Marek Olšák [Tue, 26 Jan 2016 21:39:24 +0000 (22:39 +0100)]
radeonsi: move a few r600_can_dump_shader calls to where they're needed
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Tue, 26 Jan 2016 16:27:54 +0000 (17:27 +0100)]
radeonsi: remove useless code that handles dx10_clamp_mode
"enable-no-nans-fp-math" is a wrong string and there was a disagreement
about fixing it.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Tue, 26 Jan 2016 21:16:55 +0000 (22:16 +0100)]
radeonsi: dump SPI_PS_INPUT values along with shader stats
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Wed, 6 Jan 2016 15:03:38 +0000 (16:03 +0100)]
radeonsi: read SPI_PS_INPUT_ADDR from LLVM if it returns it
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Sat, 9 Jan 2016 13:33:38 +0000 (14:33 +0100)]
radeonsi: don't force gl_SampleMaskIn to 1 for smoothing
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Fri, 1 Jan 2016 23:41:43 +0000 (00:41 +0100)]
radeonsi: split PS input interpolation code into its own function
This will be used by the fragment shader prolog.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Sun, 3 Jan 2016 18:00:29 +0000 (19:00 +0100)]
radeonsi: implement forcing per-sample_interpolation using the shader key only
It was partly a state and partly emulated by shader code, but since we want
to do this in a fragment shader prolog, we need to put it into the shader
key, which will be used to generate the prolog.
This also removes the spi_ps_input states and moves the registers
to the PS state.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Sat, 2 Jan 2016 02:18:03 +0000 (03:18 +0100)]
radeonsi: remove si_shader::ps_input_interpolate
tgsi_shader_info has this too.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Sat, 2 Jan 2016 01:54:29 +0000 (02:54 +0100)]
radeonsi: move BCOLOR PS input locations after all other inputs
BCOLOR inputs were immediately after COLOR inputs. Thus, all following inputs
were offset by 1 if color_two_side was enabled, and not offset if it was not
enabled, which is a variation that's problematic if we want to have 1 variant
per shader and the variant doesn't care about color_two_side (that should be
handled by other bytecode attached at the beginning).
Instead, move BCOLOR inputs after all other inputs, so BCOLOR0 is at location
"num_inputs" if it's present. BCOLOR1 is next.
This also allows removing si_shader::nparam and
si_shader::ps_input_param_offset, which are useless now.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Sat, 2 Jan 2016 01:25:51 +0000 (02:25 +0100)]
radeonsi: move SPI_PS_INPUT_CNTL value computation to a separate function
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Fri, 1 Jan 2016 18:44:16 +0000 (19:44 +0100)]
radeonsi: generate a color_two_side variant only if the shader reads colors
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Sun, 27 Dec 2015 19:10:33 +0000 (20:10 +0100)]
radeonsi: move si_shader_context initialization into a separate function
This will be re-used later.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Sat, 30 Jan 2016 15:43:53 +0000 (16:43 +0100)]
st/mesa: remove st_is_program_native
The default scenario sets GL_TRUE too.
Reviewed-by: Edward O'Callaghan <eocallaghan@alterapraxis.com>
Marek Olšák [Sat, 30 Jan 2016 15:34:20 +0000 (16:34 +0100)]
st/mesa: unify destroy_program_variants cases for TCS, TES, GS
Reviewed-by: Edward O'Callaghan <eocallaghan@alterapraxis.com>
Marek Olšák [Sat, 30 Jan 2016 15:24:29 +0000 (16:24 +0100)]
st/mesa: unify get_variant functions for TCS, TES, GS
Reviewed-by: Edward O'Callaghan <eocallaghan@alterapraxis.com>
Marek Olšák [Sat, 30 Jan 2016 14:10:11 +0000 (15:10 +0100)]
st/mesa: unify variants and delete functions for TCS, TES, GS
no difference between those
Reviewed-by: Edward O'Callaghan <eocallaghan@alterapraxis.com>
Brian Paul [Tue, 9 Feb 2016 16:58:39 +0000 (09:58 -0700)]
mesa: fix incorrect viewport position when GL_CLIP_ORIGIN = GL_LOWER_LEFT
Ilia Mirkin found/fixed the mistake.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=93813
Cc: "11.1" <mesa-stable@lists.freedesktop.org>
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Brian Paul [Tue, 9 Feb 2016 00:50:23 +0000 (17:50 -0700)]
mesa: rewrite save_CallLists() code
When glCallLists() is compiled into a display list, preserve the call
as a single glCallLists rather than 'n' glCallList calls. This will
matter for an upcoming display list optimization project.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Brian Paul [Mon, 8 Feb 2016 22:30:39 +0000 (15:30 -0700)]
mesa: add missing error check in _mesa_CallLists()
Generate GL_INVALID_VALUE if n < 0. Return early if n==0 or lists==NULL.
v2: fix formatting, also check for lists==NULL.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Brian Paul [Mon, 8 Feb 2016 18:29:07 +0000 (11:29 -0700)]
mesa: whitespace clean-ups in dlist.h
And remove 'extern' qualifiers.
Brian Paul [Mon, 8 Feb 2016 16:59:40 +0000 (09:59 -0700)]
st/mesa: don't allocate bitmap drawing state until needed
Most apps don't use glBitmap so don't allocate the bitmap cache or
gallium state objects/shaders/etc until the first call to st_Bitmap().
v2: simplify a conditional, per Gustaw Smolarczyk.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Brian Paul [Wed, 3 Feb 2016 00:24:34 +0000 (17:24 -0700)]
st/mesa: move the setup_bitmap_vertex_data() code into draw_bitmap_quad()
Now all the code to setup the vertex data and draw it is in one place.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Brian Paul [Wed, 3 Feb 2016 00:12:46 +0000 (17:12 -0700)]
st/mesa: refactor some bitmap drawing code
Move setup/restoration of rendering state into helper functions.
This makes the draw_bitmap_quad() function much more concise.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Ilia Mirkin [Fri, 5 Feb 2016 02:55:13 +0000 (21:55 -0500)]
mesa: remove hack to fix up GL_ANY_SAMPLES_PASSED results
Both st/mesa and i965 should return a true/false result now, and the
only other driver implementing queries (radeon) doesn't support
ARB_occlusion_query2 which added that pname.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Ilia Mirkin [Fri, 5 Feb 2016 02:51:58 +0000 (21:51 -0500)]
st/mesa: make use of the occlusion predicate query
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Ilia Mirkin [Thu, 4 Feb 2016 17:48:29 +0000 (12:48 -0500)]
nv50: add PIPE_QUERY_OCCLUSION_PREDICATE support
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Ilia Mirkin [Thu, 4 Feb 2016 17:48:06 +0000 (12:48 -0500)]
nv30: add PIPE_QUERY_OCCLUSION_PREDICATE support
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Ilia Mirkin [Thu, 4 Feb 2016 17:47:42 +0000 (12:47 -0500)]
ilo: add PIPE_QUERY_OCCLUSION_PREDICATE support
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Chia-I Wu <olvaffe@gmail.com>
Nicolai Hähnle [Thu, 21 Jan 2016 21:10:11 +0000 (16:10 -0500)]
draw: use util_pstipple_* function for stipple pattern textures and samplers
This reduces code duplication.
Suggested-by: Jose Fonseca <jfonseca@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Nicolai Hähnle [Thu, 21 Jan 2016 21:03:17 +0000 (16:03 -0500)]
draw: use util_pstipple_create_fragment_shader
This reduces code duplication. It also adds support for drivers where the
fragment position is a system value.
Suggested-by: Jose Fonseca <jfonseca@vmware.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Marek Olšák [Sun, 7 Feb 2016 19:25:01 +0000 (20:25 +0100)]
winsys/radeon: fix a wrong NUM_TILE_PIPES value from the kernel
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94019
Tested-by: Nick Sarnie <commendsarnex@gmail.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Timothy Arceri [Tue, 2 Feb 2016 00:53:57 +0000 (11:53 +1100)]
nir: remove unused nir_variable fields
These are used in GLSL IR to removed unused varyings and match
transform feedback variables. There is no need to use these in NIR.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Timothy Arceri [Fri, 29 Jan 2016 23:50:12 +0000 (10:50 +1100)]
glsl: remove unrequired forward declaration
This was added in
2548092ad80156a4 although I don't see why as it
was already in the linker.h header.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Timothy Arceri [Fri, 22 Jan 2016 22:08:23 +0000 (09:08 +1100)]
glsl: clean up and fix bug in varying linking rules
The existing code was very hard to follow and has been the source
of at least 3 bugs in the past year.
The existing code also has a bug for SSO where if we have a
multi-stage SSO for example a tes -> gs program, if we try to use
transform feedback with gs the existing code would look for the
transform feedback varyings in the tes stage and fail as it can't
find them.
V2: Add more code comments, always try to remove unused inputs
to the first stage.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Timothy Arceri [Wed, 27 Jan 2016 05:16:01 +0000 (16:16 +1100)]
glsl: simplify ES Vertex/Fragment shader requirements
We really just needed to skip the existing ES < 3.1 check if we have
a compute shader, all other scenarios are already covered.
* No shaders is a link error.
* Geom or Tess without Vertex is a link error which means we always
require a Vertex shader and hence a Fragment shader.
* Finally a Compute shader linked with any other stage is a link error.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Timothy Arceri [Wed, 27 Jan 2016 04:42:58 +0000 (15:42 +1100)]
glsl: simplify required stages for linking rules
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Timothy Arceri [Wed, 27 Jan 2016 04:34:53 +0000 (15:34 +1100)]
glsl: small tidy up now that link_shaders() exits early with 0 shaders
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Timothy Arceri [Mon, 25 Jan 2016 10:56:18 +0000 (21:56 +1100)]
glsl: don't attempt to link empty program
Previously an empty program would go through the entire
link_shaders() function and we would have to be careful
not to cause a segfault.
In core profile also now set link_status to false by
generating an error, it was previously set to true.
From Section 7.3 (PROGRAM OBJECTS) of the OpenGL 4.5 spec:
"Linking can fail for a variety of reasons as specified in the
OpenGL Shading Language Specification, as well as any of the
following reasons:
- No shader objects are attached to program."
V2: Only generate an error in core profile and add spec quote (Ian)
V3: generate error in ES too, remove previous check which was only
applying the rule to GL 4.5/ES 3.1 and above. My understand is that
this spec change is clarifying previously undefined behaviour and
therefore should be applied retrospectively. The ES CTS tests for
this are in ES 2 I suspect it was passing because it would have
generated an error for not having both a vertex and fragment shader.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Matt Turner [Tue, 2 Feb 2016 00:44:18 +0000 (16:44 -0800)]
nir: Recognize open-coded bitfield_reverse.
Helps 11 shaders in UnrealEngine4 demos.
I seriously hope they would have given us bitfieldReverse() if we
exposed GL 4.0 (but we do expose ARB_gpu_shader5, so why not use that
anyway?).
instructions in affected programs: 4875 -> 4633 (-4.96%)
cycles in affected programs: 270516 -> 244516 (-9.61%)
I suspect there's a *lot* of room to improve nir_search/opt_algebraic's
handling of this. We'd actually like to match, e.g., step2 by matching
step1 once and then doing a pointer comparison for the second instance
of step1, but unfortunately we generate an enormous tuple for instead.
The .text size increases by 6.5% and the .data by 17.5%.
text data bss dec hex filename
22957 45224 0 68181 10a55 nir_libnir_la-nir_opt_algebraic.o
24461 53160 0 77621 12f35 nir_libnir_la-nir_opt_algebraic.o
I'd be happy to remove this if Unreal4 uses bitfieldReverse() if it is
in a GL 4.0 context once we expose GL 4.0.
Reviewed-by: Jason Ekstrand <jason.ekstrand@intel.com>
Matt Turner [Tue, 2 Feb 2016 00:35:41 +0000 (16:35 -0800)]
nir: Handle large unsigned values in opt_algebraic.
The next patch adds an algebraic rule that uses the constant 0xff00ff00.
Without this change, the build fails with
return hex(struct.unpack('I', struct.pack('i', self.value))[0])
struct.error: 'i' format requires -
2147483648 <= number <=
2147483647
The hex() function handles integers of any size, and assigning a
negative value to an unsigned does what we want in C. The pack/unpack is
unnecessary (and as we see, buggy).
Reviewed-by: Dylan Baker <baker.dylan.c@gmail.com>
Matt Turner [Thu, 4 Feb 2016 20:04:42 +0000 (12:04 -0800)]
nir: Do opt_algebraic in reverse order.
Walking the SSA definitions in order means that we consider the smallest
algebraic optimizations before larger optimizations. So if a smaller
rule is part of a larger rule, the smaller one will happen first,
preventing the larger one from happening.
instructions in affected programs: 32721 -> 32611 (-0.34%)
helped: 106
In programs whose nir_optimize loop count changes (129 of them):
before: 1164 optimization loops
after: 1071 optimization loops
Of the 129 affected, 16 programs' optimization loop counts increased.
Prevents regressions and annoyances in the next commits.
Reviewed-by: Eduardo Lima Mitev <elima@igalia.com>
Reviewed-by: Jason Ekstrand <jason.ekstrand@intel.com>
Matt Turner [Thu, 4 Feb 2016 20:00:15 +0000 (12:00 -0800)]
nir: Recognize product of open-coded pow()s.
Prevents regressions in the next commit.
Reviewed-by: Jason Ekstrand <jason.ekstrand@intel.com>
Matt Turner [Tue, 2 Feb 2016 00:34:46 +0000 (16:34 -0800)]
nir: Add opt_algebraic rules for xor with zero.
instructions in affected programs: 668 -> 664 (-0.60%)
helped: 4
Reviewed-by: Eduardo Lima Mitev <elima@igalia.com>
Reviewed-by: Jason Ekstrand <jason.ekstrand@intel.com>
Timothy Arceri [Fri, 5 Feb 2016 02:08:19 +0000 (13:08 +1100)]
glsl: validate arrays of arrays on empty type delclarations
Fixes:
dEQP-GLES31.functional.shaders.arrays_of_arrays.invalid.empty_declaration_without_var_name_fragment
dEQP-GLES31.functional.shaders.arrays_of_arrays.invalid.empty_declaration_without_var_name_vertex
Reviewed-by: Dave Airlie <airlied@redhat.com>
Kenneth Graunke [Fri, 22 Jan 2016 00:37:20 +0000 (16:37 -0800)]
i965: Use nir_lower_load_const_to_scalar().
I don't know why, but we never hooked up this pass Eric wrote.
Otherwise, you can end up with stupid scalarized code such as:
vec4 ssa_7 = load_const (0.0, 0.0, 0.0, 0.0)
vec4 ssa_8 = ...
vec1 ssa_9 = feq ssa_8, ssa_7
vec1 ssa_10 = feq ssa_8.y, ssa_7.y
vec1 ssa_11 = feq ssa_8, ssa_7.z
vec1 ssa_12 = feq ssa_8.y, ssa_7.w
ssa_8.xyxy == <0, 0, 0, 0> should only take two feq instructions.
shader-db on Skylake:
total instructions in shared programs:
9121153 ->
9120749 (-0.00%)
instructions in affected programs: 32421 -> 32017 (-1.25%)
helped: 277
HURT: 69
total cycles in shared programs:
69003364 ->
69000912 (-0.00%)
cycles in affected programs: 899186 -> 896734 (-0.27%)
helped: 313
HURT: 403
This also prevents regressions when disabling channel expressions.
v2: Don't call opt_cse afterwards (requested by Matt). It should
happen in the optimization loop below anyway.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eduardo Lima Mitev <elima@igalia.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Timothy Arceri [Fri, 5 Feb 2016 22:38:55 +0000 (09:38 +1100)]
mesa: remove now unused sampler index handing code
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Fri, 5 Feb 2016 22:30:00 +0000 (09:30 +1100)]
mesa: compute sampler index in ir_to_mesa rather than using UniformHash
The aim of this is to work towards removing UniformHash from the program
struct so that we don't need to hold onto it in memory and pass it around
outside the linker.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Kenneth Graunke [Thu, 4 Feb 2016 16:10:02 +0000 (08:10 -0800)]
i965: Don't add barrier deps for FB write messages.
There are never render target reads, so there are no scheduling hazards.
Giving the extra flexibility to the scheduler makes it possible to do
FB writes as soon as their sources are available, reducing register
pressure. It also makes it possible to do the payload setup for more
than one FB write message at a time, which could better hide latency.
shader-db results on Skylake:
total instructions in shared programs:
9110254 ->
9110211 (-0.00%)
instructions in affected programs: 2898 -> 2855 (-1.48%)
helped: 3
HURT: 0
LOST: 0
GAINED: 1
A reduction in instruction counts is surprising, but legitimate:
the three shaders helped were spilling, and reducing register
pressure allowed us to issue fewer spills/fills.
total cycles in shared programs:
69035108 ->
68928820 (-0.15%)
cycles in affected programs:
4412402 ->
4306114 (-2.41%)
helped: 4457
HURT: 213
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Connor Abbott <cwabbott0@gmail.com>
Dave Airlie [Thu, 4 Feb 2016 07:38:54 +0000 (17:38 +1000)]
st/mesa: enable AoA for gallium drivers reporting GLSL 1.30
Acked-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Timothy Arceri <timothy.arceri@collabora.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Fri, 5 Feb 2016 02:00:38 +0000 (12:00 +1000)]
st/mesa: add atomic AoA support
reuse the sampler deref handling code to do the same
thing for atomics.
Acked-by: Ilia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Fri, 5 Feb 2016 03:34:29 +0000 (13:34 +1000)]
mesa: drop unused nonconst sampler functions.
Since we fixed the glsl->tgsi conversion we no longer need
this function.
Reviewed-by: Timothy Arceri <timothy.arceri@collabora.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Thu, 4 Feb 2016 06:48:18 +0000 (16:48 +1000)]
st/mesa: handle indirect samplers in arrays/structs properly (v4.1)
The state tracker never handled this properly, and it finally
annoyed me for the second time so I decided to fix it properly.
This is inspired by the NIR sampler lowering code and I only realised
NIR seems to do its deref ordering different to GLSL at the last
minute, once I got that things got much easier.
it fixes a bunch of tests in
tests/spec/arb_gpu_shader5/execution/sampler_array_indexing/
v2: fix AoA tests when forced on.
I was right I didn't need all that code, fixing the AoA code
meant cleaning up a chunk of code I didn't like in the array
handling.
v3: start generalising the code a bit more for atomics.
v3.1: use UniformRemapTable
v4: handle uniforms differently using the param_index,
and go back to UniformStorage
fix issues identified by Timothy with deref handling.
v4.1: squash const fix and move handling 1D const out
of recursive function.
Reviewed-by: Timothy Arceri <timothy.arceri@collabora.com>
Acked-by: Ilia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Mon, 8 Feb 2016 01:09:29 +0000 (11:09 +1000)]
glsl/ir: add param index to variable.
We have a requirement to store the index into the mesa parameterlist
for uniforms. Up until now we've overwritten var->data.location with
this info. However this then stops us accessing UniformStorage,
which is needed to do proper dereferencing.
Add a new variable to ir_variable to store this value in, and change
the two uses to use it correctly.
Reviewed-by: Timothy Arceri <timothy.arceri@collabora.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Francisco Jerez [Thu, 14 Jan 2016 20:20:46 +0000 (12:20 -0800)]
i965: Rename define for the PIPE_CONTROL DC flush bit.
Its previous name was somewhat misleading, this really behaves like a
RW cache flush rather than an invalidation.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Thu, 14 Jan 2016 20:17:01 +0000 (12:17 -0800)]
i965: Invalidate state cache before L3 partitioning set-up.
The state cache is also L3-backed so it seems sensible to make sure
it's clean as we do for other RO caches before repartitioning the L3.
This wasn't part of my original L3 partitioning code because I was
able to reproduce hangs on Gen7 hardware when the state cache
invalidation happened asynchronously with previous 3D rendering, which
should no longer be possible after the previous change.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Thu, 14 Jan 2016 19:22:46 +0000 (11:22 -0800)]
i965: Fix cache pollution race during L3 partitioning set-up.
We need to split the stalling flush from the RO cache invalidation
into a different PIPE_CONTROL command to make sure that the top of the
pipe invalidation happens after any previous rendering is complete.
Otherwise it's possible for previous rendering to pollute the L3 cache
in the short window of time between RO invalidation and the completion
of the stalling flush. Fixes rendering artifacts on Unigine Heaven,
Metro Last Light Redux and Metro 2033 Redux.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=93540
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=93599
Tested-by: Darius Spitznagel <d.spitznagel@goodbytez.de>
Tested-by: Martin Peres <martin.peres@linux.intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Sun, 7 Feb 2016 02:43:45 +0000 (18:43 -0800)]
i965/fs: Don't emit unnecessary SEL instruction from emit_image_atomic().
The SEL instruction with predication mode NONE emitted when the atomic
operation doesn't need to be predicated is a no-op and might rely on
undocumented hardware behaviour. Noticed by chance while looking at
the assembly output.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Matt Turner [Mon, 8 Feb 2016 23:32:12 +0000 (15:32 -0800)]
i965/vec4: Update vec4 unit tests for commit
01dacc83ff.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94050
Brian Paul [Mon, 8 Feb 2016 17:52:02 +0000 (10:52 -0700)]
dri/common: include debug_output.h to silence warning
Brian Paul [Mon, 8 Feb 2016 16:29:38 +0000 (09:29 -0700)]
tgsi: minor whitespace fixes in tgsi_scan.c
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Edward O'Callaghan <eocallaghan@alterapraxis.com>
Brian Paul [Mon, 8 Feb 2016 16:29:38 +0000 (09:29 -0700)]
tgsi: s/true/TRUE/ in tgsi_scan.c
Just to be consistent.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Edward O'Callaghan <eocallaghan@alterapraxis.com>
Brian Paul [Mon, 8 Feb 2016 16:29:38 +0000 (09:29 -0700)]
tgsi: use switches instead of big if/else ifs
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Edward O'Callaghan <eocallaghan@alterapraxis.com>
Brian Paul [Mon, 8 Feb 2016 16:29:38 +0000 (09:29 -0700)]
tgsi: break gigantic tgsi_scan_shader() function into pieces
New functions for examining instructions, declarations, etc.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Edward O'Callaghan <eocallaghan@alterapraxis.com>
Brian Paul [Mon, 8 Feb 2016 16:29:38 +0000 (09:29 -0700)]
st/mesa: minor formatting fixes in st_cb_bitmap.c
Brian Paul [Mon, 8 Feb 2016 16:29:38 +0000 (09:29 -0700)]
mesa: move GL_ARB_debug_output code into new debug_output.c file
The errors.c file had grown quite large so split off this extension
code into its own file. This involved making a handful of functions
non-static.
Acked-by: Timothy Arceri <timothy.arceri@collabora.com>
Brian Paul [Mon, 8 Feb 2016 16:29:38 +0000 (09:29 -0700)]
gallium/util: whitespace, formatting fixes in u_debug_stack.c
Brian Paul [Mon, 8 Feb 2016 16:29:38 +0000 (09:29 -0700)]
gallium/util: whitespace, formatting fixes in u_staging.[ch] files
Still some nonsensical comments.
Brian Paul [Mon, 8 Feb 2016 16:29:38 +0000 (09:29 -0700)]
gallium/util: switch over to new u_debug_image.[ch] code
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Brian Paul [Mon, 8 Feb 2016 16:29:38 +0000 (09:29 -0700)]
gallium/util: put image dumping functions into separate file
To try to reduce the clutter in u_debug.[ch]
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Brian Paul [Mon, 8 Feb 2016 16:29:38 +0000 (09:29 -0700)]
gallium/util: whitespace, formatting fixes in u_debug.c
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Samuel Pitoiset [Sun, 7 Feb 2016 22:27:48 +0000 (23:27 +0100)]
trace: add missing pipe_context::clear_texture()
This fixes a crash with bin/arb_clear_texture-base-formats and
probably some other tests which use clear_texture().
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Samuel Pitoiset [Sun, 7 Feb 2016 21:33:33 +0000 (22:33 +0100)]
trace: remove useless MALLOC() in trace_context_draw_vbo()
There is no need to allocate memory when unwrapping the indirect buf.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Vinson Lee [Sat, 6 Feb 2016 07:16:31 +0000 (23:16 -0800)]
mesa/extensions: Fix NVX_gpu_memory_info lexicographical order.
Fixes MesaExtensionsTest.AlphabeticallySorted.
Fixes: 1d79b9958090 ("mesa: implement GL_NVX_gpu_memory_info (v2)")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94016
Signed-off-by: Vinson Lee <vlee@freedesktop.org>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Ilia Mirkin [Sat, 6 Feb 2016 22:08:29 +0000 (17:08 -0500)]
glsl: return cloned signature, not the builtin one
The builtin data can get released with a glReleaseShaderCompiler call.
We're careful everywhere to clone everything that comes out of builtins
except here, where we accidentally return the signature belonging to the
builtin version, rather than the locally-cloned one.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Timothy Arceri <timothy.arceri@collabora.com>
Tested-by: Rob Herring <robh@kernel.org>
Cc: mesa-stable@lists.freedesktop.org
Ilia Mirkin [Sat, 6 Feb 2016 22:07:59 +0000 (17:07 -0500)]
glsl: make sure builtins are initialized before getting the shader
The builtin function shader is part of the builtin state, released
when glReleaseShaderCompiler is called. We must ensure that the
builtins have been (re)initialized before attempting to link with the
builtin shader.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Timothy Arceri <timothy.arceri@collabora.com>
Tested-by: Rob Herring <robh@kernel.org>
Cc: mesa-stable@lists.freedesktop.org
Samuel Pitoiset [Sat, 6 Feb 2016 19:24:41 +0000 (20:24 +0100)]
tgsi: use TGSI_WRITEMASK_XYZW instead of hardcoding the mask
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Serge Martin <edb+mesa@sigluy.net>
Timothy Arceri [Tue, 2 Feb 2016 22:46:56 +0000 (09:46 +1100)]
glsl: don't generate transform feedback candidate when not required
If we are not even looking for one don't bother generating a candidate
list.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Timothy Arceri [Tue, 2 Feb 2016 22:39:10 +0000 (09:39 +1100)]
glsl: replace unreachable code with an assert()
All interface blocks will have been lowered by this point so just
use an assert. Returning false would have caused all sorts of
problems if they were not lowered yet and there is an assert to
catch this later anyway.
We also update the tests to reflect this change.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Jan Vesely [Fri, 5 Feb 2016 22:54:57 +0000 (17:54 -0500)]
r600, compute: Do not overwrite pipe_resource.screen
found by inspection.
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Jan Vesely [Fri, 5 Feb 2016 17:01:13 +0000 (12:01 -0500)]
r600g: Ignore format for PIPE_BUFFER targets
Fixes compute since
7dd31b81fee7fe40bd09cf3fbc324fcc32782479
gallium/radeon: support PIPE_CAP_SURFACE_REINTERPRET_BLOCKS
Signed-off-by: Jan Vesely <jan.vesely@rutgers.edu>
Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Marek Olšák [Fri, 5 Feb 2016 18:38:40 +0000 (19:38 +0100)]
mesa/get: fix a breakage after rebase
trivial.
Matt Turner [Mon, 18 Jan 2016 01:30:14 +0000 (20:30 -0500)]
i965/vec4: don't copy ATTR into 3src instructions with complex swizzles
The vec4 backend, at the end, does this:
if (inst->is_3src()) {
for (int i = 0; i < 3; i++) {
if (inst->src[i].vstride == BRW_VERTICAL_STRIDE_0)
assert(brw_is_single_value_swizzle(inst->src[i].swizzle));
So make sure that we use the same conditions when trying to
copy-propagate. UNIFORMs will be converted to vstride 0 in
convert_to_hw_regs, but so will ATTRs when interleaved (as will happen
in a GS with multiple attributes). Since the vstride is not set at
copy-prop time, infer it by inspecting dispatch_mode and reject ATTRs if
they have non-scalar swizzles and are interleaved.
Fixes assertion errors in dolphin-generated geometry shaders (or
misrendering on opt builds) on Sandybridge or on IVB/HSW with
INTEL_DEBUG=nodualobj.
Co-authored-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=93418
Cc: "11.0 11.1" <mesa-stable@lists.freedesktop.org>
Marek Olšák [Fri, 5 Feb 2016 16:47:13 +0000 (17:47 +0100)]
docs/relnotes: document memory info extensions
Marek Olšák [Tue, 2 Feb 2016 01:09:36 +0000 (02:09 +0100)]
gallium/radeon: implement query_memory_info (v2)
v2: don't use DIV_ROUND_UP (no so useful)
also return eviction stats
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Marek Olšák [Tue, 2 Feb 2016 00:27:55 +0000 (01:27 +0100)]
st/mesa: implement and enable memory info extensions (v2)
v2: assert and return if query_memory_info is not set
rebase
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Marek Olšák [Tue, 2 Feb 2016 00:26:59 +0000 (01:26 +0100)]
mesa: implement GL_ATI_meminfo (v2)
v2: rebase
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Marek Olšák [Tue, 2 Feb 2016 00:22:52 +0000 (01:22 +0100)]
mesa: implement GL_NVX_gpu_memory_info (v2)
v2: implement eviction queries properly
add gl_memory_info structure
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Marek Olšák [Mon, 1 Feb 2016 20:56:50 +0000 (21:56 +0100)]
gallium: add interface for querying memory usage and sizes (v2)
If you're worried about the duplication of some CAPs, we can remove them
later.
v2: add fields for memory eviction stats
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Marek Olšák [Sat, 30 Jan 2016 01:54:47 +0000 (02:54 +0100)]
gallium/radeon: remove radeon_info::r600_tiling_config
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Marek Olšák [Sat, 30 Jan 2016 01:50:34 +0000 (02:50 +0100)]
gallium/radeon: get pipe_interleave_bytes AKA group_bytes from the winsys
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Marek Olšák [Sat, 30 Jan 2016 01:29:32 +0000 (02:29 +0100)]
gallium/radeon: set num_banks in the winsys
amdgpu doesn't have to set this, because radeonsi gets it from tile mode
arrays by default.
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Marek Olšák [Sat, 30 Jan 2016 00:52:58 +0000 (01:52 +0100)]
gallium/radeon: just get num_tile_pipes from the winsys
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Marek Olšák [Sat, 30 Jan 2016 00:44:26 +0000 (01:44 +0100)]
winsys/amdgpu: add an assertion to cik_get_num_tile_pipes (v2)
v2: print an error to stderr
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Marek Olšák [Sat, 30 Jan 2016 00:37:17 +0000 (01:37 +0100)]
winsys/amdgpu: remove an r600-only setting
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Marek Olšák [Sat, 30 Jan 2016 00:27:46 +0000 (01:27 +0100)]
gallium/radeon: rename & reorder members of radeon_info
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Steinar H. Gunderson [Tue, 2 Feb 2016 00:16:51 +0000 (01:16 +0100)]
mesa: Fix locking of GLsync objects.
GLsync objects had a race condition when used from multiple threads
(which is the main point of the extension, really); it could be
validated as a sync object at the beginning of the function, and then
deleted by another thread before use, causing crashes. Fix this by
changing all casts from GLsync to struct gl_sync_object to a new
function _mesa_get_and_ref_sync() that validates and increases
the refcount.
In a similar vein, validation itself uses _mesa_set_search(), which
requires synchronization -- it was called without a mutex held, causing
spurious error returns and other issues. Since _mesa_get_and_ref_sync()
now takes the shared context mutex, this problem is also resolved.
Fixes bug #92757, found while developing Nageru, my live video mixer
(due for release at FOSDEM 2016).
v2: Marek: silence warnings, fix declaration after code
Signed-off-by: Steinar H. Gunderson <sesse@google.com>
Cc: "11.0 11.1" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Fri, 11 Dec 2015 21:03:56 +0000 (16:03 -0500)]
radeonsi: add placeholder MC and SRBM performance counter groups
Yet another change motivated by AMD GPUPerfStudio compatibility. These groups
are not directly accessible from userspace, and AMD GPUPerfStudio does not
actually query them - it just requires them to be there. Hence, adding
a placeholder for now.
Reviewed-by: Edward O'Callaghan <eocallaghan@alterapraxis.com>
Acked-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Fri, 11 Dec 2015 20:58:11 +0000 (15:58 -0500)]
radeonsi: re-order the SQ_xx performance counter blocks
This is yet another change motivated by appeasing AMD GPUPerfStudio's
hardcoding of performance counter group numbers.
Reviewed-by: Edward O'Callaghan <eocallaghan@alterapraxis.com>
Acked-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Fri, 11 Dec 2015 20:42:44 +0000 (15:42 -0500)]
radeonsi: re-order the perfcounter hardware blocks
As documented in the comment, AMD GPUPerfStudio unfortunately hardcodes the
order of performance counter groups. Let's do the pragmatic thing and present
the same order as Catalyst/Crimson.
Reviewed-by: Edward O'Callaghan <eocallaghan@alterapraxis.com>
Acked-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Fri, 11 Dec 2015 20:39:23 +0000 (15:39 -0500)]
gallium/radeon: add GPIN driver query group
This group was used by older versions of AMD GPUPerfStudio (via
AMD_performance_monitor) to identify the GPU family, and GPUPerfStudio
still complains when it isn't available.
Reviewed-by: Edward O'Callaghan <eocallaghan@alterapraxis.com>
Acked-by: Marek Olšák <marek.olsak@amd.com>