Caio Marcelo de Oliveira Filho [Fri, 6 Jul 2018 18:26:13 +0000 (11:26 -0700)]
util/set: add a basic unit test
Reviewed-by: Eric Anholt <eric@anholt.net>
Marek Olšák [Tue, 7 Nov 2017 01:02:21 +0000 (02:02 +0100)]
radeonsi: add support for Vega20
Reviewed-by: Alex Deucher <alexander.deucher@amd.com>
Eric Anholt [Wed, 11 Jul 2018 21:53:57 +0000 (14:53 -0700)]
u_blitter: Add an option to draw the triangles using an index buffer.
For V3D, the HW will interpolate slightly differently along the shared
edge of the trifan. The conformance tests manage to catch this in the
nearest_consistency_* group. To get interpolation to match, we need the
last vertex of the triangle to be shared.
I first tried implementing draw_rectangle to do triangles instead, but
that was quite a bit (147 lines) of code duplication from u_blitter, and
this seems much simpler and less likely to break as u_blitter changes.
Fixes dEQP-GLES3.functional.fbo.blit.rect.nearest_consistency_* on V3D.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Eric Anholt [Wed, 11 Jul 2018 21:58:40 +0000 (14:58 -0700)]
u_draw: Add some indices to the util_draw_elements() helpers.
These helpers have been unused, and were definitely not useful since
330d0607ed60 ("gallium: remove pipe_index_buffer and set_index_buffer")
made it so that they never had an index buffer passed in.
For an upcoming u_blitter change to use these helpers, I have just 6 bytes
of index data, so pass it as user data until a more interesting caller
comes along.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Eric Anholt [Wed, 11 Jul 2018 18:23:36 +0000 (11:23 -0700)]
vc4: Don't automatically reallocate a PERSISTENT-mapped buffer.
I had mistakenly used the COHERENT flag, which can only be set when
PERSISTENT is mapped, but isn't always.
Fixes: a2014c2eb9e0 ("vc4: Simplify the DISCARD_RANGE handling")
Eric Anholt [Wed, 11 Jul 2018 18:22:16 +0000 (11:22 -0700)]
v3d: Don't automatically reallocate a PERSISTENT-mapped buffer.
I had mistakenly used the COHERENT flag, which can only be set when
PERSISTENT is mapped, but isn't always.
Fixes piglit bufferstorage-persistent read
Eric Anholt [Wed, 11 Jul 2018 18:11:34 +0000 (11:11 -0700)]
v3d: Fix stride of 1D_ARRAY mappings.
All of our other texture arrays will be tiled, but 1D is an array of
raster mappings and we had the wrong value plugged in here. Fixes piglit
getteximage-targets 1D_ARRAY
Eric Anholt [Wed, 11 Jul 2018 18:02:11 +0000 (11:02 -0700)]
v3d: Fix MRT blending with independent blending disabled.
We were only emitting the RT blend state for RT 0 and only enabling it for
RT 0, when the gallium API for !independent_blend is for rt0's state to
apply to all of them.
Fixes piglit fbo-drawbuffers-blend-add.
Eric Anholt [Tue, 10 Jul 2018 00:51:37 +0000 (17:51 -0700)]
gallium/u_transfer_helper: Initialize the stride of MSAA maps.
We just never set the value that was returned for MSAA mappings (directly
reading back an MSAA framebuffer). Since we're handing back ss_map, it
should be ss_map's stride from our nested transfer.
Fixes piglit /home/anholt/src/piglit/bin/fbo-depthstencil -samples=4
cases.
Reviewed-by: Rob Clark <robdclark@gmail.com>
Eric Anholt [Mon, 9 Jul 2018 21:09:07 +0000 (14:09 -0700)]
gallium/u_transfer_helper: Fix MSAA mappings with nonzero x/y.
We created a temporary with box->{width,height} and then tried to map
width,height from a nonzero offset when we meant to just map the whole
temporary.
Fixes segfaults in V3D in dEQP-GLES3.functional.prerequisite.read_pixels
with --deqp-egl-config-name=rgba8888d24s8ms4 and also piglit's read-front
clear-front-first -samples=4
Reviewed-by: Rob Clark <robdclark@gmail.com>
Jason Ekstrand [Thu, 12 Jul 2018 00:06:26 +0000 (17:06 -0700)]
util/rb_tree: Fix a compiler warning
Gcc 8 warns "cast to pointer from integer of different size" in 32-bit
builds.
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Jose Maria Casanova Crespo [Wed, 11 Jul 2018 09:19:20 +0000 (11:19 +0200)]
i965/fs: unspills shoudn't use grf127 as dest since Gen8+
At
232ed8980217dd65ab0925df28156f565b94b2e5 "i965/fs: Register allocator
shoudn't use grf127 for sends dest" we didn't take into account the case
of SEND instructions that are not send_from_grf. But since Gen7+ although
the backend still uses MRFs internally for sends they are finally
assigned to a GRFs.
In the case of unspills the backend assigns directly as source its
destination because it is suppose to be available. So we always have a
source-destination overlap. If the reg_allocator assigns registers that
include the grf127 we fail the validation rule that affects Gen8+
"r127 must not be used for return address when there is a src and dest
overlap in send instruction."
So this patch activates the grf127_send_hack_node for Gen8+ and if we
have any register spilled we add interferences to the destination of
the unspill operations.
We also need to avoid that opt_bank_conflicts() optimization, that runs
after the register allocation, doesn't move things around, causing the
grf127 to be used in the condition we were avoiding.
Fixes piglit test tests/spec/arb_compute_shader/linker/bug-93840.shader_test
and some shader-db crashed because of the grf127 validation rule..
v2: make sure that opt_bank_conflicts() optimization doesn't change
the use of grf127. (Caio)
Found by Caio Marcelo de Oliveira Filho
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107193
Fixes: 232ed89802 "i965/fs: Register allocator shoudn't use grf127 for sends dest"
Cc: 18.1 <mesa-stable@lists.freedesktop.org>
Cc: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Cc: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Michel Dänzer [Thu, 12 Jul 2018 14:29:51 +0000 (16:29 +0200)]
gallium: Check pipe_screen::resource_changed before dereferencing it
It's optional, only implemented by the etnaviv driver so far.
Fixes: 501d0edeca32 "st/mesa: call resource_changed when binding a
EGLImage to a texture"
Fixes: a37cf630b4d1 "gallium: add pipe_screen::resource_changed callback
wrappers"
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
Jason Ekstrand [Wed, 11 Jul 2018 23:03:38 +0000 (16:03 -0700)]
docs/features: Add the missing KHR extensions
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Jason Ekstrand [Wed, 11 Jul 2018 23:03:37 +0000 (16:03 -0700)]
docs/features: Move the Vulkan 1.1 extensions to the 1.1 section
While we're at it, add some extensions we missed along the way like the
VK_KHR_maintenanceN extensions.
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Jason Ekstrand [Wed, 11 Jul 2018 23:03:36 +0000 (16:03 -0700)]
docs/features: Mark some Vulkan extensions as done
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Karol Herbst [Fri, 4 May 2018 14:28:03 +0000 (16:28 +0200)]
nir/spirv: handle OpConstantComposites with OpUndef members
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Thu, 22 Feb 2018 22:35:50 +0000 (23:35 +0100)]
nir/spirv: implement BuiltInGlobalSize
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Wed, 11 Jul 2018 00:42:03 +0000 (02:42 +0200)]
nir: move lowering of SYSTEM_VALUE_LOCAL_GROUP_SIZE into a function
we already have this code duplicated and we will need it for the global
group size as well
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Tue, 10 Jul 2018 23:13:46 +0000 (01:13 +0200)]
compiler: add missing entries to gl_system_value_name
also reorder to match the gl_system_value enum.
It is weird that the STATIC_ASSERT doesn't trigger though.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Rob Clark [Fri, 23 Feb 2018 20:56:03 +0000 (15:56 -0500)]
nir/spirv: print extension name in fail msg
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Rob Clark [Sat, 3 Mar 2018 20:31:13 +0000 (15:31 -0500)]
nir/spirv: Use imov where we might have 8 bit types
Otherwise nir_validate may complain about 8 bit floats, which do not exist.
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Samuel Pitoiset [Tue, 10 Jul 2018 14:13:42 +0000 (16:13 +0200)]
radv: simplify the logic in radv_set_descriptor_set()
Now that 'set' can't be NULL because the meta operations no
longer bind a NULL descriptor, the logic can be simplified
a little bit.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Samuel Pitoiset [Tue, 10 Jul 2018 14:13:41 +0000 (16:13 +0200)]
radv: remove one useless check in radv_bind_descriptor_set()
'set' shouldn't be NULL.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Samuel Pitoiset [Tue, 10 Jul 2018 14:13:40 +0000 (16:13 +0200)]
radv/meta: do not restore a NULL descriptor
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Samuel Pitoiset [Tue, 10 Jul 2018 14:13:39 +0000 (16:13 +0200)]
radv: remove unnecessary verification code around ring_offsets_idx
I don't want to waste CPU cycles for nothing.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Samuel Pitoiset [Tue, 10 Jul 2018 14:13:38 +0000 (16:13 +0200)]
radv: get rid of buffer object priorities
We mostly use the same priority for all buffer objects, so
I don't think that matter much. This should reduce CPU
overhead a little bit.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Lucas Stach [Tue, 20 Mar 2018 11:14:12 +0000 (12:14 +0100)]
st/mesa: call resource_changed when binding a EGLImage to a texture
When a EGLImage is newly bound to a texture, we need to make sure the
driver is informed that the resource might have changed. Fixes stale
texture content on Etnaviv when binding an existing EGLImage to an
existing texture object.
Signed-off-by: Lucas Stach <l.stach@pengutronix.de>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Samuel Pitoiset [Wed, 11 Jul 2018 09:55:55 +0000 (11:55 +0200)]
radv: emit a dummy ZPASS_DONE to prevent GPU hangs on GFX9
A ZPASS_DONE or PIXEL_STAT_DUMP_EVENT (of the DB occlusion
counters) must immediately precede every timestamp event to
prevent a GPU hang on GFX9.
Cc: 18.1 <mesa-stable@lists.freedesktop.org>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Samuel Pitoiset [Sun, 8 Jul 2018 15:47:52 +0000 (17:47 +0200)]
radv: add support for VK_KHR_create_renderpass2
VkCreateRenderPass2KHR() is quite similar to VkCreateRenderPass()
but refactoring the code is a bit painful.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Samuel Pitoiset [Sun, 8 Jul 2018 15:47:51 +0000 (17:47 +0200)]
radv: introduce radv_subpass_attachment data structure
Needed for VK_KHR_create_renderpass2.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Kenneth Graunke [Thu, 5 Jul 2018 09:55:57 +0000 (02:55 -0700)]
st/mesa: Only enable depth writes if the function isn't EQUAL.
If the depth function is EQUAL, then we'll only write the depth value
when it already matches what's in the buffer, which is pointless.
Skipping these writes can save bandwidth.
The state tracker can easily take care of this, so all drivers benefit.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Chad Versace [Thu, 28 Jun 2018 03:22:23 +0000 (20:22 -0700)]
anv/android: Fix type error in call to vk_errorf()
In a single call to vk_errorf() in the Android code, the arguments were
swapped. The bug has existed since day one. Chrome OS used to forgive
the warning, but it is now a compilation error.
CC: <mesa-stable@lists.freedesktop.org>
Fixes: 053d4c32 "anv: Implement VK_ANDROID_native_buffer (v9)"
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Chad Versace [Thu, 28 Jun 2018 02:40:44 +0000 (19:40 -0700)]
anv/android: Fix Autotools build for VK_ANDROID_native_buffer
Changes to vk.xml and anv_entrypoints_gen.py broke the Autotools build
on Android. The changes undef'd the VK_ANDROID_native_buffer entrypoints
in anv_entrypoints.h.
Fix it with CPPFLAGS += -DVK_USE_PLATFORM_ANDROID_KHR.
CC: <mesa-stable@lists.freedesktop.org>
See-Also:
63525ba7 "android: enable VK_ANDROID_native_buffer"
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Samuel Pitoiset [Mon, 9 Jul 2018 16:02:58 +0000 (18:02 +0200)]
radv: make sure to wait for CP DMA when needed
This might fix some synchronization issues. I don't know if
that will affect performance but it's required for correctness.
CC: <mesa-stable@lists.freedesktop.org>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Rafael Antognolli [Tue, 3 Jul 2018 18:38:39 +0000 (11:38 -0700)]
intel/tools/dump_gpu: Add option to print ppgtt mappings.
Using -vv will increase the verbosity, by printing the ppgtt mappings as
they get written into the aub file.
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Neil Roberts [Wed, 9 May 2018 13:14:36 +0000 (15:14 +0200)]
spirv: Fix InterpolateAt* instructions for vecs with dynamic index
If the glsl is something like this:
in vec4 some_input;
interpolateAtCentroid(some_input[idx])
then it now gets generated as if it were:
interpolateAtCentroid(some_input)[idx]
This is necessary because the index will get generated as a series of
nir_bcsel instructions so it would no longer be an input variable. It
is similar to what is done for GLSL in
ca63a5ed3e9efb2bd645b42.
Although I can’t find anything explicit in the Vulkan specs to say
this should be allowed, the SPIR-V spec just says “the operand
interpolant must be a pointer to the Input Storage Class”, which I
guess doesn’t rule out any type of pointer to an input.
This was found using the spec/glsl-4.40/execution/fs-interpolateAt*
Piglit tests with the ARB_gl_spirv branch.
Signed-off-by: Neil Roberts <nroberts@igalia.com>
Signed-off-by: Alejandro Piñeiro <apinheiro@igalia.com>
v2: update after nir_deref_instr land on master. Implemented by
Alejandro Piñeiro. Special thanks to Jason Ekstrand for guidance
at the new nir_deref_instr world.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Francisco Jerez [Wed, 24 Jan 2018 03:35:23 +0000 (19:35 -0800)]
intel/ir: Uncomment definition of several unused hardware opcodes.
There are a number of opcode_desc table entries for many of these
unused opcodes. A symbolic opcode enum will be required in a future
commit in order to keep them in the opcode description tables. The
alternative would be to remove the unused opcodes from the opcode
description tables.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Wed, 27 Dec 2017 03:08:10 +0000 (19:08 -0800)]
intel/fs: Initialize mlen for gen7 varying pull constant load messages.
This makes the message length available at the IR level, which should
save some guesswork in a future commit.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Sun, 3 Jun 2018 20:20:45 +0000 (13:20 -0700)]
intel/eu: Assert that the instruction is send-like in brw_set_desc_ex().
Constructing a descriptor in-place as part of the immediate of an ALU
instruction is no longer supported.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Sat, 2 Jun 2018 22:08:18 +0000 (15:08 -0700)]
intel/eu: Get rid of the return value of brw_send_indirect_message().
The return value is not used anymore. This allows simplifying the
code slightly, and in addition it should frustrate anybody's attempts
to continue using the obsolete piecemeal approach to construct a
message descriptor in combination with brw_send_indirect_message().
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Sun, 3 Jun 2018 10:30:50 +0000 (03:30 -0700)]
intel/eu: Get rid of the return value of brw_send_indirect_surface_message().
All users of brw_send_indirect_surface_message() should be providing a
full descriptor immediate up front by now, this isn't necessary
anymore.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Thu, 7 Jun 2018 22:27:06 +0000 (15:27 -0700)]
intel/eu: Use descriptor constructors for dataport typed surface messages.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Thu, 7 Jun 2018 22:24:48 +0000 (15:24 -0700)]
intel/eu: Use descriptor constructors for dataport scattered byte surface messages.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Thu, 7 Jun 2018 22:22:58 +0000 (15:22 -0700)]
intel/eu: Use descriptor constructors for dataport untyped surface messages.
v2: Use SET_BITS macro instead of left shift (Ken).
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Thu, 7 Jun 2018 22:19:49 +0000 (15:19 -0700)]
intel/eu: Provide single descriptor argument to brw_send_indirect_surface_message().
Instead of the current message_len, response_len and header_present
arguments.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Mon, 9 Jul 2018 23:16:16 +0000 (16:16 -0700)]
intel/eu: Use descriptor constructors for pixel interpolator messages.
v2: Use SET_BITS macro instead of left shift (Ken).
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Mon, 9 Jul 2018 23:12:59 +0000 (16:12 -0700)]
intel/eu: Use descriptor constructors for dataport write messages.
v2: Use SET_BITS macro instead of left shift (Ken).
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Thu, 7 Jun 2018 17:50:20 +0000 (10:50 -0700)]
intel/eu: Use descriptor constructors for dataport read messages.
v2: Use SET_BITS macro instead of left shift (Ken).
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Sat, 2 Jun 2018 22:15:15 +0000 (15:15 -0700)]
intel/eu: Use descriptor constructors for sampler messages.
v2: Use SET_BITS macro instead of left shift (Ken).
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Sat, 2 Jun 2018 22:07:31 +0000 (15:07 -0700)]
intel/eu: Provide desc immediate argument up front to brw_send_indirect_message().
The current approach of returning a setup instruction where additional
descriptor fields can be specified is still supported in order to keep
things working, but it will be removed later in this series.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Sat, 2 Jun 2018 21:59:08 +0000 (14:59 -0700)]
TRIVIAL: intel/eu: Use a local devinfo variable in brw_shader_time_add().
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Mon, 11 Jun 2018 17:49:39 +0000 (10:49 -0700)]
intel/eu: Use brw_set_desc() along with a helper to set common descriptor controls.
This replaces brw_set_message_descriptor() with the composition of
brw_set_desc() and a new inline helper function that packs the common
message descriptor controls into an integer. The goal is to represent
all message descriptors as a 32-bit integer which is written at once
into the instruction, which is more flexible (SENDS anyone?), robust
(see
d2eecf0b0b24d203d0f171807681dffd830d54de fixing an issue
ultimately caused by some bits of the extended message descriptor
being left undefined) and future-proof than the current approach of
specifying the individual descriptor fields directly into the
instruction.
This approach also seems more self-documenting, since it will allow
removing calls to functions with way too many arguments like
brw_set_*_message() and brw_send_indirect_message(), and instead
provide a single descriptor argument constructed from an appropriate
combination of brw_*_desc() helpers.
Note that because brw_set_message_descriptor() was (conditionally?)
overriding fields of the instruction which strictly speaking weren't
part of the message descriptor, this involves calling
brw_inst_set_sfid() and brw_inst_set_eot() in some cases in addition
to brw_set_desc().
v2: Use SET_BITS macro instead of left shift (Ken).
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Mon, 25 Jun 2018 19:06:50 +0000 (12:06 -0700)]
intel/eu: Define SET_BITS helper more easily reusable than SET_FIELD.
Allows to specify a bitfield based on its upper and lower bounds
instead of a symbolic field definition, kind of what the current
GET_BITS macro is to GET_FIELD.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Sat, 2 Jun 2018 20:48:42 +0000 (13:48 -0700)]
intel/eu: Define helper to specify the descriptor immediates of a SEND instruction.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Francisco Jerez [Sat, 2 Jun 2018 01:21:37 +0000 (18:21 -0700)]
intel/eu: Add brw_inst.h helpers for the SEND(C) descriptor and extended descriptor.
This introduces helpers that can be used to specify or extract the
whole descriptor of a SEND message instruction at once. Because the
the instruction encoding of these is rather awkward on some
generations using the generic brw_inst.h macros doesn't seem like an
option.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Jordan Justen [Thu, 1 Mar 2018 02:33:58 +0000 (18:33 -0800)]
i965: Support saving the gen program with glGetProgramBinary
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jordan Justen [Thu, 1 Mar 2018 05:43:22 +0000 (21:43 -0800)]
i965: Add flag_state param to brw_search_cache
This allows brw_search_cache to be used to find programs without
causing extra state to be emitted in the case where the program isn't
being made active. (For example, to find the program to save out with
the ARB_get_program_binary interface.)
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jordan Justen [Thu, 1 Mar 2018 02:29:54 +0000 (18:29 -0800)]
mesa: Add gl_shader_program param to ProgramBinarySerializeDriverBlob
This might be required because some stages might generate different
programs depending on the other stages in the program. For example,
the i965 driver's tessellation control stage depends on the
tessellation evaluation shader.
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jordan Justen [Thu, 1 Mar 2018 01:58:02 +0000 (17:58 -0800)]
i965: Add brw_populate_default_key
We will need to populate the default key for ARB_get_program_binary to
allow us to retrieve the default gen program to store in the program
binary.
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jordan Justen [Thu, 1 Mar 2018 01:14:50 +0000 (17:14 -0800)]
i965: Replace brw_setup_tex_for_precompile brw with devinfo
Trying to make sure the setup of the default program key is not
dependent on the GL state.
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jordan Justen [Mon, 9 Apr 2018 08:39:18 +0000 (01:39 -0700)]
i965: Regenerate blob without gen program for shader cache
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jordan Justen [Mon, 9 Apr 2018 08:07:03 +0000 (01:07 -0700)]
compiler/blob: Add blob_skip_bytes
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jordan Justen [Thu, 1 Mar 2018 00:20:51 +0000 (16:20 -0800)]
i965: Add support for driver cache blob containing the gen program
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jordan Justen [Tue, 6 Mar 2018 05:18:27 +0000 (21:18 -0800)]
i965: Use brw_prog_key_set_id in disk cache load/store code
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jordan Justen [Tue, 6 Mar 2018 01:17:23 +0000 (17:17 -0800)]
i965: Add brw_prog_key_set_id helper to set the program id on any stage
For saving programs (shader cache; get program binary) it is useful to
set the id to 0, with the stage being a parameter.
For restoring programs it is useful to set the id to the id allocated
to the program at creation time.
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jordan Justen [Thu, 1 Mar 2018 06:01:44 +0000 (22:01 -0800)]
i965: Add brw_stage_cache_id to map gl stages to brw cache_ids
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jordan Justen [Wed, 28 Feb 2018 23:55:47 +0000 (15:55 -0800)]
i965: Add brw_(read|write)_blob_program_data functions
We will want to use these for both the disk shader cache, and for the
ARB_get_program_binary.
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jordan Justen [Wed, 28 Feb 2018 22:41:02 +0000 (14:41 -0800)]
i965: Add brw_program_deserialize_driver_blob
brw_program_deserialize_driver_blob will be a more generic form of
brw_program_deserialize_nir. In addition to nir, it will also be able
to extract gen binaries and upload them to the program cache.
In this commit, it continues to only support nir.
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jordan Justen [Wed, 28 Feb 2018 09:39:27 +0000 (01:39 -0800)]
i965: Move brw_program_*serialize_nir to brw_program_binary.c
This will allow get_program_binary to add the gen program into its
serialization in addition to just the nir program.
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jordan Justen [Thu, 19 Apr 2018 22:39:40 +0000 (15:39 -0700)]
mesa: Always call ProgramBinarySerializeDriverBlob
The driver may prefer to have a different blob for
ARB_get_program_binary compared to the version saved out for the disk
shader cache.
Since they both use the driver_cache_blob field, we need to always
give the driver the opportunity to fill in the driver_cache_blob when
saving the program binary.
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jordan Justen [Mon, 9 Apr 2018 06:16:19 +0000 (23:16 -0700)]
i965: Use ShaderCacheSerializeDriverBlob driver function
This function is called just before the gl_program::driver_cache_blob
is saved out as part of the gl_program serialization.
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jordan Justen [Thu, 19 Apr 2018 23:20:53 +0000 (16:20 -0700)]
st/mesa: Use ShaderCacheSerializeDriverBlob driver function
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jordan Justen [Thu, 19 Apr 2018 23:14:28 +0000 (16:14 -0700)]
st/mesa: Skip serializing driver_cache_blob if it exists
Previously the mesa core code would not call to serialize the
driver_cache_blob if it existed. We will update it to always call to
serialize the driver_cache_blob meaning we should avoid re-serializing
it under mesa/state_tracker.
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jordan Justen [Mon, 9 Apr 2018 00:56:34 +0000 (17:56 -0700)]
mesa: Add disk shader cache driver blob callback
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Iago Toral Quiroga [Thu, 21 Jun 2018 07:45:19 +0000 (09:45 +0200)]
intel/compiler: emit actual barriers for working-group level barriers
Until now we have assumed that we could skip emitting these barriers
in the general case based on empirical testing and a few assumptions
detailed in a comment in the driver code, however, recent CTS tests
have showed that we actually need them to produce correct behavior.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Dave Airlie [Tue, 10 Jul 2018 00:15:34 +0000 (10:15 +1000)]
radv: add some cxxflags for new c++ file
Looks like I broke intel CI compiles.
Fixes: 6f3aee40f9 (radv: using tls to store llvm related info and speed up compiles (v10))
Tested-by: Clayton Craft <clayton.a.craft@intel.com>
Jason Ekstrand [Fri, 15 Jun 2018 22:47:41 +0000 (15:47 -0700)]
anv,radv: Add support for VK_KHR_get_display_properties2
Reviewed-by: Keith Packard <keithp@keithp.com>
Jason Ekstrand [Mon, 9 Jul 2018 23:00:17 +0000 (16:00 -0700)]
intel/aubinator_error_decode: Allow for more sections
Error states coming from actual Vulkan applications tend to have fairly
long command buffers and lots of chained batches. 30 total BOs isn't
nearly enough. This commit bumps it to 256, makes some things use the
actual number of sections instead of the #define, and adds asserts if we
ever go over 256 sections.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Jason Ekstrand [Mon, 9 Jul 2018 22:58:33 +0000 (15:58 -0700)]
intel/batch_decoder: Recurse for all 2nd level batches
Our attempt to restart the loop with the second level batch worked at
one point but got broken at some point. It was too fragile anyway and
we're not likely to have enough secondaries to actually overflow the
stack so we may as well recurse in both cases.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Dave Airlie [Fri, 8 Jun 2018 06:19:49 +0000 (16:19 +1000)]
virgl/vtest: add support to vtest for new cap getting.
The vtest protocol is pretty simple but also pretty dumb, and
the v1 caps query was fixed size, with no nice way to expand it,
however the server also ignores any command it doesn't understand.
So we can query v2 caps by sending a v2 followed by a v1, if the
v2 is ignored we know it's an old vtest server, and the we get
a v2 answer then we can just read the v1 answer and discard it.
Acked-by: Jakob Bornecrantz <jakob@collabora.com> (sounds good)
Anuj Phogat [Thu, 31 May 2018 23:03:44 +0000 (16:03 -0700)]
i965/icl: Don't set float blend optimization bit in CACHE_MODE_SS
CACHE_MODE_SS is not listed in gfxspecs table for user mode
non-privileged registers. So, making any changes from Mesa
will do nothing. Kernel is already setting this bit in
CACHE_MODE_SS register which is saved/restored to/from
the HW context image.
Signed-off-by: Anuj Phogat <anuj.phogat@gmail.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Anuj Phogat [Thu, 31 May 2018 22:41:53 +0000 (15:41 -0700)]
anv/icl: Don't set float blend optimization bit in CACHE_MODE_SS
CACHE_MODE_SS is not listed in gfxspecs table for user mode
non-privileged registers. So, making any changes from Mesa
will do nothing. Kernel is already setting this bit in
CACHE_MODE_SS register which is saved/restored to/from
the HW context image.
Signed-off-by: Anuj Phogat <anuj.phogat@gmail.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Jason Ekstrand [Mon, 2 Jul 2018 19:57:44 +0000 (12:57 -0700)]
anv: Implement VK_EXT_vertex_attribute_divisor
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Jason Ekstrand [Mon, 2 Jul 2018 19:49:06 +0000 (12:49 -0700)]
anv/pipeline: Add a per-VB instance divisor
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Jason Ekstrand [Mon, 2 Jul 2018 19:44:49 +0000 (12:44 -0700)]
anv/pipeline: Use a per-VB struct instead of separate arrays
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Jose Maria Casanova Crespo [Mon, 9 Jul 2018 00:01:32 +0000 (02:01 +0200)]
anv: Enable SPV_KHR_8bit_storage and VK_KHR_8bit_storage
Enables SPV_KHR_8bit_storage and VK_KHR_8bit_storage on gen 8+
using the VK_KHR_get_physical_device_properties2 functionality
to expose if the extension is supported or not.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Jose Maria Casanova Crespo [Mon, 9 Jul 2018 00:01:22 +0000 (02:01 +0200)]
spirv/nir: Add support for SPV_KHR_8bit_storage
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Jose Maria Casanova Crespo [Mon, 9 Jul 2018 00:01:14 +0000 (02:01 +0200)]
spirv: Include headers and grammar for SPV_KHR_8bit_storage
Updates headers and grammar to
ff684ffc6a35d2a58f0f63108877d0064ea33feb
Acked-by: Jason Ekstrand <jason@jlekstrand.net>
Jose Maria Casanova Crespo [Mon, 9 Jul 2018 00:01:01 +0000 (02:01 +0200)]
i965/fs: Enable store_ssbo for 8-bit types.
v2: Update comment according to this patch. (Jason Ekstrand)
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Jose Maria Casanova Crespo [Mon, 9 Jul 2018 00:00:34 +0000 (02:00 +0200)]
intel/compiler: relax brw_eu_validate for byte raw movs
When the destination is a BYTE type allow raw movs
even if the stride is not exact multiple of destination
type and exec type, execution type is Word and its size is 2.
This restriction was only allowing stride==2 destinations
for 8-bit types.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Jose Maria Casanova Crespo [Mon, 9 Jul 2018 00:00:23 +0000 (02:00 +0200)]
i965/fs: Enable conversions to 8-bit integers
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Jose Maria Casanova Crespo [Mon, 9 Jul 2018 00:00:06 +0000 (02:00 +0200)]
i965: Support for 8-bit base types in helper functions
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Jose Maria Casanova Crespo [Wed, 18 Apr 2018 23:15:23 +0000 (01:15 +0200)]
i965/fs: Register allocator shoudn't use grf127 for sends dest
Since Gen8+ Intel PRM states that "r127 must not be used for return
address when there is a src and dest overlap in send instruction."
This patch implements this restriction creating new grf127_send_hack_node
at the register allocator. This node has a fixed assignation to grf127.
For vgrf that are used as destination of send messages we create node
interfereces with the grf127_send_hack_node. So the register allocator
will never assign to these vgrf a register that involves grf127.
If dispatch_width > 8 we don't create these interferences to the because
all instructions have node interferences between sources and destination.
That is enough to avoid the r127 restriction.
This fixes CTS tests that raised this issue as they were executed as SIMD8:
dEQP-VK.spirv_assembly.instruction.graphics.8bit_storage.8struct_to_32struct.storage_buffer_*int_geom
Shader-db results on Skylake:
total instructions in shared programs:
7686798 ->
7686797 (<.01%)
instructions in affected programs: 301 -> 300 (-0.33%)
helped: 1
HURT: 0
total cycles in shared programs:
337092322 ->
337091919 (<.01%)
cycles in affected programs:
22420415 ->
22420012 (<.01%)
helped: 712
HURT: 588
Shader-db results on Broadwell:
total instructions in shared programs:
7658574 ->
7658625 (<.01%)
instructions in affected programs: 19610 -> 19661 (0.26%)
helped: 3
HURT: 4
total cycles in shared programs:
340694553 ->
340676378 (<.01%)
cycles in affected programs:
24724915 ->
24706740 (-0.07%)
helped: 998
HURT: 916
total spills in shared programs: 4300 -> 4311 (0.26%)
spills in affected programs: 333 -> 344 (3.30%)
helped: 1
HURT: 3
total fills in shared programs: 5370 -> 5378 (0.15%)
fills in affected programs: 274 -> 282 (2.92%)
helped: 1
HURT: 3
v2: Avoid duplicating register classes without grf127. Let's use a node
with a fixed assignation to grf127 and create interferences to send
message vgrf destinations. (Eric Anholt)
v3: Update reference to CTS VK_KHR_8bit_storage failing tests.
(Jose Maria Casanova)
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Cc: 18.1 <mesa-stable@lists.freedesktop.org>
Jose Maria Casanova Crespo [Mon, 26 Mar 2018 12:59:46 +0000 (14:59 +0200)]
intel/compiler: grf127 can not be dest when src and dest overlap in send
Implement at brw_eu_validate the restriction from Intel Broadwell PRM,
vol 07, section "Instruction Set Reference", subsection "EUISA
Instructions", Send Message (page 990):
"r127 must not be used for return address when there is a src and
dest overlap in send instruction."
v2: Style fixes (Matt Turner)
Reviewed-by: Matt Turner <mattst88@gmail.com>
Cc: 18.1 <mesa-stable@lists.freedesktop.org>
Dave Airlie [Wed, 27 Jun 2018 01:34:25 +0000 (11:34 +1000)]
radv: using tls to store llvm related info and speed up compiles (v10)
This uses the common compiler passes abstraction to help radv
avoid fixed cost compiler overheads. This uses a linked list per
thread stored in thread local storage, with an entry in the list
for each target machine.
This should remove all the fixed overheads setup costs of creating
the pass manager each time.
This takes a demo app time to compile the radv meta shaders on nocache
and exit from 1.7s to 1s. It also has been reported to take the startup
time of uncached shaders on RoTR from 12m24s to 11m35s (Alex)
v2: fix llvm6 build, inline emit function, handle multiple targets
in one thread
v3: rebase and port onto new structure
v4: rename some vars (Bas)
v5: drag all code into radv for now, we can refactor it out later
for radeonsi if we make it shareable
v6: use a bit more C++ in the wrapper
v7: logic bugs fixed so it actually runs again.
v8: rebase on top of radeonsi changes.
v9: drop some C++ headers, cleanup list entry
v10: use pop_back (didn't have enough caffeine)
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Adam Jackson [Mon, 9 Jul 2018 16:51:37 +0000 (12:51 -0400)]
swrast: Fix eglMakeCurrent(dpy, NULL, NULL, ctx) (v2)
Fixes 14 piglits, mostly in egl_khr_create_context.
v2: Also short-circuit the same-context-no-drawables case (Eric Anholt)
Fixes: https://github.com/anholt/libepoxy/issues/177
Reviewed-by: Eric Anholt <eric@anholt.net>
Signed-off-by: Adam Jackson <ajax@redhat.com>
Lionel Landwerlin [Fri, 6 Jul 2018 09:58:47 +0000 (10:58 +0100)]
intel: tools: dump_gpu: fix ppgtt mapping
We were not properly writing page tables when the virtual address
range spans multiple subtrees of the tables.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Rafael Antognolli <rafael.antognolli@intel.com>
Eric Anholt [Fri, 6 Jul 2018 22:48:46 +0000 (15:48 -0700)]
v3d: Implement noperspective varyings on V3D 4.x.
Fixes a bunch of piglit interpolation tests, and reduces my concern about
some MSAA blit shaders with noperspective varyings.
Eric Anholt [Fri, 6 Jul 2018 22:41:56 +0000 (15:41 -0700)]
v3d: Refactor flat shade/centroid flag emission.
The logic was duplicated in a pretty gross way, when what we really need
is just a helper function for stuffing the values in the packet. This
will make implementing noperspective easier.