Samuel Pitoiset [Wed, 30 Mar 2016 22:50:39 +0000 (00:50 +0200)]
nvc0/ir: add support for compute UBOs on Kepler
Make sure to avoid out of bounds access in presence of indirect
array indexing by loading the size from the driver constant buffer.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Samuel Pitoiset [Thu, 14 Jan 2016 17:24:53 +0000 (18:24 +0100)]
nvc0: add indirect compute support on Kepler
The grid size is stored as three 32-bits integers in the indirect
buffer but the launch descriptor uses a 32-bits integer for both
griddim_y and griddim_z like this (z << 16) | y. To make it work,
the 16 high bits of griddim_y are overwritten by griddim_z.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Samuel Pitoiset [Mon, 22 Feb 2016 20:44:25 +0000 (21:44 +0100)]
nvc0: reduce likelihood of collision for real buffers on Kepler
Reduce likelihood of collision with real buffers by placing the
hole at the top of the 4G area. This fixes some indirect draw+compute
tests with large buffers.
Suggested by Ilia Mirkin.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Samuel Pitoiset [Wed, 30 Mar 2016 22:50:23 +0000 (00:50 +0200)]
nvc0: store ubo info to the driver constbuf on Kepler
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Samuel Pitoiset [Mon, 11 Jan 2016 20:22:58 +0000 (21:22 +0100)]
nvc0: bind user uniforms for compute on Kepler
Uniform buffer objects will be sticked to the driver constant buffer
like buffers because the launch descriptor only allows 8 CBs.
Input kernel parameters for OpenCL are still uploaded to screen->parm
which is bound on c0, but this will be changed later with a new series.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Samuel Pitoiset [Mon, 11 Jan 2016 15:05:59 +0000 (16:05 +0100)]
nvc0: bind shader buffers for compute on Kepler
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Samuel Pitoiset [Wed, 24 Feb 2016 16:03:57 +0000 (17:03 +0100)]
nvc0: bind driver cb for compute on c7[] for Kepler
Instead of using the screen->parm buffer object which will be removed,
upload auxiliary constants to uniform_bo to be consistent regarding
what we already do for Fermi.
This breaks surfaces support (for compute only) but this will be
properly re-introduced later for ARB_shader_image_load_store.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Jose Fonseca [Fri, 1 Apr 2016 20:17:18 +0000 (21:17 +0100)]
gallivm: Prevent disassembly debug output from being truncated.
By using os_log_message directly, as _debug_vprintf truncates messages
to 4K.
Also cleanup the disassemble interface.
Spotted by Roland.
Trivial.
Rob Clark [Tue, 29 Mar 2016 14:49:03 +0000 (10:49 -0400)]
compiler: random comment fixup
Just noticed this in passing.. gl_shader_stage already has tess so this
comment no longer applies.
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Brian Paul [Thu, 31 Mar 2016 16:30:07 +0000 (10:30 -0600)]
docs: minor updates to license.html file
Mesa demos are no longer part of the main Mesa tree/tarball.
Add Gallium and GLX code to list of major components.
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Mauro Rossi [Sun, 21 Feb 2016 19:57:47 +0000 (20:57 +0100)]
radeonsi: use util_strchrnul() to fix android build error
Android Bionic does not support strchrnul() string function,
gallium auxiliary util/u_string.h provides util_strchrnul()
This change avoids the following building error:
external/mesa/src/gallium/drivers/radeonsi/si_shader.c:3863: error:
undefined reference to 'strchrnul'
collect2: error: ld returned 1 exit status
Cc: mesa-stable@lists.freedesktop.org
Signed-off-by: Emil Velikov <emil.velikov@collabora.com>
Rob Herring [Tue, 2 Feb 2016 20:23:11 +0000 (14:23 -0600)]
egl: android: enable EGL_FRAMEBUFFER_TARGET_ANDROID and EGL_RECORDABLE_ANDROID
Set EGL_FRAMEBUFFER_TARGET_ANDROID and EGL_RECORDABLE_ANDROID config
attributes to true for Android. These are required in Marshmallow.
The implementation of EGL_RECORDABLE_ANDROID support has 2 options in
the definition of the extension. Android implements the 2nd option
which is the encoder must support RGB input. The requested input format
is RGB888, so setting the attribute on all the native Android visual
formats should be sufficient.
Similarly, setting EGL_FRAMEBUFFER_TARGET_ANDROID for all configs with
a EGL_NATIVE_VISUAL_ID should be sufficient. Most likely, the HWC should
support the same set of formats the underlying DRM driver supports.
Cc: mesa-stable@lists.freedesktop.org
Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Rob Herring [Tue, 2 Feb 2016 20:23:08 +0000 (14:23 -0600)]
egl: Add EGL_RECORDABLE_ANDROID attribute
This is used by Android to select an eglconfig compatible with screen
recording.
Cc: mesa-stable@lists.freedesktop.org
Signed-off-by: Rob Herring <robh@kernel.org>
[Emil Velikov: add the _eglIsConfigAttribValid check]
Signed-off-by: Emil Velikov <emil.velikov@collabora.com>
Rob Herring [Tue, 2 Feb 2016 20:23:07 +0000 (14:23 -0600)]
egl: Add EGL_FRAMEBUFFER_TARGET_ANDROID attribute
This is used by Android to select an eglconfig compatible with HWComposer.
Cc: mesa-stable@lists.freedesktop.org
Signed-off-by: Rob Herring <robh@kernel.org>
[Emil Velikov: add the _eglIsConfigAttribValid check]
Signed-off-by: Emil Velikov <emil.velikov@collabora.com>
Rob Herring [Tue, 2 Feb 2016 20:45:07 +0000 (14:45 -0600)]
Android: fix x86 gallium builds
Builds with gallium enabled fail on x86 with linker error:
external/mesa3d/src/mesa/vbo/vbo_exec_array.c:127: error: undefined reference to '_mesa_uint_array_min_max'
The problem is sse_minmax.c is not included in the libmesa_st_mesa
library. Since the SSE4.1 files are needed for both libmesa_st_mesa
and libmesa_dricore, move SSE4.1 files into a separate static library
that can be used by both.
Cc: "11.1 11.2" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Rob Herring <robh@kernel.org>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Jose Fonseca [Thu, 31 Mar 2016 22:37:34 +0000 (23:37 +0100)]
gallivm: Use vector selects on LLVM 3.3+.
This is an old patch I had around.
Vector selects seem to work well from LLVM 3.3. Using them should
improve code quality, as it might make constant propagation pass more
effective.
Tested lp_test_*
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Alejandro Piñeiro [Fri, 1 Apr 2016 07:11:15 +0000 (09:11 +0200)]
glsl: do not raise unitialized variable warnings on builtins/reserved GL variables
Needed because not all the built-in variables are marked as system
values, so they still have the mode ir_var_auto. Right now it fixes
raising the warning when gl_GlobalInvocationID and
gl_LocalInvocationIndex are used.
v2: use is_gl_identifier instead of filtering for some names (Ilia
Mirkin)
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Ilia Mirkin [Fri, 1 Apr 2016 01:52:13 +0000 (21:52 -0400)]
nv50,nvc0: add PIPE_BIND_LINEAR support to is_format_supported
vdpau has recently come to rely on this, so make sure to check it
properly.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Ilia Mirkin [Thu, 31 Mar 2016 04:48:01 +0000 (00:48 -0400)]
mesa: add GL_OES/EXT_draw_buffers_indexed support
This is the same ext as ARB_draw_buffers_blend (plus some core
functionality that already exists). Add the alias entrypoints.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Kenneth Graunke [Thu, 31 Mar 2016 07:53:21 +0000 (00:53 -0700)]
i965: Use brw->urb.min_vs_urb_entries instead of 32 for BLORP.
Haswell GT2 and GT3 have a minimum of 64 entries. Hardcoding 32
is not legal.
v2: Delete stale comment (caught by Alejandro).
Cc: mesa-stable@lists.freedesktop.org
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Kenneth Graunke [Tue, 29 Mar 2016 16:58:11 +0000 (09:58 -0700)]
i965: Fix textureSize() depth value for 1 layer surfaces on Gen4-6.
According to the Sandybridge PRM's description of the resinfo message,
the .z value returned will be Depth == 0 ? 0 : Depth + 1. The earlier
PRMs have the same table.
This means we return 0 for array textures with a single slice, when
we ought to return 1. Just override it to max(depth, 1).
Fixes 10 dEQP-GLES3.functional tests on Sandybridge:
shaders.texture_functions.texturesize.sampler2darray_fixed_vertex
shaders.texture_functions.texturesize.sampler2darray_fixed_fragment
shaders.texture_functions.texturesize.sampler2darray_float_vertex
shaders.texture_functions.texturesize.sampler2darray_float_fragment
shaders.texture_functions.texturesize.isampler2darray_vertex
shaders.texture_functions.texturesize.isampler2darray_fragment
shaders.texture_functions.texturesize.usampler2darray_vertex
shaders.texture_functions.texturesize.usampler2darray_fragment
shaders.texture_functions.texturesize.sampler2darrayshadow_vertex
shaders.texture_functions.texturesize.sampler2darrayshadow_fragment
Cc: mesa-stable@lists.freedesktop.org
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Tue, 29 Mar 2016 22:25:04 +0000 (15:25 -0700)]
nir: Simplify a bcsel to logical-or
Oddly, this did not affect the shader where I first noticed the pattern.
That particular shader doesn't get its if-statement converted to a bcsel
because there are two assignments in the else-statement. This led to me
submitting https://bugs.freedesktop.org/show_bug.cgi?id=94747.
shader-db results:
Sandy Bridge
total instructions in shared programs: 8467384 -> 8467069 (-0.00%)
instructions in affected programs: 36594 -> 36279 (-0.86%)
helped: 46
HURT: 0
total cycles in shared programs:
117573448 ->
117568518 (-0.00%)
cycles in affected programs: 339114 -> 334184 (-1.45%)
helped: 46
HURT: 0
Ivy Bridge / Haswell / Broadwell / Skylake:
total instructions in shared programs: 7774258 -> 7773999 (-0.00%)
instructions in affected programs: 30874 -> 30615 (-0.84%)
helped: 46
HURT: 0
total cycles in shared programs:
65739190 ->
65734530 (-0.01%)
cycles in affected programs: 180380 -> 175720 (-2.58%)
helped: 45
HURT: 1
No change on G45 or Ironlake.
I also tried these expressions, but none of them affected any shaders in
shader-db:
(('bcsel', a, 'a@bool', 'b@bool'), ('ior', a, b)),
(('bcsel', a, 'b@bool', False), ('iand', a, b)),
(('bcsel', a, 'b@bool', 'a@bool'), ('iand', a, b)),
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Ian Romanick [Thu, 24 Mar 2016 22:48:55 +0000 (15:48 -0700)]
ptn: Fix all users of ptn_swizzle
None of the callers actually wanted what it did. In ptn_xpd, you only
ever want a vec3 swizzle. In ptn_tex, you want a swizzle that matches
the number of required texture coordinates.
shader-db results:
G45:
total instructions in shared programs: 4011240 -> 4010911 (-0.01%)
instructions in affected programs: 59232 -> 58903 (-0.56%)
helped: 114
HURT: 0
total cycles in shared programs:
84314194 ->
84313220 (-0.00%)
cycles in affected programs: 779150 -> 778176 (-0.13%)
helped: 110
HURT: 13
Ironlake:
total instructions in shared programs: 6397262 -> 6396605 (-0.01%)
instructions in affected programs: 117402 -> 116745 (-0.56%)
helped: 227
HURT: 0
total cycles in shared programs:
128889798 ->
128888524 (-0.00%)
cycles in affected programs: 1214644 -> 1213370 (-0.10%)
helped: 179
HURT: 44
Sandy Bridge:
total instructions in shared programs: 8467391 -> 8467384 (-0.00%)
instructions in affected programs: 3107 -> 3100 (-0.23%)
helped: 10
HURT: 6
total cycles in shared programs:
117580120 ->
117573448 (-0.01%)
cycles in affected programs: 103158 -> 96486 (-6.47%)
helped: 84
HURT: 11
Ivy Bridge:
total instructions in shared programs: 7774255 -> 7774258 (0.00%)
instructions in affected programs: 1677 -> 1680 (0.18%)
helped: 8
HURT: 6
total cycles in shared programs:
65743828 ->
65739190 (-0.01%)
cycles in affected programs: 89312 -> 84674 (-5.19%)
helped: 78
HURT: 23
Haswell:
total instructions in shared programs: 7107172 -> 7107150 (-0.00%)
instructions in affected programs: 2048 -> 2026 (-1.07%)
helped: 16
HURT: 0
total cycles in shared programs:
64653636 ->
64647486 (-0.01%)
cycles in affected programs: 86836 -> 80686 (-7.08%)
helped: 85
HURT: 17
Broadwell and Skylake:
total instructions in shared programs: 8447529 -> 8447507 (-0.00%)
instructions in affected programs: 2038 -> 2016 (-1.08%)
helped: 16
HURT: 0
total cycles in shared programs:
66418670 ->
66413416 (-0.01%)
cycles in affected programs: 90110 -> 84856 (-5.83%)
helped: 83
HURT: 20
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Ian Romanick [Tue, 29 Mar 2016 00:27:36 +0000 (17:27 -0700)]
ptn: Silence unused parameter warning
The KIL instruction doesn't have a destination, so ptn_kil never uses
dest.
program/prog_to_nir.c: In function ‘ptn_kil’:
program/prog_to_nir.c:547:38: warning: unused parameter ‘dest’ [-Wunused-parameter]
ptn_kil(nir_builder *b, nir_alu_dest dest, nir_ssa_def **src)
^
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Samuel Pitoiset [Thu, 31 Mar 2016 08:54:18 +0000 (10:54 +0200)]
tgsi: silence compiler warning in fetch_sampler_unit()
The unit variable can be used uninitialized.
Fixes:
24e77cb09 ("tgsi: handle indirect sampler arrays. (v2)")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Samuel Pitoiset [Thu, 31 Mar 2016 08:54:17 +0000 (10:54 +0200)]
tgsi: fix out of bounds access in exec_atomop()
The number of channels must be 4 for all RGBA components.
Fixes:
22d129601 ("tgsi: add support for image operations to tgsi_exec. (v2.1)")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Brian Paul [Wed, 30 Mar 2016 22:54:08 +0000 (16:54 -0600)]
tgsi: split tgsi_util_get_texture_coord_dim() function into two
It was kind of overloaded, returning two different things. Now get
the index of the shadow reference src register with a new
tgsi_util_get_shadow_ref_src_index() function.
To verify the new code, I added some temp/debug code which looped
over all TGSI_TEXTURE_x values, calling the old function and new and
checking that the returned indexes matched.
Also tested piglit "shadow" tests with softpipe/llvmpipe.
No testing of ilo and radeonsi changes.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Brian Paul [Wed, 30 Mar 2016 15:55:56 +0000 (09:55 -0600)]
tgsi: skip texture query opcodes when examining texture targets
Should fix the assertion in piglit
spec@arb_gpu_shader5@texturegather@fs-r-none-shadow-2d when the
TXQ instruction specifies a 2D target but the sampler view was
declared as SHADOW2D.
Reviewed-by: Michel Dänzer <michel.daenzer@amd.com>
Tested-by: Michel Dänzer <michel.daenzer@amd.com>
Pierre Moreau [Sat, 19 Mar 2016 13:04:54 +0000 (14:04 +0100)]
nv50/ir: Check for valid insn instead of def size
This fixes a null pointer dereference during the register allocation pass,
if a function had arguments.
Functions arguments get a definition from the function itself, a definition
which is therefore not linked to any instruction. If a value ends up having
a definition but no linked instruction, the register allocation pass doesn't
need to consider whether that value is generated by an instruction that
can only handle "short" registers (on nv50).
Signed-off-by: Pierre Moreau <pierre.morrow@free.fr>
Ilia Mirkin [Wed, 17 Feb 2016 18:27:14 +0000 (13:27 -0500)]
mesa: add GL_EXT_copy_image support
The extension is identical to GL_OES_copy_image. But dEQP has tests that
want the EXT variant.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Ilia Mirkin [Tue, 16 Feb 2016 01:34:52 +0000 (20:34 -0500)]
mesa: add GL_OES_copy_image support
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Ilia Mirkin [Thu, 31 Mar 2016 02:03:06 +0000 (22:03 -0400)]
mesa: remove duplicate MAX_GEOMETRY_SHADER_INVOCATIONS entry
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Ilia Mirkin [Tue, 16 Feb 2016 06:27:27 +0000 (01:27 -0500)]
st/mesa: add ES sample-shading support
We require the full ARB_gpu_shader5 for now, but in the future some
other CAP could get exposed to indicate that only the multisample-related
behavior of ARB_gpu_shader5 is available.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Ilia Mirkin [Sat, 20 Feb 2016 20:03:55 +0000 (15:03 -0500)]
mesa: add GL_OES_shader_multisample_interpolation support
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Ilia Mirkin [Tue, 16 Feb 2016 19:29:38 +0000 (14:29 -0500)]
mesa: add GL_OES_sample_shading support
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Ilia Mirkin [Fri, 19 Feb 2016 18:23:10 +0000 (13:23 -0500)]
glsl: add GL_OES_sample_variables support
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Ilia Mirkin [Tue, 16 Feb 2016 06:20:15 +0000 (01:20 -0500)]
mesa: add OES_sample_variables to extension table, add enable bit
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Ilia Mirkin [Fri, 19 Feb 2016 18:20:48 +0000 (13:20 -0500)]
glsl: add gl_MaxSamples, new in GL 4.5 / GL ES 3.2
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Matt Turner [Sun, 13 Mar 2016 05:16:03 +0000 (21:16 -0800)]
i965: Don't add barrier deps for FB write messages.
Ken did this earlier, and this is just me reimplementing his patch a
little differently.
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Matt Turner [Sun, 13 Mar 2016 05:15:19 +0000 (21:15 -0800)]
i965: Add and use is_scheduling_barrier() function.
Matt Turner [Mon, 15 Feb 2016 18:43:39 +0000 (10:43 -0800)]
i965: Remove NOP insertion kludge in scheduler.
Instead of removing every instruction in add_insts_from_block(), just
move the instruction to its scheduled location. This is a step towards
doing both bottom-up and top-down scheduling without conflicts.
Note that this patch changes cycle counts for programs because it begins
including control flow instructions in the estimates.
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Matt Turner [Mon, 15 Feb 2016 18:42:14 +0000 (10:42 -0800)]
i965: Assert that an instruction is not inserted around itself.
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Matt Turner [Mon, 15 Feb 2016 18:05:33 +0000 (10:05 -0800)]
i965: Relax restriction on scheduling last instruction.
I think when this code was written, basic blocks were always ended by a
control flow instruction or an end-of-thread message. That's no longer
the case, and removing this restriction actually helps things:
instructions in affected programs: 7267 -> 7244 (-0.32%)
helped: 4
total cycles in shared programs:
66559580 ->
66431900 (-0.19%)
cycles in affected programs:
28310152 ->
28182472 (-0.45%)
helped: 9577
HURT: 879
GAINED: 2
The addition of the is_control_flow() checks is not a functional change,
since the add_insts_from_block() does not put them in the list of
instructions to schedule. I plan to change this in a later patch.
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Matt Turner [Tue, 15 Mar 2016 00:39:19 +0000 (17:39 -0700)]
i965/vec4/tcs: Set conditional mod on TCS_OPCODE_SRC0_010_IS_ZERO.
Missing this causes an assertion failure in the scheduler with the next
patch.
Additionally, this gives cmod propagation enough information to optimize
code better.
total instructions in shared programs: 7112991 -> 7112852 (-0.00%)
instructions in affected programs: 25704 -> 25565 (-0.54%)
helped: 139
total cycles in shared programs:
64812898 ->
64810674 (-0.00%)
cycles in affected programs: 127224 -> 125000 (-1.75%)
helped: 139
Acked-by: Francisco Jerez <currojerez@riseup.net>
Matt Turner [Wed, 17 Feb 2016 19:04:50 +0000 (11:04 -0800)]
Revert "i965: Don't add barrier deps for FB write messages."
This reverts commit
d0e1d6b7e27bf5f05436e47080d326d7daa63af2.
The change in the vec4 code is a mistake -- there's never an
FS_OPCODE_FB_WRITE in vec4 code.
The change in the fs code had the (harmless) effect of not recognizing
an FB_WRITE as a scheduling barrier even if it was marked EOT --
harmless because the scheduler marked the last instruction of a block as
a barrier, something I'm changing in the following patches.
This will be reimplemented later in the series.
Matt Turner [Mon, 15 Feb 2016 07:21:03 +0000 (23:21 -0800)]
i965: Simplify full scheduling-barrier conditions.
All of these were simply code for "architecture register file" (and in
the case of destinations, "not the null register").
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Matt Turner [Mon, 15 Feb 2016 07:23:53 +0000 (23:23 -0800)]
i965: Remove incorrect cycle estimates.
These printed the cycle count the last basic block (sched.time is set
per basic block!). We have accurate, full program, data printed
elsewhere.
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Dave Airlie [Thu, 31 Mar 2016 02:35:25 +0000 (12:35 +1000)]
st/mesa: fix fallout from xfb changes.
Failed to update state tracker with new buffer interface.
Reviewed-by: Timothy Arceri <timothy.arceri@collabora.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Matt Turner [Thu, 31 Mar 2016 02:18:16 +0000 (19:18 -0700)]
nir: Fix typo from commit
6702f1acde9.
Timothy Arceri [Thu, 10 Mar 2016 05:41:03 +0000 (16:41 +1100)]
docs: mark xfb_* qualifiers as DONE
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Thu, 10 Mar 2016 05:17:13 +0000 (16:17 +1100)]
mesa: add query support for GL_TRANSFORM_FEEDBACK_BUFFER interface
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Thu, 10 Mar 2016 04:04:02 +0000 (15:04 +1100)]
glsl: add transform feedback buffers to resource list
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Thu, 10 Mar 2016 04:57:19 +0000 (15:57 +1100)]
mesa: add support to query GL_TRANSFORM_FEEDBACK_BUFFER_INDEX
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Thu, 10 Mar 2016 00:40:37 +0000 (11:40 +1100)]
mesa: add support to query GL_OFFSET for GL_TRANSFORM_FEEDBACK_VARYING
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Thu, 10 Mar 2016 04:20:32 +0000 (15:20 +1100)]
mesa: rename tranform feeback varying macro XFB to XFV
A latter patch will use XFB for buffers.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Mon, 14 Mar 2016 00:16:55 +0000 (11:16 +1100)]
glsl: always enable transform feedback mode when xfb_stride defined
This enables in shader defined transform feedback mode even if the
only place xfb_stride is defined is on the global out.
We don't worry about xfb_buffer since Issue 22 c) in the spec says:
"If the shader has an "xfb_buffer" qualifier identifying a buffer,
but doesn't declare "xfb_offset" on anything associated with it,
what happens?
...
variables not qualified with "xfb_offset" are not captured, which
makes the associated "xfb_buffer" qualifier irrelevant."
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Sun, 13 Mar 2016 23:32:17 +0000 (10:32 +1100)]
glsl: handle varyings that are not written to but have an xfb_offset
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Sun, 13 Mar 2016 23:17:48 +0000 (10:17 +1100)]
glsl: when lowering named interface set assigned flag
This will be used when checking if xfb should attempt to capture
a varying.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Sun, 13 Mar 2016 05:36:25 +0000 (16:36 +1100)]
glsl: reset current stream tracker
When we move to the next buffer we need to reset the stream
so that we don't generate an error message about streams not
matching.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Fri, 11 Mar 2016 02:53:13 +0000 (13:53 +1100)]
glsl: generate link error when implicit stride is to large
This moves the check until after we have done the stride
calculation and applies it to the xfb_* qualifiers.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Thu, 3 Mar 2016 04:26:53 +0000 (15:26 +1100)]
glsl: add xfb_stride link time validation
From the ARB_enhanced_layous spec:
"It is a compile-time or link-time error to have any *xfb_offset*
that overflows *xfb_stride*, whether stated on declarations before
or after the *xfb_stride*, or in different compilation units.
...
When no *xfb_stride* is specified for a buffer, the stride of a
buffer will be the smallest needed to hold the variable placed at
the highest offset, including any required padding."
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Fri, 11 Mar 2016 00:57:52 +0000 (11:57 +1100)]
glsl: validate global out xfb_stride qualifiers and set stride on empty buffers
Here we use the built-in validation in
ast_layout_expression::process_qualifier_constant() to check for mismatching
global out strides on buffers in a single shader.
From the ARB_enhanced_layouts spec:
"While *xfb_stride* can be declared multiple times for the same buffer,
it is a compile-time or link-time error to have different values
specified for the stride for the same buffer."
For intrastage validation a new helper link_xfb_stride_layout_qualifiers()
is created. We also take this opportunity to make sure stride is at least
a multiple of 4, we will validate doubles at a later stage.
From the ARB_enhanced_layouts spec:
"If the buffer is capturing any double-typed outputs, the stride must
be a multiple of 8, otherwise it must be a multiple of 4, or a
compile-time or link-time error results."
Finally we update store_tfeedback_info() to apply the strides to
LinkedTransformFeedback and update the buffers bitmask to mark any global
buffers with a stride as active. For example a shader with:
layout (xfb_buffer = 0, xfb_offset = 0) out vec4 gs_fs;
layout (xfb_buffer = 1, xfb_stride = 64) out;
Is expected to have a buffer bound to both 0 and 1.
From the ARB_enhanced_layouts spec:
"A binding point requires a bound buffer object if and only if its
associated stride in the program object used for transform feedback
primitive capture is non-zero."
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Thu, 10 Mar 2016 04:00:00 +0000 (15:00 +1100)]
mesa: split transform feedback buffer into its own struct
This will be used in a following patch to implement interface
query support for TRANSFORM_FEEDBACK_BUFFER.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Thu, 3 Mar 2016 02:20:01 +0000 (13:20 +1100)]
glsl: use bitmask of active xfb buffer indices
This allows us to print the correct binding point when not all
buffers declared in the shader are bound.
For example if we use a single buffer:
layout(xfb_buffer=2, offset=0) out vec4 v;
We now print '2' when the buffer is not bound rather than '0'.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Fri, 11 Mar 2016 12:16:16 +0000 (23:16 +1100)]
glsl: sort xfb varyings in offset/buffer order
The existing transform feedback code expects to receive the list
of varyings in increasing buffer order.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Wed, 24 Feb 2016 05:40:32 +0000 (16:40 +1100)]
glsl: basic linking support for xfb qualifiers
This adds the initial infrastructure for enabling transform feedback
mode via in shader qualifiers and adds initial buffer support.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Wed, 24 Feb 2016 05:37:02 +0000 (16:37 +1100)]
glsl: add xfb helpers and fields to the tfeedback_decl class
We also apply any array/struct offsets.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Wed, 24 Feb 2016 05:27:03 +0000 (16:27 +1100)]
glsl: add helper to process xfb qualifiers during linking
This function checks for any xfb_* qualifiers which will enable
transform feedback mode and cause any API defined xfb varyings
to be ignored.
It also counts the number of varyings that have a xfb_offset
qualifier and finally it calls the create_xfb_varying_names()
helper to generate the names of varyings to be caputured.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Wed, 24 Feb 2016 04:40:31 +0000 (15:40 +1100)]
glsl: add helper to generate xfb varying names
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Tue, 15 Mar 2016 06:52:06 +0000 (17:52 +1100)]
glsl: add helper for counting varyings
This will be used to get a count of the number of varying name
strings we are required to generate for use with the query api.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Mon, 15 Feb 2016 02:27:55 +0000 (13:27 +1100)]
glsl: add xfb qualifier lowering support for named blocks
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Fri, 22 Jan 2016 05:22:40 +0000 (16:22 +1100)]
glsl: add xfb qualifiers to has_layout helper
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Thu, 10 Mar 2016 00:51:48 +0000 (11:51 +1100)]
glsl: apply xfb_stride to implicit offsets for ifc block members
When we have an interface block like:
layout (xfb_buffer = 0, xfb_offset = 0) out Block {
vec4 var1;
layout (xfb_stride = 32) vec4 var2;
vec4 var3;
};
We take into account the stride of var2 when calculating the offset
for var3.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Sat, 13 Feb 2016 03:53:45 +0000 (14:53 +1100)]
glsl: add xfb_stride compile time rules
From the ARB_enhanced_layouts spec:
"The *xfb_stride* qualifier specifies how many bytes are consumed
by each captured vertex. It applies to the transform feedback
buffer for that declaration, whether it is inherited or explicitly
declared. It can be applied to variables, blocks, block members,
or just the qualifier out. If the buffer is capturing any
double-typed outputs, the stride must be a multiple of 8, otherwise
it must be a multiple of 4, or a compile-time or link-time error
results.
...
The resulting stride (implicit or explicit) must be less than or
equal to the implementation-dependent constant
gl_MaxTransformFeedbackInterleavedComponents."
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Wed, 24 Feb 2016 04:21:59 +0000 (15:21 +1100)]
glsl: add xfb_offset compile time rules
We also copy the qualifier values to the IR in this step.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Fri, 11 Mar 2016 12:00:16 +0000 (23:00 +1100)]
glsl: add xfb_buffer compile time rules
Also copies the qualifier values to GLSL IR.
From the ARB_enhanced_layouts spec:
"The *xfb_buffer* qualifier can be applied to the qualifier out,
to output variables, to output blocks, and to output block
members. Shaders in the transform feedback capturing mode have
an initial global default of
layout(xfb_buffer = 0) out;
This default can be changed by declaring a different buffer with
xfb_buffer on the interface qualifier out. This is the only way
the global default can be changed. When a variable or output block
is declared without an xfb_buffer qualifier, it inherits the global
default buffer. When a variable or output block is declared with an
xfb_buffer qualifier, it has that declared buffer. All members of a
block inherit the block's buffer. A member is allowed to declare
an xfb_buffer, but it must match the buffer inherited from its
block, or a compile-time error results.
The *xfb_buffer* qualifier follows the same conventions, behavior,
defaults, and inheritance rules as the qualifier stream, and the
examples for stream apply here as well. This includes a block's
inheritance of the current global default buffer, a block member's
inheritance of the block's buffer, and the requirement that any
*xfb_buffer* declared on a block member must match the buffer
inherited from the block.
...
It is a compile-time error to specify an *xfb_buffer* that is
greater than the implementation-dependent constant
gl_MaxTransformFeedbackBuffers."
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Wed, 24 Feb 2016 04:18:09 +0000 (15:18 +1100)]
glsl: add field to track if xfb_buffer is an explicit or implicit value
Since any of the xfb_* qualifiers trigger the shader to be in
transform feedback mode we need an extra field to track if
the xfb_buffer on interface members was set explicitly since
xfb_buffer will always have a default value.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Wed, 24 Feb 2016 05:06:00 +0000 (16:06 +1100)]
glsl: add xfb_* qualifiers to glsl_struct_field
These will be used to hold qualifier values for interface and
struct members.
Support is added to the struct/interface constructors to copy these
fields upon creation.
We also update record_compare() to ensure we don't reuse a glsl_type
with the wrong xfb_* qualifier values.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Thu, 21 Jan 2016 05:22:12 +0000 (16:22 +1100)]
glsl: add IR fields for transform feedback layout qualifiers
Adds xfb_buffer/stride fields and adds comment to offset field
which is reused for xfb_offset.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Tue, 9 Feb 2016 11:24:30 +0000 (22:24 +1100)]
glsl: add validation for out layout qualifiers
This adds validation for all qualifiers as allowed by the
table in Section 4.4 (Layout Qualifiers) of the GLSL 4.5 spec.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Mon, 18 Jan 2016 09:46:29 +0000 (20:46 +1100)]
glsl: relax stage restrictions on layout defaults for outputs
The new xfb_buffer and xfb_stride global qualifiers are allowed in
geom, tess and vertex stages.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Fri, 22 Jan 2016 01:45:10 +0000 (12:45 +1100)]
glsl: parse new transform feedback layout qualifiers
We reuse the existing offset field for holding the xfb_offset
expression but create a new flag as to avoid hitting the rules
for the offset qualifier for UBOs.
xfb_buffer qualifiers require extra processing when merging as
they can be applied to global out defaults. We just apply the
same rules as we do for the stream qualifier as the spec says:
"The *xfb_buffer* qualifier follows the same conventions,
behavior, defaults, and inheritance rules as the qualifier
stream, and the examples for stream apply here as well."
For xfb_stride we push everything into a global out field for
later processing as xfb_stride applies to the entire buffer.
We still need to have a separate field to store per variable
strides because they can still effect implicit offsets
e.g. when applied to block members with implicit offsets.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Sat, 5 Mar 2016 01:16:22 +0000 (12:16 +1100)]
glsl: move process_qualifier_constant() to ast_type.cpp
We will make use of this function being here in the following patch.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Wed, 13 Jan 2016 03:40:05 +0000 (14:40 +1100)]
glsl: add transform feedback built-in constants
These are new built-ins added by ARB_enhanced_layouts.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Fri, 11 Mar 2016 05:15:02 +0000 (16:15 +1100)]
glsl: generate named interface block names correctly
Firstly this updates the named interface lowering pass to store the
interface without the arrays removed.
Note we need to remove the arrays in the interface/varying matching
code to not regress things but in future this should be fixed
futher as it would seem we currently successfully match interface
blocks with differnt array sizes.
Since we now know if the interface was an array we can reduce the
IR flags from_named_ifc_block_array and from_named_ifc_block_nonarray
to just from_named_ifc_block.
Next rather than having a different code path for named interface
blocks in program_resource_visitor we just make use of the one used
by UBOs this allows us to now handle arrays of arrays correctly.
Finally we add a new param to the recursion function
named_ifc_member this is because we only want to process a single
member at a time. Note that this is also the glsl_struct_field
from the original ifc type before lowering rather than the type
from the lowered variable. This fixes a bug in Mesa where we would
generate the names like WithInstArray[0].g[0][0] when it should be
WithInstArray[0].g[0] for the following interface.
out WithInstArray {
float g[3];
} instArray[2];
Reviewed-by: Dave Airlie <airlied@redhat.com>
Timothy Arceri [Wed, 9 Mar 2016 05:58:29 +0000 (16:58 +1100)]
glsl: Fix segfault when lhs is error_type in TCS
It seems expected that both lhs and rhs could be of type error_type
in this code however the TCS case wasn't expecting it.
Fixes segfault in an enhanced layouts GL CTS test.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Mon, 21 Mar 2016 22:00:52 +0000 (08:00 +1000)]
docs: update softpipe status for shader_image_load_store.
Reviewed-by: Brian Paul <brianp@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Mon, 21 Mar 2016 21:59:35 +0000 (07:59 +1000)]
softpipe: add image support to softpipe (v3)
This adds support for ARB_shader_image_load_store to softpipe.
v2: add RESQ support (Ilia)
v3: constify, cleanup internals, add some comments (Brian).
Reviewed-by: Brian Paul <brianp@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Mon, 21 Mar 2016 21:58:39 +0000 (07:58 +1000)]
draw: add support for passing images to vs/gs shaders.
This just adds support for passing through images to the
tgsi execution stage.
Reviewed-by: Brian Paul <brianp@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Mon, 21 Mar 2016 21:53:48 +0000 (07:53 +1000)]
tgsi: add support for image operations to tgsi_exec. (v2.1)
This adds support for load/store/atomic operations on images
along with image tracking support.
v2: add RESQ support. (Ilia)
v2.1: constify interface (Brian)
split get_image_coord_dim (Brian)
Reviewed-by: Brian Paul <brianp@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Mon, 21 Mar 2016 21:52:26 +0000 (07:52 +1000)]
softpipe: add support for explicit early depth testing
ARB_shader_image_load_store adds support for explicit early
depth testing. However we need to make sure we don't overwrite
values using the shader written values in this case.
This fixes early depth testing in softpipe to conform with
those requirements.
Reviewed-by: Brian Paul <brianp@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Mon, 21 Mar 2016 21:50:37 +0000 (07:50 +1000)]
tgsi: introduce NonHelperMask
This is a mask of which of the current 2x2 grid are non-helper
invocations. This allows us to mask off the helper invocations
later for the image operations.
Reviewed-by: Brian Paul <brianp@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Sun, 20 Mar 2016 22:52:14 +0000 (08:52 +1000)]
tgsi_exec: handle execmask when doing indirect lookups
Reviewed-by: Brian Paul <brianp@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Dave Airlie [Sun, 20 Mar 2016 22:51:54 +0000 (08:51 +1000)]
tgsi_exec: add support for up to 3 address registers (v2)
v2: be consistent with other definitions.
Reviewed-by: Brian Paul <brianp@vmware.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Matt Turner [Mon, 22 Feb 2016 23:16:49 +0000 (15:16 -0800)]
nir: Propagate negates up multiplication chains.
total instructions in shared programs: 7112159 -> 7088092 (-0.34%)
instructions in affected programs: 1374915 -> 1350848 (-1.75%)
helped: 7392
HURT: 621
GAINED: 2
LOST: 2
Matt Turner [Wed, 25 Nov 2015 01:17:29 +0000 (17:17 -0800)]
i965: Don't inline intel_batchbuffer_require_space().
It's called by the inline intel_batchbuffer_begin() function which
itself is used in BEGIN_BATCH. So in sequence of code emitting multiple
packets, we have inlined this ~200 byte function multiple times. Making
it an out-of-line function presumably improved icache usage.
Improves performance of Gl32Batch7 by 3.39898% +/- 0.358674% (n=155) on
Ivybridge.
Reviewed-by: Abdiel Janulgue <abdiel.janulgue@linux.intel.com>
Christian König [Wed, 30 Mar 2016 13:38:29 +0000 (15:38 +0200)]
r600: ignore PIPE_BIND_LINEAR in *_is_format_supported
Similar to radeonsi linear layout should work for all not compressed
or depth/stencil formats. Fixes issues with VDPAU on r600.
Signed-off-by: Christian König <christian.koenig@amd.com>
Tested-by: Dieter Nützel <Dieter@nuetzel-hh.de>
Thomas Hindoe Paaboel Andersen [Wed, 30 Mar 2016 06:13:24 +0000 (08:13 +0200)]
st/vdpau: correct null check
The null check of result was the wrong way around. Also, move memset
and dereference of result after the null check.
Reviewed-by: Christian König <christian.koenig@amd.com>
Brian Paul [Wed, 30 Mar 2016 17:22:07 +0000 (11:22 -0600)]
docs: remove docs/COPYING which contains GPL license
There hasn't been GPL code in Mesa for a long time now.
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Samuel Pitoiset [Tue, 29 Mar 2016 21:11:07 +0000 (23:11 +0200)]
glsl: add missing types for buffer images
Type of GLSL_SAMPLER_DIM_BUF can be sampler or image.
Spotted while trying to run dEQP tests related to
ARB_shader_image_load_store.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Tested-by: Ilia Mirkin <imirkin@alum.mit.edu>