Jordan Justen [Mon, 18 Jan 2016 17:44:31 +0000 (09:44 -0800)]
nir: Add support for lowering load/stores of shared variables
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Jordan Justen [Mon, 18 Jan 2016 17:53:44 +0000 (09:53 -0800)]
nir: Add atomic operations on variables
This allows us to first generate atomic operations for shared
variables using these opcodes, and then later we can lower those to
the shared atomics intrinsics with nir_lower_io.
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Jordan Justen [Sat, 9 Jan 2016 01:16:29 +0000 (17:16 -0800)]
nir: Add compute shader shared variable storage class
Previously we were receiving shared variable accesses via a lowered
intrinsic function from glsl. This change allows us to send in
variables instead. For example, when converting from SPIR-V.
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Jordan Justen [Sun, 17 Jan 2016 07:11:16 +0000 (23:11 -0800)]
nir/print: Add space after shader_storage var mode
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Iago Toral Quiroga [Thu, 3 Dec 2015 08:50:49 +0000 (09:50 +0100)]
i965: Skip execution size adjustment for instructions of width 4
This code in brw_set_dest adjusts the execution size of any instruction
with a dst.width < 8. However, we don't want to do this with instructions
operating on doubles, since these will have a width of 4, but still
need an execution size of 8 (for SIMD8). Unfortunately, we can't just check
the size of the operands involved to detect if we are doing an operation on
doubles, because we can have instructions that do operations on double
operands interpreted as UD, operating on any of its 2 32-bit components.
Previous commits have made it so we never emit instructions with a horizontal
width of 4 that don't have the correct execution size set for gen6+, so
we can skip it in this case, avoiding the conflicts with fp64 requirements.
Expanding the same fix to other hardware generations requires many more
changes but since we are not targetting fp64 support on them
wer don't really care for now.
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Samuel Iglesias Gonsalvez [Tue, 15 Dec 2015 08:34:38 +0000 (09:34 +0100)]
i965/vec4/gen6: fix exec_size for MOV with a width of 4 in generate_gs_ff_sync()
Signed-off-by: Samuel Iglesias Gonsalvez <siglesias@igalia.com>
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Samuel Iglesias Gonsalvez [Fri, 4 Dec 2015 09:23:15 +0000 (10:23 +0100)]
i965/vec4/gen6: fix exec_size for instructions with destination width of 4
Signed-off-by: Samuel Iglesias Gonsalvez <siglesias@igalia.com>
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Samuel Iglesias Gonsalvez [Thu, 3 Dec 2015 17:27:39 +0000 (18:27 +0100)]
i965/vec4/gen6: fix exec_size for instructions with width of 4 in generate_gs_svb_write()
Signed-off-by: Samuel Iglesias Gonsalvez <siglesias@igalia.com>
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Samuel Iglesias Gonsalvez [Thu, 3 Dec 2015 17:05:39 +0000 (18:05 +0100)]
i965/gs/gen6: fix execsize for instructions with width of 4 in gen6_sol_program()
v2:
- Add assert (Topi).
Signed-off-by: Samuel Iglesias Gonsalvez <siglesias@igalia.com>
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Iago Toral Quiroga [Thu, 3 Dec 2015 10:11:14 +0000 (11:11 +0100)]
i965: set correct execsize for MOVS with a width of 4 in brw_find_live_channel
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Iago Toral Quiroga [Thu, 3 Dec 2015 10:10:12 +0000 (11:10 +0100)]
i965/eu: set execution size for SEND message in brw_send_indirect_message
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Iago Toral Quiroga [Thu, 3 Dec 2015 09:59:23 +0000 (10:59 +0100)]
i965/fs: Set exec size for gen7 pull const loads
v2 (Topi):
- No need to set the execsize for the indirect send message,
the next patch will handle that.
- Set the execution size explicitly instead of taking it from
the width of the dst that we set before.
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Iago Toral Quiroga [Thu, 3 Dec 2015 07:49:13 +0000 (08:49 +0100)]
i965/eu: set correct execution size in brw_NOP
v2: NOP should have an execsize of 1 (Matt)
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Kenneth Graunke [Tue, 15 Mar 2016 17:51:55 +0000 (10:51 -0700)]
meta: Don't use integer handles for shaders or programs.
Previously, we gave our internal clear/blit shaders actual GL handles
and stored them in the shader/program hash table. We used ordinary
GL API entrypoints to work with them.
We thought this shouldn't be a problem because GL doesn't allow
applications to invent their own names for shaders or programs.
GL allocates all names via glCreateShader and glCreateProgram.
However, having them in the hash table is a bit risky: if a broken
application guesses the name of our shaders or programs, it could
alter them, potentially screwing up future meta operations.
Also, test cases can observe the programs in the hash table. Running
a single dEQP process that executes the following test list:
dEQP-GLES3.functional.negative_api.buffer.clear
dEQP-GLES3.functional.negative_api.shader.compile_shader
dEQP-GLES3.functional.negative_api.shader.delete_shader
would result in the last two tests breaking. The compile_shader test
calls glCompileShader(9) straight away, and since it hasn't even created
any shaders or programs, it expects to get a GL_INVALID_VALUE error
because there's no such name. However, because the clear test ran
first, it created Meta programs, so an object named "9" did exist.
This patch reworks Meta to work with gl_shader and gl_shader_program
pointers directly. These internal programs have bogus names, and are
never stored in the hash tables, so they're invisible to applications.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94485
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Kenneth Graunke [Tue, 15 Mar 2016 17:51:33 +0000 (10:51 -0700)]
mesa: Expose compile_shader() and link_program() beyond the file.
This will allow me to use them directly from Meta, bypassing the
versions that work with GL integer handles.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Timothy Arceri <timothy.arceri@collabora.com>
Kenneth Graunke [Wed, 16 Mar 2016 00:08:17 +0000 (17:08 -0700)]
mesa: Make link_program() take a gl_shader_program, not a GLuint.
In half the callers, we already have a pointer, and don't need
to look it up again. This will also help with upcoming meta work.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Timothy Arceri <timothy.arceri@collabora.com>
Kenneth Graunke [Tue, 15 Mar 2016 17:24:09 +0000 (10:24 -0700)]
mesa: Make compile_shader() take a gl_shader, not a GLuint.
In half the callers, we already have a pointer, and don't need
to look it up again. This will also help with upcoming meta work.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Timothy Arceri <timothy.arceri@collabora.com>
Kenneth Graunke [Tue, 15 Mar 2016 23:21:36 +0000 (16:21 -0700)]
meta: Use the _mesa_meta_compile_and_link_program helper more places.
Less boilerplate.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Eric Anholt [Wed, 16 Mar 2016 01:00:22 +0000 (18:00 -0700)]
vc4: Move discard handling to the condition flag.
Now that the field exists in the instruction, we can make discards less
special. As a bonus, that means that we should be able to merge some more
.sf instructions together when we get around to that.
This causes some scheduling changes, as it allows tlb_color_reads to be
delayed past the discard condition setup. Since the tlb_color_read ends
up later, this may mean performance improvements, but I haven't tested.
total instructions in shared programs: 78114 -> 78035 (-0.10%)
instructions in affected programs: 1922 -> 1843 (-4.11%)
total estimated cycles in shared programs: 234318 -> 234329 (0.00%)
estimated cycles in affected programs: 8200 -> 8211 (0.13%)
Eric Anholt [Wed, 16 Mar 2016 01:58:43 +0000 (18:58 -0700)]
vc4: Don't make a temporary for setting flags.
The register allocator doesn't really do anything about the temp, so it
doesn't seem like it should matter. However, the scheduler would think
that a new def is being created.
This doesn't change anything yet, but it avoids a bunch of regressions in
the next commit.
Eric Anholt [Wed, 16 Mar 2016 01:57:20 +0000 (18:57 -0700)]
vc4: Add a safety check for setting flags.
If a pack was on the src reg, should it be a float, int, or mul unpack?
Just complain, instead.
Eric Anholt [Wed, 16 Mar 2016 01:50:32 +0000 (18:50 -0700)]
vc4: Reuse list_for_each_entry_safe_rev().
This didn't exist when I wrote the code.
Kenneth Graunke [Tue, 15 Mar 2016 18:13:25 +0000 (11:13 -0700)]
meta: Use ARB_explicit_attrib_location in the rest of the meta shaders.
This is cleaner than using glBindAttribLocation().
Not all drivers support the extension, but I don't think those drivers
use GLSL in the first place. Apparently some Meta shaders already use
GL_ARB_explicit_attrib_location, so I think it should be okay.
Honestly, I'm not sure how the old code worked anyway - we bound the
attribute location for "texcoords", while all the shaders capitalized
or spelled it differently.
v2: Convert another instance in brw_meta_fast_clear.c.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Plamena Manolova [Tue, 15 Mar 2016 18:39:49 +0000 (20:39 +0200)]
mesa: Ignore glPointSize when GL_POINT_SIZE_ARRAY_OES is enabled
When a user defines a point size array and enables it, the point
size value set via glPointSize should be ignored. To achieve this,
we can simply toggle ctx->VertexProgram.PointSizeEnabled.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=42187
Signed-off-by: Plamena Manolova <plamena.manolova@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Varad Gautam [Mon, 7 Mar 2016 19:31:59 +0000 (01:01 +0530)]
vc4: Coalesce instructions using VPM reads into the VPM read.
This is done instead of copy propagating the VPM reads into the
instructions using them, because VPM reads have to stay in order.
shader-db results:
total instructions in shared programs: 78509 -> 78114 (-0.50%)
instructions in affected programs: 5203 -> 4808 (-7.59%)
total estimated cycles in shared programs: 234670 -> 234318 (-0.15%)
estimated cycles in affected programs: 5345 -> 4993 (-6.59%)
Signed-off-by: Varad Gautam <varadgautam@gmail.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Tested-by: Rhys Kidd <rhyskidd@gmail.com>
Varad Gautam [Mon, 7 Mar 2016 19:31:58 +0000 (01:01 +0530)]
vc4: rename file to group vpm optimizations together
This file will contain optimization passes for both vpm reads
and writes.
Signed-off-by: Varad Gautam <varadgautam@gmail.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Eric Anholt [Tue, 15 Mar 2016 19:48:55 +0000 (12:48 -0700)]
vc4: Fix failures with nir_extract_* since the addition of the opcodes.
Roland Scheidegger [Tue, 15 Mar 2016 15:39:55 +0000 (16:39 +0100)]
llvmpipe: fix lp_rast_plane alignment on 32bit
Some rasterization code relies (for sse) on the first and third planes
(but not the second for now) being 128bit aligned, and we didn't get that
on 32bit - I mistakenly thought the 64bit number in the struct would get
the thing aligned to 64bit even on 32bit archs.
Stephane Marchesin really figured this out.
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
CC: <mesa-stable@lists.freedesktop.org>
Roland Scheidegger [Tue, 15 Mar 2016 18:40:44 +0000 (19:40 +0100)]
draw: fix line stippling
The logic was comparing actual ints, not true/false values.
This meant that it was emitting always multiple line segments instead of just
one even if the stipple test had the same result, which looks inefficient, and
the segments also overlapped thus breaking line aa as well.
(In practice, with the no-op default line stipple pattern, for a 10-pixel
long line from 0-9 it was emitting 10 segments, with the individual segments
ranging from 0-1, 0-2, 0-3 and so on.)
This fixes https://bugs.freedesktop.org/show_bug.cgi?id=94193
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
CC: <mesa-stable@lists.freedesktop.org>
Roland Scheidegger [Sun, 13 Mar 2016 18:38:23 +0000 (19:38 +0100)]
softpipe: fix misleading TGSI_QUAD_SIZE usage
All these img filter loops iterate through NUM_CHANNELS, not QUAD_SIZE.
In practice both are of course the same unchangeable value (4), but it
makes the code look a bit confusing. Moreover, some of the functions were
actually given an array of 4 values according to the declaration, yet the
code was addressing values 0/4/8/12 out of it, so fix this by just saying
it's a pointer to floats like the other functions.
While here, also add comment about not quite correct filtering.
There's no actual code difference.
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Roland Scheidegger [Sun, 13 Mar 2016 18:13:09 +0000 (19:13 +0100)]
softpipe: fix anisotropic filtering crash
The filt_args->offset wasn't assigned but was always used later leading
to a crash (as far as I can tell, texel offsets don't actually make much
sense with anisotropic filtering, but because there's no explicit setting
if offsets are enabled there the array is always accessed).
This fixes https://bugs.freedesktop.org/show_bug.cgi?id=94481
Reviewed-by: Eduardo Lima Mitev <elima@igalia.com>
CC: <mesa-stable@lists.freedesktop.org>
Nicolai Hähnle [Fri, 11 Mar 2016 23:20:00 +0000 (18:20 -0500)]
radeonsi: set DEPTH_BEFORE_SHADER based on FS_EARLY_DEPTH_STENCIL
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Tue, 9 Feb 2016 17:54:10 +0000 (12:54 -0500)]
tgsi: add tgsi_full_src_register_from_dst helper function
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Sat, 6 Feb 2016 21:49:17 +0000 (16:49 -0500)]
gallium/u_inlines: add util_copy_image_view
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Sun, 13 Mar 2016 14:10:53 +0000 (09:10 -0500)]
st/mesa: set image access flags in st_bind_images
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Sat, 12 Mar 2016 01:04:19 +0000 (20:04 -0500)]
gallium: add access field to pipe_image_view
This allows drivers to make smarter decisions e.g. about whether the image
has to be decompressed.
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Fri, 11 Mar 2016 23:11:35 +0000 (18:11 -0500)]
st/glsl_to_tgsi: set FS_EARLY_DEPTH_STENCIL when required
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Fri, 11 Mar 2016 23:11:22 +0000 (18:11 -0500)]
tgsi: add TGSI_PROPERTY_FS_EARLY_DEPTH_STENCIL
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Sun, 13 Mar 2016 02:47:35 +0000 (21:47 -0500)]
st/glsl_to_tgsi: set memory access type on image intrinsics
This is required to preserve the image variable's coherent/restrict/volatile
qualifiers in TGSI.
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Sun, 7 Feb 2016 18:28:01 +0000 (13:28 -0500)]
st/glsl_to_tgsi: provide Texture and Format information for image ops
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Thu, 10 Mar 2016 21:30:07 +0000 (16:30 -0500)]
tgsi: add Texture and Format to tgsi_instruction_memory
Frontends should have this information readily available, and it simplifies
image LOAD/STORE/ATOM* handling especially with indirect image access.
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Thu, 10 Mar 2016 22:41:29 +0000 (17:41 -0500)]
get: reconcile aliasing enums for MaxCombinedShaderOutputResources
The enums MAX_COMBINED_IMAGE_UNITS_AND_FRAGMENT_OUTPUTS and
MAX_COMBINED_SHADER_OUTPUT_RESOURCES are equal and should therefore only
appear once.
Noticed while implementing ARB_shader_image_load_store without previously
implementing SSBO.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Mon, 7 Mar 2016 03:03:56 +0000 (19:03 -0800)]
i965/fs: Restrict inequality that can only hold equal in saturate propagation.
Should have no functional change. The IP value of an instruction that
reads src_var cannot possibly be after the end of the live interval of
the variable it's reading from, by the definition of live interval.
Might save future readers a momentary WTF while trying to understand
this code.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Francisco Jerez [Mon, 14 Mar 2016 02:15:45 +0000 (19:15 -0700)]
i965/vec4: Consider removal of no-op MOVs as progress during register coalesce.
Bug found by the liveness analysis validation pass that will be
introduced in a later commit. The no-op MOV check in
opt_register_coalesce() was removing instructions which makes the
cached liveness analysis calculation inconsistent with the shader IR.
We were failing to set progress to true in that case though, which
means that invalidate_live_intervals() wouldn't necessarily be called
at the end of the function.
Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Matt Turner <mattst88@gmail.com>
Francisco Jerez [Fri, 11 Mar 2016 23:27:22 +0000 (15:27 -0800)]
i965/fs: Add missing analysis invalidation in fixup_3src_null_dest().
Bug found by the liveness analysis validation pass that will be
introduced in a later commit. fixup_3src_null_dest() was allocating
registers which makes the cached liveness analysis calculation
incomplete, so it must be invalidated.
Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Matt Turner <mattst88@gmail.com>
Francisco Jerez [Fri, 11 Mar 2016 23:22:56 +0000 (15:22 -0800)]
i965/fs: Add missing analysis invalidation in opt_sampler_eot().
Bug found by the liveness analysis validation pass that will be
introduced in a later commit. opt_sampler_eot() was allocating
registers and inserting and removing instructions, which makes the
cached liveness analysis calculation inconsistent with the shader IR,
so it must be invalidated.
Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Matt Turner <mattst88@gmail.com>
Hans de Goede [Mon, 14 Mar 2016 14:01:05 +0000 (15:01 +0100)]
clover: Fix pipe_grid_info.indirect not being initialized.
After pipe_grid_info.indirect was introduced, clover was not modified
to set it causing it to pass uninitialized memory for it to launch_grid.
This commit fixes this by zero-ing the entire pipe_grid_info struct when
declaring it, to avoid similar problems popping-up in the future.
Cc: "11.2" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Hans de Goede <hdegoede@redhat.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
[ Francisco Jerez: Trivial codestyle fix. ]
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Sarah Sharp [Thu, 29 Oct 2015 23:11:54 +0000 (16:11 -0700)]
mesa: docs: Intel i965 hardware limits.
This should help the next person working on hardware enabling figure out
where in the Intel PRMs to find the magic platform hardware values.
Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Sarah Sharp [Thu, 29 Oct 2015 19:12:40 +0000 (12:12 -0700)]
mesa: docs: i965: Use correct doxygen groupings syntax
When reading the source code, it's useful to indicate that a group of
fields in a struct are related in someway. There were several places
where people tried to group related structure members with the {@
syntax, without realizing they also needed to add the \name syntax in
order to generate correct doxygen html.
There are several files with groupings that look like this:
struct foo {
/**
* Related fields description
* @{
*/
int bar;
char baz;
/** @} */
long qux;
}
However, the doxygen syntax for grouping is:
struct foo {
/**
* \name Related fields description
* @{
*/
int bar;
char baz;
/** @} */
long qux;
}
https://www.stack.nl/~dimitri/doxygen/manual/grouping.html
Without the group name definition, the fields don't get properly
grouped. Instead, the group description is applied to the first field.
Fix the Intel hardware information structure, brw_device_info to
properly group the GPU hardware limitations and hardware quirks fields.
Once you've run `cd doxygen; make clean; make all`,
updated documentation can be found at
mesa/doxygen/i965/structbrw__device__info.html
Signed-off-by: Sarah Sharp <sarah.a.sharp@linux.intel.com>
Bruce Cherniak [Thu, 10 Mar 2016 01:30:00 +0000 (19:30 -0600)]
gallium/swr: Resource management
Better tracking of resource state and synchronization.
A follow on commit will clean up resource functions into a new
swr_resource.cpp file.
Reviewed-By: George Kyriazis <george.kyriazis@intel.com>
Marek Olšák [Mon, 14 Mar 2016 15:41:54 +0000 (16:41 +0100)]
configure.ac: require libdrm 2.4.66 for drmGetDevice
since
737b6ed13e8f813987b5566004f0f45e9c55f1e8
src/gallium/winsys/amdgpu/drm/amdgpu_winsys.c no longer compiles:
error: unknown type name ‘drmDevicePtr’
Francisco Jerez [Wed, 9 Mar 2016 01:23:37 +0000 (17:23 -0800)]
i965: Remove useless IR self-destruct backend_shader method.
From the point it's constructed the CFG contains the only existing
copy of the program IR, and it never becomes invalid. Calling
backend_shader::invalidate_cfg would have destroyed the program
structure irrecoverably -- We weren't calling it at all for a good
reason.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org
Reviewed-by: Matt Turner <mattst88@gmail.com>
Pierre Moreau [Sun, 13 Mar 2016 21:11:30 +0000 (22:11 +0100)]
nv50,nvc0: Set only NEW_CP_GLOBALS upon binding
Signed-off-by: Pierre Moreau <pierre.morrow@free.fr>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Rob Clark [Sun, 13 Mar 2016 18:03:04 +0000 (14:03 -0400)]
freedreno/ir3: lower extract_byte/word
The following commits broke things by starting to feed us unhandled
extract_u16/extract_u8 opcodes:
commit
905ff861982450831a56d112036f68a751337441
Author: Matt Turner <mattst88@gmail.com>
AuthorDate: Wed Feb 3 14:28:31 2016 -0800
Commit: Matt Turner <mattst88@gmail.com>
CommitDate: Fri Mar 4 11:52:34 2016 -0800
nir: Recognize open-coded extract_u16.
commit
76289fbfa84a06ef4db8ad44ea0eb88ad0be8d5c
Author: Matt Turner <mattst88@gmail.com>
AuthorDate: Thu Jan 21 09:09:48 2016 -0800
Commit: Matt Turner <mattst88@gmail.com>
CommitDate: Fri Mar 4 11:52:34 2016 -0800
nir: Recognize open-coded extract_u8.
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Ilia Mirkin [Sun, 13 Mar 2016 02:26:21 +0000 (21:26 -0500)]
nv50,nvc0: handle SQRT lowering inside the driver
First off, st/mesa lowers DSQRT incorrectly (it uses CMP to attempt to
find out whether the input is less than 0). Secondly the current
approach (x * rsq(x)) behaves poorly for x = inf - a NaN is produced
instead of inf.
Instead we switch to the less accurate rcp(rsq(x)) method - this behaves
nicely for all valid inputs. We still don't do this for DSQRT since the
RSQ/RCP ops are *really* inaccurate, and don't even have Newton-Raphson
steps right now. Eventually we should have a separate library function
for DSQRT that does it more precisely (and perhaps move this lowering to
the post-opt phase).
This fixes a number of dEQP precision tests that were expecting better
behavior for infinite inputs.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Tested-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Ilia Mirkin [Sun, 13 Mar 2016 01:53:34 +0000 (20:53 -0500)]
nv50/ir: avoid folding mul + add if the mul has a dnz
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Ilia Mirkin [Sat, 12 Mar 2016 02:26:31 +0000 (21:26 -0500)]
nvc0: fix blit triangle size to fully cover FB's > 8192x8192
The idea is that a single triangle will cover the whole area being
drawn, allowing the blit shader to do its work. However the max fb size
is 16384x16384, which means that the triangle we draw needs to be twice
that in order to cover the whole area fully. Increase the size of the
triangle to 32768x32768.
This fixes a number of dEQP tests that were failing because a blit was
involved which would miss some of the resulting texture.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: "11.1 11.2" <mesa-stable@lists.freedesktop.org>
Rob Clark [Wed, 9 Mar 2016 09:07:51 +0000 (04:07 -0500)]
freedreno: OUT_RELOC vs OUT_RELOCW fixes
Make sure we use OUT_RELOCW() in cases where the buffer is written to.
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Rob Clark [Sat, 5 Mar 2016 21:53:11 +0000 (16:53 -0500)]
freedreno/a4xx: hw binning
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Rob Clark [Sat, 5 Mar 2016 21:50:09 +0000 (16:50 -0500)]
freedreno/a4xx: use generated headers for draw initiator
No need to open-code this.
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Rob Clark [Sat, 5 Mar 2016 21:47:26 +0000 (16:47 -0500)]
freedreno/a4xx: remove RB_RENDER_CONTROL patching
Bitfields where shuffled around for the better on a4xx, so we don't need
any patching on this one. It appears to be something we set entirely in
the gmem code so no conflict between tiling and render state like we had
in a3xx.
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Rob Clark [Sat, 5 Mar 2016 21:41:21 +0000 (16:41 -0500)]
freedreno: update generated headers
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Rob Clark [Sun, 13 Mar 2016 16:15:28 +0000 (12:15 -0400)]
freedreno/a3xx: move where we deal w/ binning FS
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Rob Clark [Mon, 7 Mar 2016 05:52:03 +0000 (00:52 -0500)]
freedreno/a4xx: move where we deal w/ binning FS
Move where we pick dummy FS for binning pass, so the whole driver sees
the same dummy/no-op FS stage.
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Rob Clark [Sun, 13 Mar 2016 16:09:51 +0000 (12:09 -0400)]
freedreno/a3xx: constify the shader variants
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Rob Clark [Mon, 7 Mar 2016 05:50:21 +0000 (00:50 -0500)]
freedreno/a4xx: constify the shader variants
Most of the driver just needs read-only access, so constify..
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Rob Clark [Sun, 6 Mar 2016 03:11:26 +0000 (22:11 -0500)]
freedreno/a3xx: remove duplicate mark of end of binning cmds
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Nicolai Hähnle [Fri, 11 Mar 2016 16:07:38 +0000 (11:07 -0500)]
radeonsi: avoid crash when a sampler state is bound for a buffer texture
Sampler states don't really make sense with buffer textures, but they
can be set anyway, so we need to be defensive here. This bug was lurking
for a while and was finally noticed due to PBO uploads setting sampler
states.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94284
Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Tested-by: Laurent Carlier <lordheavym@gmail.com>
Tested-by: Shawn Starr <shawn.starr@rogers.com>
Matt Turner [Mon, 15 Feb 2016 06:28:51 +0000 (22:28 -0800)]
i965: Use foreach_in_list_reverse_safe() macro.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Jason Ekstrand [Sat, 13 Feb 2016 04:51:50 +0000 (20:51 -0800)]
nir/clone: Add support for cloning a single function_impl
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Jason Ekstrand [Sun, 14 Feb 2016 02:08:30 +0000 (18:08 -0800)]
nir/validate: Better function validation
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Jason Ekstrand [Sat, 13 Feb 2016 04:41:19 +0000 (20:41 -0800)]
nir/print: Better function argument printing
Since we aren't going to put the function parameters or the return variable
in the list of locals, it won't get a proper declaration. This changes
nir_print to print the type along with each parameter or return variable.
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Jason Ekstrand [Sat, 26 Dec 2015 18:26:29 +0000 (10:26 -0800)]
nir/print: Factor variable name lookup into a helper
Otherwise, we have a problem when we go to print functions with arguments
because their names get added to the hash table during declaration which
happens after we print the prototype.
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Jason Ekstrand [Mon, 15 Feb 2016 05:42:34 +0000 (21:42 -0800)]
nir: Create function parameters in function_impl_create
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Jason Ekstrand [Wed, 28 Oct 2015 04:34:56 +0000 (21:34 -0700)]
nir: Add a helper for creating a "bare" nir_function_impl
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Jason Ekstrand [Fri, 12 Feb 2016 19:58:06 +0000 (11:58 -0800)]
nir: Add a new "param" variable mode for parameters and return variables
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Jason Ekstrand [Fri, 12 Feb 2016 18:50:56 +0000 (10:50 -0800)]
nir/glsl: Remove dead function parameter handling code
NIR has never been used on IR where we haven't already done function
inlining so this code has been dead from the beginning. Let's just get rid
of it for now. We can always put it back in if we decide to use NIR for
function inlining at some point in the future.
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Boyuan Zhang [Tue, 22 Dec 2015 01:07:14 +0000 (20:07 -0500)]
st/va: add HEVC main 10 profile
Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Boyuan Zhang [Tue, 22 Dec 2015 01:06:26 +0000 (20:06 -0500)]
radeon/video: enable HEVC main 10 decode
Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Boyuan Zhang [Tue, 22 Dec 2015 01:05:45 +0000 (20:05 -0500)]
radeon/uvd: handle HEVC main 10 decode
Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Ben Widawsky [Mon, 8 Feb 2016 20:42:29 +0000 (12:42 -0800)]
i965/chv: Display proper branding
"Braswell" is a Cherryview based *thing*. It unfortunately requires extra
information to determine its marketing name. Unlike all previous products, and
hopefully all future ones, there is no unique 1:1 mapping of PCI device ID to
brand string.
I put up a fight about adding any complexity to our GL renderer string code for
a very long time. However, a wise man made a comment to me that I couldn't argue
with: if a user installs Windows on their hardware, the brand string should be
the same as what we display in Linux. The Windows driver apparently does this
check, so we should too.
Note that I did manage to find a good use for this info anyway in the compute
shader thread counts.
v2: memcpy instead of strncpy, and some minor changes (Matt)
Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com
Ben Widawsky [Tue, 9 Feb 2016 02:11:42 +0000 (18:11 -0800)]
i965/chv: Update lower min for CS threads
We have better information now, and 28 was not a valid thing to support. 6 EUs
per sublice with 7 threads per EU is the minimum supported config.
Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com
Ben Widawsky [Tue, 9 Feb 2016 02:00:41 +0000 (18:00 -0800)]
i965/chv: Check that compute threads are above threshold
The way we are organizing this code, the statically configured max_cs_threads
should always be the minimum value we actually support (ie. are aware of). As a
result, we can fall back to that if we get invalid numbers from the kernel (ie.
when the query succeeds, but the result is lower than expected).
I was originally planning to use an assert, but there is no reason to be so
mean.
Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com
Ben Widawsky [Tue, 9 Feb 2016 00:22:06 +0000 (16:22 -0800)]
i965/chv: Use kernel provided info for max_cs_threads
With the previous patches, the code can find out the actual number of available
compute threads. It is enabled only for Cherryview since that is the only
platform I know for a fact has shipped devices which can benefit from this. It
seems like other platforms /might/ benefit from this because of fused
configurations which /might/ have shipped. Fallback code is still there.
v2: Some minor adjustments from Matt
Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com
Ben Widawsky [Mon, 8 Feb 2016 19:52:17 +0000 (11:52 -0800)]
i965: Query and store GPU properties from kernel
Certain products are not uniquely identifiable based on device id alone. The
kernel exports an interface to help deal with this. This patch merely introduces
the consumer of the interface and makes sure nothing breaks.
It is also possible to use these values for programming GPGPU mode, and I plan
to do that as well.
The interface was introduced in libdrm 2.4.60, which is already required, so it
should all be fine.
v2: Some minor changes recommended by Matt
Signed-off-by: Ben Widawsky <benjamin.widawsky@intel.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Nicolai Hähnle [Thu, 10 Mar 2016 20:15:02 +0000 (15:15 -0500)]
st/mesa: check that the image unit is valid in st_bind_images
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Bas Nieuwenhuizen [Thu, 10 Mar 2016 16:57:41 +0000 (17:57 +0100)]
radeonsi: Lazily re-set sampler views after disabling DCC
Clear DCC flags if necessary when binding a new sampler view.
v2: Do not reset DCC flags of bound sampler views.
v3: Check that we have a real texture (Nicolai)
Signed-off-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Wed, 9 Mar 2016 16:03:12 +0000 (17:03 +0100)]
st/mesa: remove ST_NEW_MESA flag (v2)
Only used indirectly when checking dirty.st != 0
v2: also update st_cb_compute.c
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Nicolai Hähnle [Fri, 11 Mar 2016 02:19:56 +0000 (21:19 -0500)]
r600g: clear compressed_depthtex/colortex_mask when binding buffer texture
Found by inspection of the source based on a bisected bug report.
This bug has been in the code for a long time, but the more recent PBO upload
feature exposed it because it leads to more uses of buffer textures.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94388
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Cc: "11.0 11.1 11.2" <mesa-stable@lists.freedesktop.org>
Ilia Mirkin [Sat, 20 Feb 2016 04:18:33 +0000 (23:18 -0500)]
st/mesa: add GL_ARB_shader_atomic_counter_ops support
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Ilia Mirkin [Sat, 20 Feb 2016 04:07:38 +0000 (23:07 -0500)]
mesa: add GL_ARB_shader_atomic_counter_ops support
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Ilia Mirkin [Wed, 9 Mar 2016 06:04:58 +0000 (01:04 -0500)]
nvc0: add support for TGSI FMA ops
This will allow the nouveau backend to not try and split up ops that are
fused in GLSL.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Nicolai Hähnle [Wed, 9 Mar 2016 20:42:31 +0000 (15:42 -0500)]
radeonsi: update compressed_colortex_masks when a cmask is created or disabled
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Mon, 8 Feb 2016 03:27:17 +0000 (22:27 -0500)]
radeonsi: move si_decompress_textures to si_blit.c
Since it is all about calling into blitter functions, it makes more
sense here. This change also reduces the size of the interfaces between
.c files.
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Wed, 9 Mar 2016 22:48:31 +0000 (17:48 -0500)]
r600g: update compressed_colortex_masks when a cmask is created or disabled
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Nicolai Hähnle [Mon, 8 Feb 2016 04:33:44 +0000 (23:33 -0500)]
gallium/radeon: notify all contexts when cmasks are enabled/disabled
There is an annoying corner case that I stumbled across while looking into
piglit's arb_shader_image_load_store/execution/load-from-cleared-image.shader_test
(which can be easily adapted to demonstrate the bug without the
ARB_shader_image_load_store extension)
When we bind a texture and then clear it using glClear (by attaching it
to the current framebuffer) for the first time, we allocate a separate
cmask for the texture to do fast clear, but the corresponding bit in
compressed_colortex_mask is not set. Subsequent rendering will use
incorrect data.
Conversely, when a currently bound texture with an existing cmask is
exported leading to that cmask being disabled, the compressed_colortex_mask
bit will remain set, leading to an assertion later on in debug builds.
Since iterating through all contexts and/or remembering where every
texture is bound would be costly, and cmask enable/disable should be
rare, we will maintain a global counter to signal contexts that they
must update their compressed_colortex_masks.
This patch introduces the global counter, and subsequent patches will
do the mask update.
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Kenneth Graunke [Wed, 9 Mar 2016 04:00:06 +0000 (20:00 -0800)]
i965: Set a proper _BaseFormat for window system renderbuffers in ES.
intel_alloc_private_renderbuffer_storage did:
rb->_BaseFormat = _mesa_base_fbo_format(ctx, internalFormat);
Unfortunately, internalFormat was usually an unsized format (such as
GL_DEPTH_COMPONENT). In OpenGL ES, _mesa_base_fbo_format() refuses to
accept unsized formats, and returns 0 rather than a real base format.
This meant that we ended up with a completely bogus rb->_BaseFormat for
window system buffers on OpenGL ES. All other renderbuffer allocation
functions in intel_fbo.c instead use the mesa_format, and do:
rb->_BaseFormat = _mesa_get_format_base_format(...);
We can do likewise, using rb->Format. This appears to work just fine.
dEQP-GLES3.functional.state_query.fbo.framebuffer_attachment_x_size_initial
failed, as it tried to perform a GL_FRAMEBUFFER_ATTACHMENT_DEPTH_SIZE query
on the window system depth buffer. That query relies on a proper
rb->_BaseFormat being set, so it broke because rb->_BaseFormat was 0 due
to the above bug.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94458
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Kenneth Graunke [Wed, 9 Mar 2016 03:03:11 +0000 (19:03 -0800)]
glcpp: Fix locations when encounting "#<NEWLINE>".
We were failing to reset our location tracking when encountering a
NEWLINE in the <HASH> state. Rip the code from the <*>{NEWLINE} rule,
which handles this properly.
Also, update 146-version-first-hash.c to have proper expectations.
When I introduced the test, I didn't verify that the line/column
numbers were correct, and it turns out they varied based on the type
of newline ending.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94447
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Tim Rowley [Tue, 8 Mar 2016 17:22:54 +0000 (11:22 -0600)]
gallium/swr: remove use of BYTE from swr driver
Remove use of a win32-style type leaked from the swr rasterizer.
Reviewed-by: Bruce Cherniak <bruce.cherniak@intel.com>
Samuel Pitoiset [Wed, 9 Mar 2016 22:58:09 +0000 (23:58 +0100)]
nvc0: expose SM35 perf counters to AMD_performance_monitor
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Ilia Mirkin <imirkin@alum.mit.edu>