OSDN Git Service
Chris Forbes [Sat, 12 Oct 2013 11:02:04 +0000 (00:02 +1300)]
i965: Remove ir_txf coord+offset special case in visitors
Just let it be handled by the lowering pass.
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Chris Forbes [Sat, 12 Oct 2013 11:02:55 +0000 (00:02 +1300)]
i965: Generalize coord+offset lowering pass for ir_txf
ir_txf expects an ivec* coordinate, and may be larger than ivec2;
shuffle things around so that this will work.
V2: Fix style nits, use ir_builder
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Chris Forbes [Sat, 12 Oct 2013 10:14:15 +0000 (23:14 +1300)]
i965: Add lowering pass to fold offset into unnormalized coords
It turns out that nonzero offsets with gsampler2DRect don't work -- they
just return garbage. Work around this by folding the offset into the
coord.
Done as an IR pass rather than yet another hack in the visitors because
it's clear what's going on this way. Can possibly reuse this to replace
the existing txf coord+offset hacks.
V2: Use ir_builder
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Chris Forbes [Thu, 10 Oct 2013 09:15:14 +0000 (22:15 +1300)]
i965: Add lowering pass for splitting textureGatherOffsets
Rewrites textureGatherOffsets(s, p, offsets) into
gvec4(
textureGatherOffset(s, p, offsets[0]).w,
textureGatherOffset(s, p, offsets[1]).w,
textureGatherOffset(s, p, offsets[2]).w,
textureGatherOffset(s, p, offsets[3]).w
)
V2: Use ir_builder to be slightly clearer.
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Chris Forbes [Thu, 10 Oct 2013 08:40:46 +0000 (21:40 +1300)]
i965: Add asserts to ensure that ir_tg4 offset arrays are lowered
We don't have a message that does 4 independent offsets; a lowering
pass needs to lower it to 4 normal gather4s before reaching this
point.
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Chris Forbes [Thu, 10 Oct 2013 08:38:43 +0000 (21:38 +1300)]
glsl: add signatures for textureGatherOffsets()
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Chris Forbes [Thu, 10 Oct 2013 08:34:03 +0000 (21:34 +1300)]
glsl: add support for texture functions with offset arrays
This is needed for textureGatherOffsets()
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Chris Forbes [Thu, 10 Oct 2013 06:57:29 +0000 (19:57 +1300)]
i965/fs: Add support for shadow comparitors with gather4
Note that gather4_po_c's parameters are too long for SIMD16. It might be
worth emitting 2xSIMD8 messages in this case at some point.
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Chris Forbes [Thu, 10 Oct 2013 06:42:47 +0000 (19:42 +1300)]
i965/vs: Add support for shadow comparitors with gather4
gather4_c's argument layout is straightforward -- refz just goes on the
end.
gather4_po_c's layout however -- the array index is replaced with refz.
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Chris Forbes [Thu, 10 Oct 2013 06:39:54 +0000 (19:39 +1300)]
i965: Add Gen7 gather4_c and gather4_po_c message types
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Chris Forbes [Thu, 10 Oct 2013 06:35:36 +0000 (19:35 +1300)]
glsl: Add new textureGather[Offset]() overloads for shadow samplers
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Chris Forbes [Thu, 10 Oct 2013 06:32:34 +0000 (19:32 +1300)]
glsl: Add support for separate reference Z for shadow samplers
ARB_gpu_shader5's textureGather*() functions which take shadow samplers
have a separate `refz` parameter rather than adding it to the
coordinate.
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Chris Forbes [Tue, 8 Oct 2013 09:19:58 +0000 (22:19 +1300)]
i965/vs: add support for gather4 with nonconstant offsets
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Chris Forbes [Tue, 8 Oct 2013 09:10:34 +0000 (22:10 +1300)]
i965/fs: add support for gather4 with nonconstant offsets
V3: fixup crazy check for whether we need to emit the coordinate after
custom handling.
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Chris Forbes [Tue, 8 Oct 2013 09:09:28 +0000 (22:09 +1300)]
i965: relax brw_texture_offset assert
Some texturing ops are about to have nonconstant offset support; the
offset in the header in these cases should be zero.
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Chris Forbes [Tue, 8 Oct 2013 08:42:10 +0000 (21:42 +1300)]
i965: Add SHADER_OPCODE_TG4_OFFSET for gather with nonconstant offsets.
The generator code ends up clearer this way than if we had to sniff
via the message length. Implemented via the gather4_po message in
hardware, which is present in Gen7 and later.
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Chris Forbes [Tue, 8 Oct 2013 08:34:22 +0000 (21:34 +1300)]
i965: add missing tg4 case in brw_instruction_name
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Chris Forbes [Sun, 6 Oct 2013 01:26:01 +0000 (14:26 +1300)]
glsl: relax const offset requirement for textureGatherOffset
Prior to ARB_gpu_shader5 / GLSL 4.0, the offset is required to be
a constant expression.
With that extension, it is relaxed to be an arbitrary expression.
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Chris Forbes [Sun, 6 Oct 2013 00:23:59 +0000 (13:23 +1300)]
glsl: Add ARB_gpu_shader5 textureGatherOffset signatures
- gsampler2DRect
- optional `comp` parameter
Signed-off-by: Chris Forbes <chrisf@ijw.co.nz>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Kenneth Graunke [Tue, 28 May 2013 02:18:14 +0000 (19:18 -0700)]
i965: Weaken the flushing in gen7_end_transform_feedback().
Since
062317d6671 (i965: Go back to using the kernel SOL reset feature.)
we've been flushing the batch on BeginTransformFeedback(). So it's not
necessary to do it on EndTransformFeedback(). A PIPE_CONTROL will work.
This makes gen7_end_transform_feedback() exactly the same as the gen6
variant. However, they'll diverge again shortly.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Eric Anholt [Tue, 22 Oct 2013 19:38:14 +0000 (12:38 -0700)]
i965/fs: Stop trying to hack around MRF dep chains on gen7+ LIFO scheduling.
This was a hack to avoid choosing to schedule all texturing before
consumption of any texture results due to the way dependency chains worked
out in the presence of MRFs. On gen7, we don't have MRFs, so the problem
doesn't apply, and this was just badly constraining our scheduling.
total instructions in shared programs:
1615306 ->
1612534 (-0.17%)
instructions in affected programs: 9958 -> 7186 (-27.84%)
GAINED: 259
LOST: 9
Reviewed-by: Matt Turner <mattst88@gmail.com>
Eric Anholt [Tue, 22 Oct 2013 19:27:06 +0000 (12:27 -0700)]
i965: Try not to reverse-schedule things when doing LIFO scheduling.
The LIFO plan was simple: Take the most recently made available
instructions, and pick those first.
But because of the order we were pushing things onto our list of
available-to-schedule instructions, it meant that when a set of
instructions was made available at the same time (for example, everything
at the start of the program that didn't depend on other instructions) we'd
schedule them in reverse order.
If you had 10 texture calls in a row in your program, each with
independent argument setup, we'd set up the last texture call's args and
execute it first, even though we wouldn't be able to consume its results
until we'd finished the other 9 texture calls (assuming consumption of
texture results happens near each texture call, and combines it with
another texture result, which is normal for a convolution shader).
To fix this, walk the list for doing LIFO in the order that instructions
were originally generated in the program, but choose to push
newly-made-available instructions to the other end of the list instead.
total instructions in shared programs:
1587242 ->
1586290 (-0.06%)
instructions in affected programs: 7801 -> 6849 (-12.20%)
GAINED: 76
LOST: 67
Thanks to Chia-I Wu for pointing out the bug in my first version of the
patch that made it a huge loss.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ilia Mirkin [Fri, 4 Oct 2013 08:32:16 +0000 (04:32 -0400)]
mesa/st: disable ARB_framebuffer_object when no driver support.
When PIPE_CAP_MIXED_FRAMEBUFFER_SIZES is not provided, parts of
ARB_framebuffer_object can't be supported, such as on NV30.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Ilia Mirkin [Fri, 4 Oct 2013 08:32:15 +0000 (04:32 -0400)]
gallium: add PIPE_CAP_MIXED_FRAMEBUFFER_SIZES
This CAP will determine whether ARB_framebuffer_object can be enabled.
The nv30 driver does not allow mixing swizzled and linear zsbuf/cbuf
textures.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Adam Jackson [Fri, 25 Oct 2013 19:12:04 +0000 (15:12 -0400)]
glx: Fix return value from indirect_bind_context
_XReply returns 1 on success, but indirect_bind_context returns 0 on
success.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=70486
Reviewed-and-tested-by: Ian Romanick <ian.d.romanick@intel.com>
Signed-off-by: Adam Jackson <ajax@redhat.com>
Matt Turner [Wed, 23 Oct 2013 23:42:34 +0000 (16:42 -0700)]
glsl: Optimize (not A) and (not B) into not (A or B).
No shader-db changes, but seems like a good idea.
Reviewed-by: Eric Anholt <eric@anholt.net>
Matt Turner [Wed, 23 Oct 2013 23:40:16 +0000 (16:40 -0700)]
glsl: Optimize (not A) or (not B) into not (A and B).
A few Serious Sam 3 shaders affected:
instructions in affected programs: 4384 -> 4344 (-0.91%)
Reviewed-by: Eric Anholt <eric@anholt.net>
Matt Turner [Fri, 18 Oct 2013 23:02:11 +0000 (16:02 -0700)]
i965/fs: Match commutative expressions with reversed arguments.
total instructions in shared programs:
1645011 ->
1644938 (-0.00%)
instructions in affected programs: 17543 -> 17470 (-0.42%)
Reviewed-by: Eric Anholt <eric@anholt.net>
Matt Turner [Sat, 19 Oct 2013 23:40:19 +0000 (16:40 -0700)]
i965: s/Muchnik/Muchnick/.
Reviewed-by: Eric Anholt <eric@anholt.net>
Marek Olšák [Tue, 8 Oct 2013 19:50:43 +0000 (21:50 +0200)]
r600g,radeonsi: use fences provided by the winsys
Marek Olšák [Tue, 8 Oct 2013 19:26:34 +0000 (21:26 +0200)]
winsys/radeon: add the implementation of fences from r300g
Marek Olšák [Wed, 23 Oct 2013 14:10:38 +0000 (16:10 +0200)]
radeonsi: add the vertex shader position output if it's missing
This fixes a lockup in piglit/spec/glsl-1.40/execution/tf-no-position.
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Marek Olšák [Tue, 22 Oct 2013 20:05:35 +0000 (22:05 +0200)]
radeonsi: respect semantic indices for COLOR[i] fragment shader outputs
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Paul Berry [Tue, 15 Oct 2013 21:56:28 +0000 (14:56 -0700)]
glsl: When disabling gl_PerVertex variables, check that mode matches.
In commit
1b4a737 (glsl: Support redeclaration of VS and GS
gl_PerVertex output), I added code to ensure that when an unnamed
gl_PerVertex interface block is redeclared, any ir_variables that
weren't included in the redeclaration are removed from the IR (and the
symbol table). This ensures that only those variables that were
explicitly redeclared may be used.
However, when I wrote this code, I neglected to match the variable
mode when finding variables to remove. This meant that redeclaring a
built-in output block might cause the built-in input gl_in to be
accidentally removed.
Fixes piglit test gs-redeclares-pervertex-out-only.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Paul Berry [Tue, 15 Oct 2013 22:13:59 +0000 (15:13 -0700)]
glsl: Remove unused gl_PerVertex interface blocks.
The GLSL 4.10 rules for redeclaration of built-in interface blocks
(which we've chosen to regard as clarifications of GLSL 1.50) only
require gl_PerVertex blocks to match in shaders that actually use
those blocks. The easiest way to implement this is to detect
situations where a compiled shader doesn't refer to any elements of
gl_PerVertex, and remove all the associated ir_variables from the
shader at the end of ast-to-ir conversion.
Fixes piglit tests
linker/interstage-{pervertex,pervertex-in,pervertex-out}-redeclaration-unneeded.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Paul Berry [Tue, 15 Oct 2013 23:48:59 +0000 (16:48 -0700)]
glsl: Call check_builtin_array_max_size when redeclaring gl_in.
Normally when a built-in array (such as gl_ClipDistance) is
redeclared, we call get_variable_being_redeclared() to do the
redeclaration, and it in turn calls check_builtin_array_max_size() to
make sure that the redeclared array size isn't too large.
However when a built-in array is redeclared as part of redeclaring
gl_in, we don't call get_variable_being_redeclared() (since the
individual built-ins aren't each represented by their own ir_variable
anymore). So we need to add an explicit call to
check_builtin_array_max_size() to make sure the new array size isn't
too large.
Note: at the moment this is redundant with a test that's done at link
time, so there's no change to piglit results. But the patch that
follows will prevent link errors from being reported if gl_PerVertex
isn't used, so in order to prevent that patch from causing
regressions, we need to add the compile check now. Besides, it's
nicer to report this error at compile time anyhow.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Paul Berry [Wed, 16 Oct 2013 18:01:42 +0000 (11:01 -0700)]
mesa: Fix geometry shader program queries.
The queries GEOMETRY_VERTICES_OUT, GEOMETRY_INPUT_TYPE, and
GEOMETRY_OUTPUT_TYPE (defined by GL 3.2) differ from the corresponding
queries in ARB_geometry_shader4 in the following ways:
- They use different enum values
- They can only be queried; they cannot be set.
- Attempting to query them yields INVALID_OPERATION if the program is
not linked, or lacks a geometry shader.
This patch switches us over from the ARB_geometry_shader4 behaviour to
the GL 3.2 behaviour.
Fixes piglit test query-gs-prim-types.
v2: Improve comment above has_core_gs.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Paul Berry [Tue, 22 Oct 2013 04:09:47 +0000 (21:09 -0700)]
glsl: Account for interface block lowering in program_resource_visitor.
When program_resource_visitor visits variables that were created by
lower_named_interface_blocks, it needs to do extra work to un-do the
effects of lower_named_interface_blocks and construct the proper API
names.
Fixes piglit test
spec/glsl-1.50/execution/interface-blocks-api-access-members.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Paul Berry [Tue, 22 Oct 2013 03:27:23 +0000 (20:27 -0700)]
glsl: mark variables produced by lower_named_interface_blocks.
These variables will need to be treated specially by
program_resource_visitor, so that they can be addressed through the
API using their interface block name (and array index, for interface
block arrays).
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Paul Berry [Tue, 22 Oct 2013 22:11:51 +0000 (15:11 -0700)]
glsl: Keep track of centroid/interpolation mode for interface block members.
Fixes piglit tests:
- interface-block-interpolation-{array,named,unnamed}
- glsl-1.50-interface-block-centroid {array,named,unnamed}
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Paul Berry [Tue, 22 Oct 2013 22:03:29 +0000 (15:03 -0700)]
glsl: Pass variable mode into ast_process_structure_or_interface_block().
Later patches will use this information to do proper error checking of
interpolation qualifiers that appear inside of interface blocks.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Paul Berry [Tue, 22 Oct 2013 21:54:10 +0000 (14:54 -0700)]
glsl: Extract interpretation of interpolation to its own function.
In future patches, we will need this in order to interpret
interpolation qualifiers that appear inside interface blocks.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Paul Berry [Tue, 22 Oct 2013 21:48:08 +0000 (14:48 -0700)]
glsl: Pull interpolation_string() out of ir_variable.
Future patches will need to call this function when there isn't an
ir_varible present to refer to.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Paul Berry [Wed, 16 Oct 2013 03:44:00 +0000 (20:44 -0700)]
i965: Reduce gl_MaxGeometryInputComponents to 64.
Although in principle there is no hardware limitation that prevents
gl_MaxGeometryInputComponents from being set to 128 on Gen7, we have
the following limitations in the vec4 compiler back end:
- Registers assigned to geometry shader inputs can't be spilled or
later re-used for any other purpose.
- The last 16 registers are set aside for the "MRF hack", meaning they
can only be used to send messages, and not for general purpose
computation.
- Up to 32 registers may be reserved for push constants, even if there
is sufficient register pressure to make this impractical.
A shader using 128 geometry input components, and having an input type
of triangles_adjacency, would use up:
- 1 register for r0 (which holds URB handles and various pieces of
control information).
- 1 register for gl_PrimitiveID.
- 102 registers for geometry shader inputs (17 registers per input
vertex, assuming DUAL_INSTANCED dispatch mode and allowing for one
register of overhead for gl_Position and gl_PointSize, which are
present in the URB map even if they are not used).
- Up to 32 registers for push constants.
- 16 registers for the "MRF hack".
That's a total of 152 registers, which is well over the 128 registers
the hardware supports.
Fortunately, the GLSL 1.50 spec allows us to reduce
gl_MaxGeometryInputComponents to 64. Doing that frees up 48
registers, brining the total down to 104 registers, leaving 24
registers available to do computation.
Fixes piglit test
spec/glsl-1.50/execution/geometry/max-input-components.
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Paul Berry [Wed, 16 Oct 2013 19:27:37 +0000 (12:27 -0700)]
i965/gs: If a DUAL_OBJECT gs would spill, fall back to DUAL_INSTANCED.
This is similar to what we do for 16-wide vs 8-wide fragment shaders.
First we try compiling the geometry shader in DUAL_OBJECT mode. If we
can't do that without spilling, we fall back on DUAL_INSTANCED mode,
which should require less spilling (since it uses an interleaved
layout of payload registers).
In an ideal world we'd fall back to SINGLE mode, which would allow us
to interleave general-purpose registers too (resulting in even less
likelihood of spilling). But at the moment, the vec4 generator and
visitor classes don't have the infrastructure to interleave general
purpose registers, so DUAL_INSTANCED is the best we can do.
As a side benefit this paves the way for implementing instanced
geometry shaders (which are incompatible with DUAL_OBJECT mode).
Since most geometry shaders used in piglit testing are small,
DUAL_INSTANCED mode won't get exercised very much in a normal piglit
run. To force DUAL_INSTANCED mode to be used for all geometry
shaders, set INTEL_DEBUG=nodualobj.
Reviewed-by: Eric Anholt <eric@anholt.net>
Paul Berry [Wed, 16 Oct 2013 20:18:11 +0000 (13:18 -0700)]
i965/gs: Fix up gl_PointSize input swizzling for DUAL_INSTANCED gs.
Geometry shaders that run in "DUAL_INSTANCED" mode store their inputs
in vec4's. This means that when compiling gl_PointSize input
swizzling (a MOV instruction which uses a geometry shader input as
both source and destination), we need to do two things:
- Set force_writemask_all to ensure that the MOV happens regardless of
which channels are enabled.
- Set the source register region to <4;4,1> (instead of <0;4,1> to
satisfy register region restrictions.
v2: move the source register region fixup to the top of
vec4_generator::generate_vec4_instruction(), so that it applies to all
instructions rather than just MOV.
Reviewed-by: Eric Anholt <eric@anholt.net>
Paul Berry [Wed, 16 Oct 2013 19:04:19 +0000 (12:04 -0700)]
i965/gs: Add the ability to compile a DUAL_INSTANCED geometry shader.
Not yet enabled.
Reviewed-by: Eric Anholt <eric@anholt.net>
Paul Berry [Wed, 16 Oct 2013 19:13:20 +0000 (12:13 -0700)]
i965/vec4: Add the ability to suppress register spilling.
In future patches, this will allow us to first try compiling a
geometry shader in DUAL_OBJECT mode (which is more efficient but uses
more registers) and then if spilling is required, fall back on
DUAL_INSTANCED mode.
Reviewed-by: Eric Anholt <eric@anholt.net>
Paul Berry [Wed, 16 Oct 2013 20:13:20 +0000 (13:13 -0700)]
i965/vec4: if register allocation fails, don't try to schedule.
Otherwise the scheduler would be invoked with prog_data->total_grf ==
0, causing havoc.
In a future patch, this will allow us to try compiling a geometry
shader in DUAL_OBJECT mode with spilling disabled, and then fall back
to DUAL_INSTANCED mode if that failed.
Reviewed-by: Eric Anholt <eric@anholt.net>
Paul Berry [Wed, 16 Oct 2013 18:40:41 +0000 (11:40 -0700)]
i965/vec4: Add the ability for attributes to be interleaved.
When geometry shaders are operated in "single" or "dual instanced"
mode, a single set of geometry shader inputs is interleaved into the
thread payload (with each payload register containing a pair of
inputs) in order to save register space.
This patch modifies vec4_visitor::lower_attributes_to_hw_regs so that
it can handle the interleaved format.
Reviewed-by: Eric Anholt <eric@anholt.net>
Paul Berry [Sat, 19 Oct 2013 20:26:27 +0000 (13:26 -0700)]
i965/gs: Set force_writemask_all when setting up g0.
All geometry shaders begin this instruction:
mov(1) g0.2<1>:ud 0x0:ud { align1 }
which sets up GRF0 properly for scratch reads and writes. Since this
instruction has a SIMD size of 1, it will only have an effect if the
first channel is enabled. In practice, the hardware seems to always
dispatch geometry shaders with the first channel enabled, but I can't
find anything in the docs to guarantee that.
So to be on the safe side, set force_writemask_all on the instruction,
which guarantees that it will have the desired effect regardless of
which channels are enabled.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Paul Berry [Wed, 23 Oct 2013 14:55:09 +0000 (07:55 -0700)]
glsl: set explicit_location correctly in lower_named_interface_blocks.
When lower_named_interface_blocks lowers a built-in interface block
member to an ir_variable, it needs to set explicit_location in the
ir_variable. Otherwise the linker gets confused and treats the
variable as a generic varying.
Fixes the following piglit tests, which were regressed by commit
63974c0 (glsl: Simplify the interface to
link_invalidate_variable_locations):
- clip-distance-bulk-copy
- clip-distance-in-bulk-read
- clip-distance-in-explicitly-sized
- clip-distance-in-param
- clip-distance-in-values
- core-inputs
- gs-redeclares-both-pervertex-blocks
- gs-redeclares-pervertex-in-only
- redeclare-pervertex-subset-vs-to-gs
- unsized-in-named-interface-block-gs
- unsized-in-named-interface-block-multiple
- unsized-in-unnamed-interface-block-gs
- unsized-in-unnamed-interface-block-multiple
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=70820
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Paul Berry [Wed, 23 Oct 2013 17:19:39 +0000 (10:19 -0700)]
i965/gs: Precompile geometry shaders.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Paul Berry [Wed, 23 Oct 2013 17:17:30 +0000 (10:17 -0700)]
i965/vec4: Extract function to set up vec4 prog key for precompiling.
This will allow us to re-use it for precompiling geometry shaders.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Paul Berry [Wed, 23 Oct 2013 18:10:14 +0000 (11:10 -0700)]
i965/vec4: Remove uses_clip_distance from program key.
This should never have been in the program key in the first place,
since it's determined by the shader source, not by GL state. Change
the code to just refer to gl_program::UsesClipDistanceOut directly.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Paul Berry [Wed, 23 Oct 2013 17:59:57 +0000 (10:59 -0700)]
glsl: Move UsesClipDistance from gl_{vertex,geometry}_program into gl_program.
This will make it easier for back-ends to share code between geometry
shader and vertex shader compilation. Also, it is renamed to
"UsesClipDistanceOut" to clarify that (a) in geometry shaders, it
refers to the gl_ClipDistance output rather than the gl_ClipDistance
input, and (b) it is irrelevant in fragment shaders.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Paul Berry [Wed, 23 Oct 2013 19:55:24 +0000 (12:55 -0700)]
glsl/gs: Fix transform feedback of gl_ClipDistance.
Since gl_ClipDistance is lowered from an array of floats to an array
of vec4's during compilation, transform feedback has special logic to
keep track of the pre-lowered array size so that attempting to perform
transform feedback on gl_ClipDistance produces a result with the
correct size.
Previously, this special logic always consulted the vertex shader's
size for gl_ClipDistance. This patch fixes it so that it uses the
geometry shader's size for gl_ClipDistance when a geometry shader is
in use.
Fixes piglit test spec/glsl-1.50/transform-feedback-type-and-size.
v2: Change the type of LastClipDistanceArraySize to "unsigned", and
clarify the comment above it.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Paul Berry [Wed, 23 Oct 2013 20:36:25 +0000 (13:36 -0700)]
i965: Fix gl_MaxCombinedTextureImageUnits.
We've always overriden
ctx->Const.{Vertex,Fragment}Program.MaxTextureImageUnits to reflect
the number of texture image units supported by the hardware (rather
than using the default values assigned by Mesa core) so it seems
sensible to do that for GeometryProgram.MaxTextureImageUnits too. We
set it to 0 if geometry shaders aren't supported.
Once that is done, we can just unconditionally add
GeometryProgram.MaxTextureImageUnits to MaxCombinedTextureImageUnits.
Fixes piglit test "spec/glsl-1.50/built-in
constants/gl_MaxCombinedTextureImageUnits".
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Rob Clark [Thu, 24 Oct 2013 21:53:31 +0000 (17:53 -0400)]
freedreno/a3xx/compiler: relative addressing
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Rob Clark [Thu, 24 Oct 2013 21:45:27 +0000 (17:45 -0400)]
freedreno/a3xx: fix const/rel/const-rel encoding
The encoding of constant, relative, and relative-const src registers is
a bit more complex than originally thought, which gives an extra bit to
encode const reg # at expense of taking a bit from relative offset.
In most cases a3xx seems to actually use a scheme whereby it can encode
an extra bit for const register. You have three possible encodings in
thirteen bits:
register: (11 bits for N.c)
00........... rN.c
relative: (10 bits for N)
010.......... r<a0.x + N>
011.......... c<a0.x + N>
const: (12 bits for N.c)
1............ cN.c
Which means we can deal w/ more consts than previously thought.
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Rob Clark [Thu, 19 Sep 2013 14:17:09 +0000 (10:17 -0400)]
freedreno/a3xx: add blend state
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Rob Clark [Fri, 27 Sep 2013 19:35:19 +0000 (15:35 -0400)]
freedreno/resource: fail more gracefully
Fail more gracefully when buffer allocation/import fails.
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Roland Scheidegger [Wed, 23 Oct 2013 17:13:21 +0000 (19:13 +0200)]
gallivm: implement fully accurate corner filtering for seamless cube maps
d3d10 requires that cube corners are filtered with accurate weights (that
is, the weight of the non-existing corner texel should be evenly distributed
to the other 3 texels). OpenGL does not require this (but recommends it).
This requires us to use different filtering code, since we need per-texel
weights which our 2d lerp doesn't (and can't) do. And of course the (now
per element) weights need to be adjusted too for it to work.
Invoke the new filtering code whenever there's an edge to keep things simpler,
as it will work for edges too not just corners but of course it's only needed
with corners.
More ugly code for not much gain but at least a hacked up cubemap demo
shows very nice corners now... Not sure yet if and how this should be
configurable...
v2: incorporate feedback from Jose, only use special corner filtering code
when there's a corner not when there's only an edge (as corner filtering code
is slower, though a perf difference was only measureable when always
forcing edge code). Plus some minor style fixes.
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Eric Anholt [Sat, 28 Sep 2013 00:03:58 +0000 (17:03 -0700)]
mesa: Remove dricore from the build.
No driver uses it any more, and it's been replaced by megadrivers.
v2: Remove always-on conditional for NEED_LIBPROGRAM (review by Emil)
Reviewed-by: Matt Turner <mattst88@gmail.com> (v1)
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Eric Anholt [Fri, 27 Sep 2013 23:57:11 +0000 (16:57 -0700)]
swrast: Build the driver into the shared mesa_dri_drivers.so.
v2: drop dridir now that it's unused.
v3: Fix linking after rebase when building just swrast from classic but a
drm-using gallium driver.
v4: Consistently put spaces around += in the updated Makefile.am block.
v5: Set a global driverAPI variable so loaders don't have to update to
createNewScreen2() (though they may want to for thread safety).
Reviewed-by: Matt Turner <mattst88@gmail.com> (v3)
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Eric Anholt [Fri, 27 Sep 2013 23:32:40 +0000 (16:32 -0700)]
radeon: Build the driver into the shared mesa_dri_drivers.so.
This required some reordering of headers to ensure that the symbol name
redefines happened before any prototypes.
v2: drop dridir now that it's unused.
v3: Consistently put spaces around += in the updated Makefile.am blocks.
v4: Set a global driverAPI variable so loaders don't have to update to
createNewScreen2() (though they may want to for thread safety).
Reviewed-by: Matt Turner <mattst88@gmail.com> (v2)
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Eric Anholt [Fri, 27 Sep 2013 21:22:59 +0000 (14:22 -0700)]
i915: Build the driver into the shared mesa_dri_drivers.so.
i915 has symbols for formerly-shared code that conflict with i965, so we
define them away using gen-symbol-redefs.py. Options considered:
- This option. Downsides: The symbols in profiling and debugging don't
match the source. The symbol list may change in the future and we won't
notice without manually running the tool again.
- Use objcopy --localize-hidden to automatically demote our symbols to
locals. This didn't work on i965 due to c++ weak symbols (which can't
be localized), but could work on i915. We could do it on i915 only, but
it does produce libtool warnings at link time due to libtool not knowing
if the resulting .o file is safe to link (stupid libtool). Plus you end
up with different symbols of the same name, which is confusing for
debugging too. On the other hand, no future symbol conflicts long term.
- Write our own libelf tool that handles c++ weak symbols like we want and
apply it to all drivers. All the downsides of above, but applies
uniformly across drivers.
- Edit the files to just rename all the i915 or i965 symbols that
conflict. There are on the order of 100 that have a prefix we used to
share, so it would take a bit of typing. Fewest downsides, but still
can have conflicts long term.
Ultimately, this is the least invasive change at the moment, and we can
see if the "more symbol conflicts appear later" thing is a real concern or
not.
Note that the ability to compile a version of i915 without INTEL_DEBUG env
support is dropped. It's too useful.
v2: drop dridir now that it's unused.
v3: Consistently put spaces around += in the updated Makefile.am block.
v4: Set a global driverAPI variable so loaders don't have to update to
createNewScreen2() (though they may want to for thread safety).
Reviewed-by: Matt Turner <mattst88@gmail.com> (v2)
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Eric Anholt [Fri, 27 Sep 2013 22:14:56 +0000 (15:14 -0700)]
dri: Add a tool for generating #defines to namespace driver global symbols.
Acked-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Eric Anholt [Tue, 24 Sep 2013 17:24:07 +0000 (10:24 -0700)]
nouveau: Build the driver into the shared mesa_dri_drivers.so.
v2: drop dridir now that it's unused.
v3: Consistently put spaces around += in the updated Makefile.am block.
v4: Set a global driverAPI variable so loaders don't have to update to
createNewScreen2() (though they may want to for thread safety).
v5: Fix missed public symbol in nouveau. (caught by Emil)
Reviewed-by: Matt Turner <mattst88@gmail.com> (v2)
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Eric Anholt [Wed, 26 Jun 2013 20:04:51 +0000 (13:04 -0700)]
i965: Build the driver into a shared mesa_dri_drivers.so .
Previously, we've split things such that mesa core is in libdricore,
exposing the whole Mesa core interface in the global namespace, and the
i965_dri.so code all links against that. Along with polluting application
namespace terribly, it requires extra PLT indirections and prevents LTO.
Instead, we can build all of the driver contents into the same .so with
just a few symbols exposed to be referenced from the actual driver .so
file, allowing LTO and reducing our exposed symbol count massively.
FPS improvement on GLB2.7 with INTEL_NO_HW=1: 2.61061% +/- 1.16957% (n=50)
(without LTO, just the PLT reductions from this commit)
Note that the X Server requires commit
7ecfab47eb221dbb996ea6c033348b8eceaeb893 to successfully load this driver!
v2: Set a global driverAPI variable so loaders don't have to update to
createNewScreen2() (though they may want to for thread safety).
v3: Drop AM_CPPFLAGS addition (Emil pointed out I'd missed some cflags
that would be necessary, though only if we actually relied on them).
v4: Fix install with DESTDIR set.
Reviewed-by: Matt Turner <mattst88@gmail.com> (v1)
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com> (v2)
Eric Anholt [Thu, 26 Sep 2013 17:51:29 +0000 (10:51 -0700)]
dri: Implement a DRI vtable extension to replace the global driDriverAPI.
As we move to megadrivers, we are unable to build multiple drivers with
the same public global symbol per driver (Think an X Server with an intel
and a nouveau driver, and the X Server implementing indirect for both --
we have to actually talk to the right driver). By slipping the
driDriverAPI vtable into the driver's extension list, we can replace the
usage of the global symbol with usage of the loader-dlsym()ed driver
information.
v2: Pull in the hunk to avoid crashing on null driver_extensions. Thanks,
Emil!
Reviewed-by: Matt Turner <mattst88@gmail.com> (v1)
Reviewed-by: Chad Versace <chad.versace@linux.intel.com>
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Eric Anholt [Fri, 27 Sep 2013 18:39:25 +0000 (11:39 -0700)]
dri: Pass in the dlsym()ed driver extension to screen creation.
This will allow a megadrivers build to reference the actual driver being
loaded from the shared dri_util screen creation code.
v2: Fix indentation, fallback case in EGL (review by Emil).
Reviewed-by: Matt Turner <mattst88@gmail.com> (v1)
Reviewed-by: Chad Versace <chad.versace@linux.intel.com> (v1)
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Eric Anholt [Sat, 12 Oct 2013 00:38:18 +0000 (17:38 -0700)]
gbm: Add support for the new __driDriverGetExtensions interface.
v2: Fix uninitialized variable use in the old-ABI case.
Reviewed-by: Chad Versace <chad.versace@linux.intel.com> (v1)
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Eric Anholt [Tue, 24 Sep 2013 18:05:22 +0000 (11:05 -0700)]
egl: Add an optional function call for getting the DRI driver interface.
v2: Fix asprintf error checking.
Reviewed-by: Matt Turner <mattst88@gmail.com> (v1)
Reviewed-by: Chad Versace <chad.versace@linux.intel.com>
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Eric Anholt [Mon, 23 Sep 2013 21:44:10 +0000 (14:44 -0700)]
glx: Add an optional function call for getting the DRI driver interface.
The previous interface relied on a static struct, which meant that the
driver didn't get a chance to edit the struct before the struct got used.
For megadrivers, I want struct specific to the driver being loaded.
v2: Fix the prototype in the docs (caught by Marek). Since the driver
name was in the function, we didn't need to also pass it in.
v3: Fix asprintf error checking (caught by Matt's gcc).
Reviewed-by: Matt Turner <mattst88@gmail.com> (v1)
Reviewed-by: Chad Versace <chad.versace@linux.intel.com>
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Eric Anholt [Fri, 27 Sep 2013 22:25:40 +0000 (15:25 -0700)]
dri: Move driver config options to dri driver extensions.
This way they aren't all sitting in the global namespace (with the same
name per driver).
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Chad Versace <chad.versace@linux.intel.com>
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Eric Anholt [Wed, 26 Jun 2013 22:15:57 +0000 (15:15 -0700)]
dri: Allow config options to be passed to the loader through extensions.
Turns out already we have this nice mechanism for providing optional
things from the driver to the loader, and I was going to have to rename
the public global symbol to avoid conflicts when doing megadrivers.
While the former __driConfigOptions is technically loader interface, this
is the only loader that made use of that symbol. Continue paying
attention to it if we can't find the new option, to retain compatibility
with old drivers.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Chad Versace <chad.versace@linux.intel.com>
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Eric Anholt [Fri, 27 Sep 2013 22:36:59 +0000 (15:36 -0700)]
glx: Move the driver extension-loading to a helper function.
I'm planning on doing driver extension parsing from 3 places, and making
the extension loading step a bit longer.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Chad Versace <chad.versace@linux.intel.com>
Reviewed-by: Emil Velikov <emil.l.velikov@gmail.com>
Francisco Jerez [Thu, 24 Oct 2013 19:09:55 +0000 (12:09 -0700)]
clover: Query maximum kernel block size from the device instead of the kernel object.
Based on a similar fix from Aaron Watry. It seems unlikely that we
will ever need a kernel-specific setting for this, and the Gallium API
doesn't support it. Remove kernel::max_block_size() altogether.
Brian Paul [Tue, 22 Oct 2013 22:50:57 +0000 (16:50 -0600)]
glsl: silence unused 'var' variable warning
Reviewed-by: Paul Berry <stereotype441@gmail.com>
Brian Paul [Tue, 22 Oct 2013 22:47:38 +0000 (16:47 -0600)]
svga: remove user-space vertex/index buffer code
The gallium vbuf module, which we've been using for some time now, takes
care of uploading user-space vertex/index data into real buffers. The
upload code in the svga driver was unused.
Reviewed-by: José Fonseca <jfonseca@vmware.com>
Chad Versace [Tue, 15 Oct 2013 22:16:19 +0000 (15:16 -0700)]
i965: Print more debuginfo in intel_texsubimage_memcpy()
Print info about packing, format, type, and tiling. This will help debug
future issues with this fastpath.
Reviewed-by: Frank Henigman <fjhenigman@google.com>
Signed-off-by: Chad Versace <chad.versace@linux.intel.com>
Chad Versace [Fri, 18 Oct 2013 21:06:49 +0000 (14:06 -0700)]
i965: Fix glTexImage when packing alignment != cpp
Fixes texture corruption of Weston clients on cairo-glesv2 backend.
Commit
49ed599 introduced the bug.
Corruption occured when glTexSubImage called
intel_texsubimage_tiled_memcpy() with:
x,y=10,9
w,h=7,7
format=GL_ALPHA(0x1906)
type=GL_UNSIGNED_BYTE(0x1401)
gl_format=MESA_FORMAT_A8(0x18)
packing.alignemnt=4
The function miscalculated the source image's stride as w*cpp=7 without
taking into account the packing alignment. The actual stride was 8.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=70435
Reported-by: U. Artie Eoff <ullysses.a.eoff@intel.com>
Tested-by: Kristian Høgsberg <krh@bitplanet.net>
Reviewed-by:Frank Henigman <fjhenigman@google.com>
Signed-off-by: Chad Versace <chad.versace@linux.intel.com>
Rob Clark [Thu, 24 Oct 2013 00:08:15 +0000 (20:08 -0400)]
freedreno: fix compile error
Small typo introduced in
a3ed98f.
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Paul Berry [Tue, 22 Oct 2013 12:56:37 +0000 (05:56 -0700)]
i965/fs: Only unroll high-accuracy dFdy() from SIMD16 to SIMD8 on gen4 and IVB.
In commit
800610f (i965/fs: Improve accuracy of dFdy() to match
dFdx()) I unrolled the high-accuracy dFdy() computation from a single
SIMD16 instruction to two SIMD8 instructions because of text I found
in the i965 (gen4) PRM saying that instruction compression could not
be used in align16 mode. I couldn't find similar text in later
hardware docs, and I observed problems trying to use instruction
compression on align16 mode on Ivy Bridge, so I assumed that the
restriction still applied and the associated documentation had simply
been lost.
After consultation with the hardware engineers, it turns out this is
not the case. In point of fact, the restriction was dropped in gen5,
re-introduced in Ivy Bridge, and dropped again in Haswell. The reason
I didn't notice this is that in the Ivy Bridge documentation, the
restriction was in a different section, and described using different
language.
Now that we know that the restriction only applies to Gen4 and Ivy
Bridge, we can limit the unrolling to those platforms.
Tested on gen5, gen6, and gen7 (both Ivy Bridge and Haswell).
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Paul Berry [Tue, 22 Oct 2013 17:26:52 +0000 (10:26 -0700)]
glsl/gs: Prevent illegal input/output primitive types.
From the GLSL 1.50 spec, section 4.3.8.1 (Input Layout Qualifiers):
The layout qualifier identifiers for geometry shader inputs are
layout-qualifier-id
points
lines
lines_adjacency
triangles
triangles_adjacency
And from section 4.3.8.2 (Output Layout Qualifiers)
The layout qualifier identifiers for geometry shader outputs are
layout-qualifier-id
points
line_strip
triangle_strip
max_vertices = integer-constant
We were erroneously allowing line_strip and triangle_strip to be used
as input qualifiers, and we were allowing lines, lines_adjacency,
triangles, and triangles_adjacency to be used as output qualifiers.
Fixes piglit tests "glsl-1.50-gs-{input,output}-layout-qualifiers *".
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Eric Anholt [Mon, 7 Oct 2013 21:34:00 +0000 (14:34 -0700)]
i965: Add perf debug hint when the app makes us do index buffer scanning.
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Eric Anholt [Fri, 4 Oct 2013 03:03:41 +0000 (20:03 -0700)]
i965: Try to avoid stalls on the GPU when doing glBufferSubData().
On DOTA2, framerate on dota2-de1.dem in windowed mode on my laptop
improves by 7.69854% +/- 0.909163% (n=3). In a microbenchmark hitting
this code path (wall time of piglit vbo-subdata-many), runtime decreases
from 0.8 to 0.05 seconds.
v2: Use out of range start/end instead of separate bool for the active
flag (suggestion by Jordan), fix double-upload in the stalling path.
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Eric Anholt [Tue, 8 Oct 2013 00:31:04 +0000 (17:31 -0700)]
i965: Be sure to reset brw->vb.buffers[] when trying to redo vertex setup.
The brw_prepare_vertices that sets up buffers[] depends on these
parameters, so don't let brw_prepare_vertices() skip it.
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Eric Anholt [Sat, 5 Oct 2013 00:46:04 +0000 (17:46 -0700)]
i965: Add support for GL_ARB_texture_buffer_range.
Supporting this extension turns out to simplify our code a bit over not
supporting this extension, once the glBufferSubData() synchronization code
lands.
v2: Use 16 byte alignment like we do for uniform buffers, due to unaligned
access penalties.
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com> (v1)
Eric Anholt [Fri, 4 Oct 2013 02:36:03 +0000 (19:36 -0700)]
i965: Add a note about the late-allocation in intel_bufferobj_buffer().
This was mostly for the i915 system-memory VBO code, which we don't have
any more, but since that existed we've ended up producing dependencies on
it being there.
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Eric Anholt [Fri, 4 Oct 2013 02:34:41 +0000 (19:34 -0700)]
i965: Drop intel_bufferobj_source().
Since src_offset was always 0, it wasn't doing anything for us beyond
intel_bufferobj_buffer().
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Eric Anholt [Fri, 4 Oct 2013 23:13:00 +0000 (16:13 -0700)]
i965: Fix texture buffer rendering after a whole buffer replacement.
If glBufferData(), glBufferSubData(0, obj->Size), or similar happens, we
get a new drm_intel_bo for the buffer object, and thus need to re-upload
texture buffer state so we point at the new data.
Fixes the new piglit GL_ARB_texture_buffer_object/data-sync
Cc: "9.2" <mesa-stable@lists.freedesktop.org>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
David Heidelberger [Wed, 23 Oct 2013 19:25:12 +0000 (21:25 +0200)]
Brian Paul [Wed, 23 Oct 2013 19:16:34 +0000 (13:16 -0600)]
nv50: clamp PIPE_SHADER_CAP_MAX_TEXTURE_SAMPLERS to PIPE_MAX_SAMPLERS
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=70212
Tested-by: Aaron Watry <awatry@gmail.com>
Brian Paul [Wed, 23 Oct 2013 18:30:36 +0000 (12:30 -0600)]
radeonsi: remove unused si_set_cs_sampler_view()
Fixes build breakage.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=70804
Tested-by: Vinson Lee <vlee@freedesktop.org>
Brian Paul [Tue, 8 Oct 2013 00:16:22 +0000 (18:16 -0600)]
gallium: new, unified pipe_context::set_sampler_views() function
The new function replaces four old functions: set_fragment/vertex/
geometry/compute_sampler_views().
Note: at this time, it's expected that the 'start' parameter will
always be zero.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Tested-by: Emil Velikov <emil.l.velikov@gmail.com>
Brian Paul [Sat, 19 Oct 2013 17:22:33 +0000 (11:22 -0600)]
svga: remove unneeded include of u_double_list.h
Kenneth Graunke [Tue, 28 May 2013 02:51:35 +0000 (19:51 -0700)]
i965: Expose write_reg() as brw_store_register_mem64().
Writing a 64-bit register value to memory is sufficiently complicated
that it makes sense to reuse this function rather than duplicating it.
Exposing it outside of gen6_queryobj.c means it needs a more descriptive
function name. It could probably be moved to brw_util.c or somewhere
else, but this works too.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Kenneth Graunke [Tue, 28 May 2013 02:44:44 +0000 (19:44 -0700)]
i965: Move flushing out of write_reg and into the callers.
The current callers just want to write a single register, so combining
the register read with a pipeline flush made sense. However, in the
future we'll want to do multiple register reads back to back, and we'll
only want to flush once.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>