 11:11:38 +0000 (12:11 +0100)]
nvc0: they removed the NTID,NCTAID,GRIDID registers on nve4
Christoph Bumiller [Sat, 23 Feb 2013 18:40:23 +0000 (19:40 +0100)]
nvc0: implement compute support for nve4
Christoph Bumiller [Mon, 11 Mar 2013 16:34:43 +0000 (17:34 +0100)]
nvc0/ir: try to fix CAS (CompareAndSwap)
Christoph Bumiller [Mon, 11 Mar 2013 16:34:05 +0000 (17:34 +0100)]
nv50/ir: add CCTL (cache control) op
Christoph Bumiller [Mon, 11 Mar 2013 16:32:52 +0000 (17:32 +0100)]
nvc0/ir/emit: fix emission of large address offsets
Christoph Bumiller [Fri, 8 Mar 2013 21:40:30 +0000 (22:40 +0100)]
nvc0: add SHADER/COMPUTE_RESOURCE bind flags to format table
Christoph Bumiller [Sat, 2 Mar 2013 17:27:56 +0000 (18:27 +0100)]
nouveau: align PIPE_BIND_SHADER,COMPUTE_RESOURCEs to 256 bytes
Christoph Bumiller [Fri, 1 Mar 2013 20:37:37 +0000 (21:37 +0100)]
nv50,nvc0: copy writable flag on surface creation
Christoph Bumiller [Sat, 2 Mar 2013 20:00:26 +0000 (21:00 +0100)]
nv50/ir: add support for different sampler and resource index on nve4
And remove non-working code for indirect sampler/resource selection.
Will be added back later.
Includes code from "nv50/ir/tgsi: Resource indirect indexing" by
Francisco Jerez (when mixing the R and S handles we can only specify
them via a register, i.e. indirectly, unless we upload all the used
handle combinations to c[] space, which we don't for now).
Christoph Bumiller [Sat, 2 Mar 2013 13:59:06 +0000 (14:59 +0100)]
nv50/ir: implement splitting of 64 bit ops after RA
Christoph Bumiller [Thu, 28 Feb 2013 21:08:36 +0000 (22:08 +0100)]
nvc0/ir: skip back edges when determining latest sched value
Christoph Bumiller [Thu, 28 Feb 2013 18:07:24 +0000 (19:07 +0100)]
nvc0/ir: use large issue delay after RET, too
Christoph Bumiller [Thu, 28 Feb 2013 18:00:02 +0000 (19:00 +0100)]
nv50/ir: fix size adjustment for sched info for multiple functions
Christoph Bumiller [Wed, 27 Feb 2013 20:02:29 +0000 (21:02 +0100)]
nv50/ir: print function inputs and outputs
Christoph Bumiller [Wed, 27 Feb 2013 14:32:35 +0000 (15:32 +0100)]
nv50/ir/ssa: add a few comments regarding RenamePass
Francisco Jerez [Mon, 25 Feb 2013 20:57:32 +0000 (21:57 +0100)]
nv50/ir/tgsi: Exclude local declarations from function prototypes.
Christoph Bumiller [Mon, 25 Feb 2013 14:52:10 +0000 (15:52 +0100)]
nv50/ir/opt: try to make use of SUCLAMP addend
Christoph Bumiller [Sun, 24 Feb 2013 17:36:44 +0000 (18:36 +0100)]
nv50/ir: don't assert on type in Modifier.applyTo if it is 0
Christoph Bumiller [Sat, 23 Feb 2013 12:09:32 +0000 (13:09 +0100)]
nv50/ir: add support for barriers
nv50 part by Francisco Jerez.
Christoph Bumiller [Wed, 20 Feb 2013 20:33:38 +0000 (21:33 +0100)]
nv50/ir/tgsi: add support for atomics
Christoph Bumiller [Fri, 22 Feb 2013 23:39:23 +0000 (00:39 +0100)]
nv50/ir/tgsi: handle TGSI_OPCODE_LOAD,STORE
Squashed and (heavily) modified original patches by Francisco Jerez:
nv50/ir/tgsi: Implement resource LOAD/STORE (wip).
nv50/ir/tgsi: Emit SUST/SULD for surface access, and add CB LOAD/STORE support
nv50/ir/tgsi: Fix/clean up the LOAD/STORE handling code.
Left out for now:
nv50/ir/tgsi: Resource indirect indexing
Treating raw, read-only surfaces as constant buffers (CBs) was removed
because CBs are limited to a size of 64 KiB which isn't desireable, and
because this decision should probably be made by the state tracker.
If we used a number of CB slots for surfaces, it might find that we
cannot accomodate the advertised limit.
Christoph Bumiller [Thu, 28 Feb 2013 20:05:45 +0000 (21:05 +0100)]
nvc0/ir: don't replace load from input in COMPUTE progs with VFETCH
Christoph Bumiller [Fri, 22 Feb 2013 23:00:27 +0000 (00:00 +0100)]
nvc0/ir: implement lowering of surface ops for nve4
Christoph Bumiller [Tue, 19 Feb 2013 21:12:01 +0000 (22:12 +0100)]
nvc0/ir: add formatted surface load lib code, move to extra header
OpenGL is nice and makes the user specify a format with an image unit.
OpenCL is evil and doesn't, and what's better than adding a huge load
of functions that we call indirectly to handle the conversion ?
Christoph Bumiller [Sun, 17 Feb 2013 11:01:55 +0000 (12:01 +0100)]
nv50/ir: extend moveSources for delta < 0
Christoph Bumiller [Fri, 22 Feb 2013 19:46:28 +0000 (20:46 +0100)]
nvc0/ir: lower atomics in s[]
Christoph Bumiller [Fri, 22 Feb 2013 19:35:32 +0000 (20:35 +0100)]
nvc0/ir/emit: implement INSBF, EXTBF, PERMT and ATOM
Christoph Bumiller [Wed, 20 Feb 2013 19:54:14 +0000 (20:54 +0100)]
nv50/ir/emit: handle OP_ATOM