Karol Herbst [Sun, 4 Mar 2018 18:06:24 +0000 (19:06 +0100)]
glsl: add packed for struct types
We need this for OpenCL kernels because we have to apply C rules for alignment
and padding inside structs and for this we also have to know if a struct is
packed or not.
v2: fix for kernel params
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Alyssa Rosenzweig [Fri, 15 Mar 2019 23:25:55 +0000 (23:25 +0000)]
panfrost: Rewrite varying assembly
There are two stages to varying assembly in the command stream: creating
the varying buffers in the command stream, and creating the varying meta
descriptors (also in the command stream) linked to the aforementioned
buffers. The previous code for this was ad hoc and brittle, making some
invalid assumptions causing unmaintainable workarounds to pile up across
the driver (both compiler and command stream side).
This patch completely rewrites the varying assembly code. There's a
trivial performance penalty (we now memcpy the varying meta to the
command stream on draw, rather than on compile). That said, the
improvement in flexibility and clarity is well-worth it.
The motivator for these changes was support for gl_PointCoord (and
eventually point sprites for legacy GL), which was impossible to
implement with the old varying assembly code. With the new refactor,
it's super easy; support for gl_PointCoord is included with this patch.
All in all, I'm quite happy with how this turned out.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Alyssa Rosenzweig [Fri, 15 Mar 2019 03:34:25 +0000 (03:34 +0000)]
panfrost: Replay more varying buffers
This is required for gl_PointCoord to show up on decodes.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Alyssa Rosenzweig [Fri, 15 Mar 2019 03:21:27 +0000 (03:21 +0000)]
panfrost/decode: Respect primitive size pointers
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Alyssa Rosenzweig [Fri, 15 Mar 2019 02:37:59 +0000 (02:37 +0000)]
panfrost: Disable PIPE_CAP_TGSI_TEXCOORD
I don't know why this was on to begin with...?
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Alyssa Rosenzweig [Fri, 15 Mar 2019 02:13:34 +0000 (02:13 +0000)]
panfrost: Fix primconvert check
In addition to fixing actual primconvert bugs, this prevents an infinite
loop when trying to draw POINTS.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Alyssa Rosenzweig [Fri, 15 Mar 2019 02:07:55 +0000 (02:07 +0000)]
panfrost: Workaround buffer overrun with mip level
Mipmaps are still broken, but at least this way we don't crash on some
apps using mipmaps.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Bas Nieuwenhuizen [Mon, 18 Mar 2019 21:20:40 +0000 (22:20 +0100)]
radv: Use correct image view comparison for fast clears.
The if is actually returning true on success, enabling fast clears, so we
need to have the test succeed when the iview dimensions are right.
Fixes: d5400a5ec2a "radv: provide a helper for comparing an image extents."
Reviewed-by: Dave Airlie <airlied@redhat.com>
Jason Ekstrand [Wed, 12 Dec 2018 16:54:26 +0000 (10:54 -0600)]
anv,radv: Implement VK_KHR_surface_capability_protected
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Eric Engestrom <eric@engestrom.ch>
Danylo Piliaiev [Mon, 18 Mar 2019 10:53:30 +0000 (12:53 +0200)]
anv: Treat zero size XFB buffer as disabled
Vulkan spec doesn't explicitly forbid zero size transform
feedback buffers.
Having zero size xfb caused SurfaceSize overflow and
triggered assert in debug build.
The only way to have zero size SO_BUFFER is to disable
SO_BUFFER as stated in hardware spec.
From SKL PRM, Vol 2a, "3DSTATE_SO_BUFFER":
"If set, stream output to SO Buffer is enabled,
if 3DSTATE_STREAMOUT::SO Function ENABLE is also enabled.
If clear, the SO Buffer is considered "not bound" and effectively
treated as a zero- length buffer for the purposes of SO output and
overflow detection. If an enabled stream's Stream to Buffer Selects
includes this buffer it is by definition an overflow condition.
That stream will cause no writes to occur,
and only SO_PRIM_STORAGE_NEEDED[<stream>] will increment."
Fixes: 36ee2fd61c8 "anv: Implement the basic form of VK_EXT_transform_feedback"
Signed-off-by: Danylo Piliaiev <danylo.piliaiev@globallogic.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Emil Velikov [Mon, 18 Mar 2019 16:02:27 +0000 (16:02 +0000)]
docs: update calendar, add news item and link release notes for 18.3.5
Signed-off-by: Emil Velikov <emil.velikov@collabora.com>
Emil Velikov [Mon, 18 Mar 2019 15:57:14 +0000 (15:57 +0000)]
docs: add sha256 checksums for 18.3.5
Signed-off-by: Emil Velikov <emil.velikov@collabora.com>
(cherry picked from commit
ec770b43b974cc86ce4bf996aa0616ceafa4e69c)
Emil Velikov [Mon, 18 Mar 2019 15:45:53 +0000 (15:45 +0000)]
docs: add release notes for 18.3.5
Signed-off-by: Emil Velikov <emil.velikov@collabora.com>
(cherry picked from commit
022708cb40a997e796f95d011a0e6c64a7333fe0)
Bas Nieuwenhuizen [Sat, 17 Nov 2018 17:39:24 +0000 (18:39 +0100)]
radv: Implement VK_EXT_host_query_reset.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Eric Engestrom <eric@engestrom.ch>
Jason Ekstrand [Tue, 5 Mar 2019 02:01:44 +0000 (20:01 -0600)]
anv: Implement VK_EXT_host_query_reset
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Bas Nieuwenhuizen [Sun, 17 Mar 2019 17:21:28 +0000 (18:21 +0100)]
vulkan: Update the XML and headers to 1.1.104
Acked-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Eric Engestrom <eric@engestrom.ch>
Acked-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Bas Nieuwenhuizen [Sun, 17 Mar 2019 19:26:07 +0000 (20:26 +0100)]
vulkan/util: Handle enums that are in platform-specific headers.
VkFullScreenExclusiveEXT comes from the win32 header. Mostly took
the logic from the entrypoint scripts:
1) If there is an ext that has it in the requires and has a platform,
take the guard for that platform.
2) Otherwise assume it is from the core headers.
Acked-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Eric Engestrom <eric@engestrom.ch>
Lionel Landwerlin [Sun, 17 Mar 2019 16:57:48 +0000 (16:57 +0000)]
vulkan: factor out wsi dependencies
In commit
530927d3f6a303d9 ("vulkan/util: generate instance/device
dispatch tables") we started generating instance dispatch tables some
of them (like wayland) require external headers.
This commit moves the dependencies up one level so that they apply the
whole vulkan directory. We use them for both the util & overlay layer.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: 530927d3f6a303 ("vulkan/util: generate instance/device dispatch tables")
Reviewed-by: Eric Engestrom <eric@engestrom.ch>
Tapani Pälli [Tue, 5 Mar 2019 07:24:16 +0000 (09:24 +0200)]
android: Build fixes for OMR1
Some of the header file locations are changed between Android
versions (when VNDK is used), patch makes sure we get all the
required headers.
v2: cleanups, put SDK version checks in all places (Tapani)
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Signed-off-by: Chen Lin Z <lin.z.chen@intel.com>
Tested-by: Clayton Craft <clayton.a.craft@intel.com>
Acked-by: Eric Engestrom <eric.engestrom@intel.com>
Bas Nieuwenhuizen [Sun, 17 Mar 2019 02:18:29 +0000 (03:18 +0100)]
radv: Allow fast clears with concurrent queue mask for some layouts.
For VK_IMAGE_LAYOUT_COLOR_ATTACHMENT_OPTIMAL and
VK_IMAGE_LAYOUT_DEPTH_STENCIL_ATTACHMENT_OPTIMAL we do not care about
the queue mask because
1) using these is only allowed on the gfx queue
2) transitions for these are only allowed on the gfx queue.
This enables some fast clears for Doom that uses
VK_SHARING_MODE_CONCURRENT.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Kenneth Graunke [Mon, 18 Mar 2019 07:51:18 +0000 (00:51 -0700)]
iris: Slightly better bounds on buffer sizes
Kenneth Graunke [Mon, 18 Mar 2019 07:18:32 +0000 (00:18 -0700)]
iris: Don't flush the batch for unsynchronized mappings
I messed this up when adding the GPU copy path.
Tapani Pälli [Fri, 15 Mar 2019 10:32:09 +0000 (12:32 +0200)]
isl: fix automake build when sse41 is not supported
Fixes: 864cc419eb0a41882762 "intel/isl: move tiled_memcpy static libs from i965 to isl"
Cc: mesa-stable@lists.freedesktop.org
Reported-by: Milav Soni <milav.soni@teqdiligent.com>
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Brian Paul [Fri, 8 Mar 2019 22:36:04 +0000 (15:36 -0700)]
gallium/util: remove pipe_sampler_view_release()
It's no longer used.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Reviewed-by: Neha Bhende <bhenden@vmware.com>
Reviewed-by: Mathias Fröhlich <Mathias.Froehlich@web.de>
Reviewed-By: Jose Fonseca <jfonseca@vmware.com>
Brian Paul [Fri, 8 Mar 2019 22:20:16 +0000 (15:20 -0700)]
i915g: remove calls to pipe_sampler_view_release()
As with previous patches for svga, llvmpipe, swr drivers.
Compile tested only.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Reviewed-by: Neha Bhende <bhenden@vmware.com>
Reviewed-by: Mathias Fröhlich <Mathias.Froehlich@web.de>
Reviewed-By: Jose Fonseca <jfonseca@vmware.com>
Brian Paul [Fri, 8 Mar 2019 22:19:02 +0000 (15:19 -0700)]
swr: remove call to pipe_sampler_view_release()
As with svga, llvmpipe drivers in previous patches.
Compile tested only.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Reviewed-by: Neha Bhende <bhenden@vmware.com>
Reviewed-by: Mathias Fröhlich <Mathias.Froehlich@web.de>
Reviewed-By: Jose Fonseca <jfonseca@vmware.com>
Brian Paul [Fri, 8 Mar 2019 21:08:13 +0000 (14:08 -0700)]
llvmpipe: stop using pipe_sampler_view_release()
This was used to avoid freeing a sampler view which was created by a
context that was already deleted. But the state tracker does not
allow that.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Reviewed-by: Neha Bhende <bhenden@vmware.com>
Reviewed-by: Mathias Fröhlich <Mathias.Froehlich@web.de>
Reviewed-By: Jose Fonseca <jfonseca@vmware.com>
Brian Paul [Fri, 8 Mar 2019 21:02:53 +0000 (14:02 -0700)]
svga: stop using pipe_sampler_view_release()
This function was used in the past to avoid deleting a sampler view
for a context that no longer exists. But the Mesa state tracker
ensures that cannot happen. Use the standard refcounting function
instead.
Also, remove the code which checked for context mis-matches in
svga_sampler_view_destroy(). It's no longer needed since implementing
the zombie sampler view code in the state tracker.
Testing Done: google chrome, variety of GL demos/games
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Reviewed-by: Neha Bhende <bhenden@vmware.com>
Reviewed-by: Mathias Fröhlich <Mathias.Froehlich@web.de>
Reviewed-By: Jose Fonseca <jfonseca@vmware.com>
Brian Paul [Fri, 8 Mar 2019 20:39:05 +0000 (13:39 -0700)]
st/mesa: stop using pipe_sampler_view_release()
In all instances here we can replace pipe_sampler_view_release(pipe,
view) with pipe_sampler_view_reference(view, NULL) because the views
in question are private to the state tracker context. So there's no
danger of freeing a sampler view with the wrong context.
Testing done: google chrome, misc GL demos, games
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Reviewed-by: Neha Bhende <bhenden@vmware.com>
Reviewed-by: Mathias Fröhlich <Mathias.Froehlich@web.de>
Reviewed-By: Jose Fonseca <jfonseca@vmware.com>
Brian Paul [Tue, 12 Mar 2019 22:01:56 +0000 (16:01 -0600)]
st/mesa: implement "zombie" shaders list
As with the preceding patch for sampler views, this patch does
basically the same thing but for shaders. However, reference counting
isn't needed here (instead of calling cso_delete_XXX_shader() we call
st_save_zombie_shader().
The Redway3D Watch is one app/demo that needs this change. Otherwise,
the vmwgfx driver generates an error about trying to destroy a shader
ID that doesn't exist in the context.
Note that if PIPE_CAP_SHAREABLE_SHADERS = TRUE, then we can use/delete
any shader with any context and this mechanism is not used.
Tested with: google-chrome, google earth, Redway3D Watch/Turbine demos
and a few Linux games.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Reviewed-by: Neha Bhende <bhenden@vmware.com>
Reviewed-by: Mathias Fröhlich <Mathias.Froehlich@web.de>
Reviewed-By: Jose Fonseca <jfonseca@vmware.com>
Brian Paul [Tue, 12 Mar 2019 15:13:00 +0000 (09:13 -0600)]
st/mesa: implement "zombie" sampler views (v2)
When st_texture_release_all_sampler_views() is called the texture may
have sampler views belonging to several contexts. If we unreference a
sampler view and its refcount hits zero, we need to be sure to destroy
the sampler view with the same context which created it.
This was not the case with the previous code which used
pipe_sampler_view_release(). That function could end up freeing a
sampler view with a context different than the one which created it.
In the case of the VMware svga driver, we detected this but leaked the
sampler view. This led to a crash with google-chrome when the kernel
module had too many sampler views. VMware bug
2274734.
Alternately, if we try to delete a sampler view with the correct
context, we may be "reaching into" a context which is active on
another thread. That's not safe.
To fix these issues this patch adds a per-context list of "zombie"
sampler views. These are views which are to be freed at some point
when the context is active. Other contexts may safely add sampler
views to the zombie list at any time (it's mutex protected). This
avoids the context/view ownership mix-ups we had before.
Tested with: google-chrome, google earth, Redway3D Watch/Turbine demos
a few Linux games. If anyone can recomment some other multi-threaded,
multi-context GL apps to test, please let me know.
v2: avoid potential race issue by always adding sampler views to the
zombie list if the view's context doesn't match the current context,
ignoring the refcount.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Reviewed-by: Neha Bhende <bhenden@vmware.com>
Reviewed-by: Mathias Fröhlich <Mathias.Froehlich@web.de>
Reviewed-By: Jose Fonseca <jfonseca@vmware.com>
Brian Paul [Tue, 12 Mar 2019 01:58:04 +0000 (19:58 -0600)]
docs: link to the meson_options.txt file gitlab.freedesktop.org
Brian Paul [Fri, 8 Mar 2019 17:31:11 +0000 (10:31 -0700)]
docs: separate information for compiler selection and compiler options
Split up the "Environment Variables" section into "Compiler Options"
and "Compiler Specification". I think this makes the information
easier to find and understand.
Mauro Rossi [Sun, 17 Mar 2019 21:52:36 +0000 (22:52 +0100)]
android: nouveau: add support for nir
Add the necessary build rules for android, to avoid building errors.
Fixes: f014ae3 ("nouveau: add support for nir")
Signed-off-by: Mauro Rossi <issor.oruam@gmail.com>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Timothy Arceri [Sun, 17 Mar 2019 10:04:20 +0000 (21:04 +1100)]
ac/nir_to_llvm: add assert to emit_bcsel()
nir to llvm assumes we have already split vectors to scalars via
nir_lower_alu_to_scalar().
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Timothy Arceri [Thu, 14 Mar 2019 00:02:11 +0000 (11:02 +1100)]
radeonsi/nir: call some more var optimisation passes
shader-db results (VEGA64):
Totals from affected shaders:
SGPRS:
5328912 ->
5329680 (0.01 %)
VGPRS:
2969308 ->
2969164 (-0.00 %)
Spilled SGPRs: 37921 -> 37917 (-0.01 %)
Spilled VGPRs: 32882 -> 29024 (-11.73 %)
Private memory VGPRs: 0 -> 0 (0.00 %)
Scratch size: 1400 -> 1200 (-14.29 %) dwords per thread
Code Size:
121126000 ->
121282784 (0.13 %) bytes
LDS: 1501 -> 1501 (0.00 %) blocks
Max Waves: 933188 -> 933229 (0.00 %)
Wait states: 0 -> 0 (0.00 %)
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Tobias Klausmann [Sat, 16 Mar 2019 18:56:59 +0000 (19:56 +0100)]
vulkan/util: meson build - add wayland client include
Without this the build breaks with:
In file included from ../src/vulkan/util/vk_util.h:32,
from ../src/vulkan/util/vk_util.c:28:
../include/vulkan/vulkan.h:51:10: fatal error: wayland-client.h: No such file or
directory
#include <wayland-client.h>
^~~~~~~~~~~~~~~~~~
compilation terminated.
The above misses the include directory for wayland:
-I/usr/include/wayland
Signed-off-by: Tobias Klausmann <tobias.johannes.klausmann@mni.thm.de>
Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Karol Herbst [Thu, 16 Aug 2018 20:11:47 +0000 (22:11 +0200)]
nv50ir/nir: move immediates before use
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Sat, 30 Jun 2018 14:22:17 +0000 (16:22 +0200)]
nv50/ir/nir: handle user clip planes for each emitted vertex
v9: convert to C++ style comments
handle for tess eval shaders as well
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Tue, 9 Jan 2018 23:35:47 +0000 (00:35 +0100)]
nv50/ir/nir: implement intrinsic shader_clock
v9: mark as fixed
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Sat, 6 Jan 2018 23:35:37 +0000 (00:35 +0100)]
nv50/ir/nir: implement load_per_vertex_output
v4: use smarter getIndirect helper
use new getSlotAddress helper
v5: use loadFrom helper
v8: don't require C++11 features
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Mon, 25 Dec 2017 22:15:03 +0000 (23:15 +0100)]
nv50/ir/nir: add memory barriers
v5: add more barrier intrinsics
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Sat, 23 Dec 2017 17:05:49 +0000 (18:05 +0100)]
nv50/ir/nir: implement images
v3: fix compiler warnings
v4: use loadFrom helper
v5: fix signed min/max
v6: set tex mask
add support for indirect image access
set cache mode
v7: make compatible with
884d27bcf688d36c3bbe01bceca525595add3b33
rework the whole deref thing to prepare for bindless
v8: port to deref instructions
don't require C++11 features
v9: implement MS images
rebase on master (image modifiers)
fix regressions due to variable src compnents
replace '(*it).' with 'it->'
convert to C++ style comments
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Sat, 23 Dec 2017 01:26:03 +0000 (02:26 +0100)]
nv50/ir/nir: implement ssbo intrinsics
v4: use loadFrom helper
v5: support indirect buffer access
v8: don't require C++11 features
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Fri, 22 Dec 2017 17:01:38 +0000 (18:01 +0100)]
nv50/ir/nir: implement nir_intrinsic_load_ubo
v4: use loadFrom helper
v8: don't require C++11 features
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Thu, 21 Dec 2017 15:30:25 +0000 (16:30 +0100)]
nv50/ir/nir: implement geometry shader nir_intrinsics
v4: use smarter getIndirect helper
use new getSlotAddress helper
use loadFrom helper
v8: don't require C++11 features
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Mon, 11 Dec 2017 01:11:50 +0000 (02:11 +0100)]
nv50/ir/nir: implement variable indexing
We store those arrays in local memory and reserve some space for each of the
arrays. With NIR we could store those arrays packed, but we don't do that yet
as it causes MemoryOpt to generate unaligned memory accesses.
v3: use fixed size vec4 arrays until we fix MemoryOpt
v4: fix for 64 bit types
v5: use loadFrom helper
v8: don't require C++11 features
v9: convert to C++ style comments
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Wed, 20 Dec 2017 16:06:03 +0000 (17:06 +0100)]
nv50/ir/nir: implement vote and ballot
v2: add vote_eq support
use the new subop intrinsic helper
add ballot
v3: add read_(first_)invocation
v8: handle vectorized intrinsics
don't require C++11 features
v9: lower_subgroups to 32 bit (produces less instructions)
use getSSA and getScratch instead of new_LValue
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Sat, 23 Dec 2017 01:25:41 +0000 (02:25 +0100)]
nv50/ir/nir: add skeleton getOperation for intrinsics
v7: don't assert in default case for getSubOp
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Pierre Moreau <pierre.morrow@free.fr>
Karol Herbst [Tue, 12 Dec 2017 17:07:01 +0000 (18:07 +0100)]
nv50/ir/nir: implement nir_instr_type_tex
a lot of those fields are not valid for a lot of tex ops. Not quite sure if
it's worth the effort to check for those or just keep it like that. It seems
to kind of work.
v2: reworked offset handling
add tex support with indirect R/S arguments
handle GLSL_SAMPLER_DIM_EXTERNAL
drop reference in convert(glsl_sampler_dim&, bool, bool)
fix tg4 component selection
v5: fill up coords args with scratch values if coords provided is less than TexTarget.getArgCount()
v7: prepare for bindless_texture support
v8: don't require C++11 features
v9: convert to C++ style comments
fix txf with a uniform constant 0 lod
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Thu, 14 Dec 2017 00:15:55 +0000 (01:15 +0100)]
nv50/ir/nir: implement nir_ssa_undef_instr
v2: use mkOp
v8: don't require C++11 features
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Pierre Moreau <pierre.morrow@free.fr>
Karol Herbst [Wed, 13 Dec 2017 21:14:03 +0000 (22:14 +0100)]
nv50/ir/nir: implement loading system values
v2: support more sys values
fixed a bug where for multi component reads all values ended up in x
v3: add load_patch_vertices_in
v4: add subgroup stuff
v5: add helper invocation
v6: fix loading 64 bit system values
v8: don't require C++11 features
v9: convert to C++ style comments
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Wed, 13 Dec 2017 20:59:29 +0000 (21:59 +0100)]
nv50/ir/nir: implement intrinsic_discard(_if)
v9: use getSSA instead of new_LValue
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Mon, 11 Dec 2017 15:21:06 +0000 (16:21 +0100)]
nv50/ir/nir: implement load_(interpolated_)input/output
v3: and load_output
v4: use smarter getIndirect helper
use new getSlotAddress helper
v5: don't use const_offset directly
fix for indirects
v6: add support for interpolateAt
v7: fix compiler warnings
add load_barycentric_sample
handle load_output for fragment shaders
v8: set info->prop.fp.readsSampleLocations for at_sample interpolation
don't require C++11 features
v9: convert to C++ style comments
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Mon, 11 Dec 2017 14:46:19 +0000 (15:46 +0100)]
nv50/ir/nir: implement nir_intrinsic_store_(per_vertex_)output
v3: add workaround for RA issues
indirects have to be multiplied by 0x10
fix indirect access
v4: use smarter getIndirect helper
use storeTo helper
v5: don't use const_offset directly
v8: don't require C++11 features
v9: convert to C++ style comments
handle clip planes correctly
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Tue, 12 Dec 2017 20:02:37 +0000 (21:02 +0100)]
nv50/ir/nir: implement nir_intrinsic_load_uniform
v2: use new getIndirect helper
fixes symbols for 64 bit types
v4: use smarter getIndirect helper
simplify address calculation
use loadFrom helper
v8: don't require C++11 features
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Tue, 12 Dec 2017 20:05:30 +0000 (21:05 +0100)]
nv50/ir/nir: implement nir_alu_instr handling
v2: user bitfield_insert instead of bfi
rework switch helper macros
remove some lowering code (LoweringHelper is now used for this)
v3: add pack_half_2x16_split
add unpack_half_2x16_split_x/y
v5: replace first argument with nullptr in loadImm calls
prefer getSSA over getScratch
v8: fix setting precise modifier for first instruction inside a block
add guard in case no instruction gets inserted into an empty block
don't require C++11 features
v9: use CC_NE for integer compares
convert to C++ style comments
fix b2f for doubles
remove macros around nir ops to make it easier to grep them
add handling for fpow
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Thu, 21 Dec 2017 12:33:23 +0000 (13:33 +0100)]
nv50/ir/nir: add skeleton for nir_intrinsic_instr
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Pierre Moreau <pierre.morrow@free.fr>
Karol Herbst [Tue, 12 Dec 2017 20:01:39 +0000 (21:01 +0100)]
nv50/ir/nir: implement nir_load_const_instr
v8: fix loading 8/16 bit constants
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Pierre Moreau <pierre.morrow@free.fr>
Karol Herbst [Fri, 15 Dec 2017 16:40:15 +0000 (17:40 +0100)]
nv50/ir/nir: parse NIR shader info
v2: parse a few more fields
v3: add special handling for GL_ISOLINES
v8: set info->prop.fp.readsSampleLocations
don't require C++11 features
v9: replace '(*it).' with 'it->'
convert to C++ style comments
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Tue, 9 Jan 2018 02:22:00 +0000 (03:22 +0100)]
nv50/ir/nir: add loadFrom and storeTo helpler
v8: don't require C++11 features
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Mon, 11 Dec 2017 17:01:29 +0000 (18:01 +0100)]
nv50/ir/nir: run assignSlots
v2: add support for geometry shaders
set idx
add some missing mappings
fix for 64bit inputs/outputs
fix up some FP color output index messup
parse centroid flag
v3: fix arrays in outputs as well
fix input/ouput size calculation for tessellation shaders
v4: add getSlotAddress helper
fix for 64 bit typed inputs
v5: change getSlotAddress interface for easier use
fix sample inputs
fix slot counting for mat
v7: fix driver_location of images
v8: don't require C++11 features
v9: convert to C++ style comments
support VERT_ATTRIB_POINT_SIZE
add more error checking to slots
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Mon, 18 Dec 2017 02:57:06 +0000 (03:57 +0100)]
nv50/ir/nir: add nir type helper functions
v4: treat imul as unsigned
v5: remove pointless !!
v7: inot is unsigned as well
v8: don't require C++11 features
v9: convert to C++ style comments
improve formatting
print error in all cases where codegen doesn't support a given type
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Acked-by: Pierre Moreau <pierre.morrow@free.fr>
Karol Herbst [Tue, 12 Dec 2017 20:01:28 +0000 (21:01 +0100)]
nv50/ir/nir: track defs and provide easy access functions
v2: add helper function for indirects
v4: add new getIndirect overload for easier use
v5: use getSSA for ssa values
we can just create the values for unassigned registers in getSrc
v6: always create at least 32 bit values
v8: don't require C++11 features
v9: include unordered_map on supported stdlibs
replace '(*it).' with 'it->'
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Karol Herbst [Sun, 10 Dec 2017 19:39:23 +0000 (20:39 +0100)]
nv50/ir/nir: run some passes to make the conversion easier
v2: add constant_folding
v6: print non final NIR only for verbose debugging
v8: add passes we will need for OpenCL compute shaders
v9: move type_size into anonymous namespace
convert to C++ style comments
lower bools to int32
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Acked-by: Pierre Moreau <pierre.morrow@free.fr>
Karol Herbst [Tue, 10 Apr 2018 14:41:01 +0000 (16:41 +0200)]
nouveau: fix nir and TGSI shader cache collision
v9: rename variable to driver_flags
use constants for shader cache flags
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Pierre Moreau <pierre.morrow@free.fr>
Karol Herbst [Sun, 10 Dec 2017 14:06:45 +0000 (15:06 +0100)]
nouveau: add support for nir
not all those nir options are actually required, it just made the work a
little easier.
v2: fix asserts
parse compute shaders
don't lower bitfield_insert
v3: fix memory leak
v4: don't lower fmod32
v5: set lower_all_io_to_temps to false
fix memory leak because we take over ownership of the nir shader
merge: use the lowering helper
v6: include TGSI debug header for proper assert call
add nv50 support
v7: fix Automake build
v8: free shader only for the set shader type
v9: check for IR type inside get_compiler_options
squash "nouveau: add env var to make nir default"
fix memory leak when creating compute shaders
use debug_get_bool_option as it is available in non debug builds
return failure if unsupported IR is encountered
don't lower fpow in nir
lower int 64 divmod inside nir to prevent crashes
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Pierre Moreau <pierre.morrow@free.fr>
Karol Herbst [Wed, 3 Jan 2018 14:31:15 +0000 (15:31 +0100)]
nv50/ir: add lowering helper
if we start supporting multiple input IRs we might want to move lowering code
into a common place and keep the initial translation simplier.
This will also allows us to react on ISA changes more easily.
v5: also handle SAT
v6: rename type variables
fixed lowering of NEG
add lowering of NOT
v8: don't require C++11 features
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Pierre Moreau <pierre.morrow@free.fr>
Karol Herbst [Tue, 2 Jan 2018 18:02:30 +0000 (19:02 +0100)]
nv50/ir: move common converter code in base class
v2: remove TGSI related bits
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Pierre Moreau <pierre.morrow@free.fr>
Karol Herbst [Fri, 15 Dec 2017 19:04:59 +0000 (20:04 +0100)]
nvc0: print the shader type when dumping headers
this makes debugging the shader header a little easier
Acked-by: Pierre Moreau <pierre.morrow@free.fr>
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Bas Nieuwenhuizen [Sat, 16 Mar 2019 21:58:38 +0000 (22:58 +0100)]
radeonsi: Remove implicit const cast.
Fixes: b9e02fe138e "gallium: add pipe_grid_info::last_block"
Reviewed-by: Eric Engestrom <eric@engestrom.ch>
Bas Nieuwenhuizen [Tue, 12 Mar 2019 23:15:09 +0000 (00:15 +0100)]
gitlab-ci: Build turnip.
No autotools build to care about.
The half baked turnips param is kind of ugly, but felt like a waste
defining more variables for it now.
Reviewed-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Kristian H. Kristensen <hoegsberg@chromium.org>
Bas Nieuwenhuizen [Tue, 12 Mar 2019 23:38:02 +0000 (00:38 +0100)]
turnip: Deconflict vk_format_table regeneration
Avoids
src/freedreno/vulkan/meson.build:42:0: ERROR: Tried to create target "vk_format_table.c", but a target of that name already exists.
when building both radv and turnip.
Fixes: 26380b3a9f8 "turnip: Add driver skeleton (v2)"
Reviewed-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Kristian H. Kristensen <hoegsberg@chromium.org>
Bas Nieuwenhuizen [Tue, 12 Mar 2019 23:07:02 +0000 (00:07 +0100)]
turnip: Fix GCC compiles.
Apparently GCC does not consider static const variables to be
integer constants, and hence the array size and the static assert
result in compile failures.
Fixes: 4b9f967cd1a "turnip: add a more complete format table"
Reviewed-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Kristian H. Kristensen <hoegsberg@chromium.org>
Jason Ekstrand [Thu, 14 Mar 2019 17:58:16 +0000 (12:58 -0500)]
intel/nir: Lower array-deref-of-vector UBO and SSBO loads
This fixes a serious performance issue with DXVK:
https://github.com/doitsujin/dxvk/issues/937
This was caused by a recent change that to improve performance on RADV
which back-fired on ANV and killed performance for some apps:
https://github.com/doitsujin/dxvk/commit/
e5a06d3f4a103a54cd4eb51970fedee405d1d698
Throwing in this bit of lowering lets us come along and CSE those UBO
loads (or copy-prop for SSBO load) and get one load where we previously
would have gotten several.
VkPipeline-db results on Kaby Lake:
total instructions in shared programs:
5115361 ->
5073185 (-0.82%)
instructions in affected programs:
1754333 ->
1712157 (-2.40%)
helped: 5331
HURT: 63
total cycles in shared programs:
2544501169 ->
2481144545 (-2.49%)
cycles in affected programs:
2531058653 ->
2467702029 (-2.50%)
helped: 9202
HURT: 4323
total loops in shared programs: 3340 -> 3331 (-0.27%)
loops in affected programs: 9 -> 0
helped: 9
HURT: 0
total spills in shared programs: 3246 -> 3053 (-5.95%)
spills in affected programs: 384 -> 191 (-50.26%)
helped: 10
HURT: 5
total fills in shared programs: 4626 -> 4452 (-3.76%)
fills in affected programs: 439 -> 265 (-39.64%)
helped: 10
HURT: 5
All of the shaders with hurt spilling were in Rise of the Tomb Raider
which also had shaders solidly helped in the spilling department. Not
shown in those results (because I've not had success dumping the
shaders) is Witcher 3 where this reduces spilling and improves over-all
perf by around 20-25%. There were no shader-db changes. Apparently,
this just isn't a pattern that happens in OpenGL.
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Cc: "19.0" mesa-stable@lists.freedesktop.org
Jason Ekstrand [Mon, 11 Mar 2019 23:47:39 +0000 (18:47 -0500)]
nir: Add a new pass to lower array dereferences on vectors
This pass was originally written for lowering TCS output reads and
writes but it is also applicable just about anything including UBOs,
SSBOs, and shared variables.
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Jason Ekstrand [Mon, 11 Mar 2019 23:58:24 +0000 (18:58 -0500)]
nir/builder: Add a vector extract helper
This one's a tiny bit better than what we had in spirv_to_nir because it
emits a binary tree rather than a linear walk. It also doesn't leave
around unneeded bcsel instructions for a constant index and returns an
undef for constant OOB access.
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Gert Wollny [Fri, 15 Mar 2019 09:31:26 +0000 (10:31 +0100)]
softpipe: Enable PIPE_CAP_MIXED_COLORBUFFER_FORMATS
It seems softpipe actually supports this. This change enables the
following piglits as passing without regressions in the gpu test set:
gl-3.1-mixed-int-float-fbo
gl-3.1-mixed-int-float-fbo int_second
fbo-blending-format-quirks
Changes for deqp:
dEQP-GLES2.functional.fbo.completeness.attachment_combinations.rbo_tex_none_none QualityWarning -> Pass
dEQP-GLES2.functional.fbo.completeness.attachment_combinations.rbo_tex_none_rbo QualityWarning -> Pass
dEQP-GLES2.functional.fbo.completeness.attachment_combinations.rbo_tex_none_tex QualityWarning -> Pass
dEQP-GLES2.functional.fbo.completeness.attachment_combinations.rbo_tex_rbo_none QualityWarning -> Pass
dEQP-GLES2.functional.fbo.completeness.attachment_combinations.rbo_tex_tex_none QualityWarning -> Pass
dEQP-GLES2.functional.fbo.completeness.attachment_combinations.tex_rbo_none_none QualityWarning -> Pass
dEQP-GLES2.functional.fbo.completeness.attachment_combinations.tex_rbo_none_rbo QualityWarning -> Pass
dEQP-GLES2.functional.fbo.completeness.attachment_combinations.tex_rbo_none_tex QualityWarning -> Pass
dEQP-GLES2.functional.fbo.completeness.attachment_combinations.tex_rbo_rbo_none QualityWarning -> Pass
dEQP-GLES2.functional.fbo.completeness.attachment_combinations.tex_rbo_tex_none QualityWarning -> Pass
dEQP-GLES3.functional.fbo.completeness.samples.rbo0_rbo0_tex Fail -> Pass
dEQP-GLES3.functional.fbo.completeness.samples.rbo0_tex_none Fail -> Pass
dEQP-GLES3.functional.fbo.completeness.samples.rbo1_rbo1_rbo1 Fail -> Pass
dEQP-GLES3.functional.fragment_out.random.* NotSupported -> Pass
dEQP-GLES31.functional.shaders.builtin_functions.common.frexp.*_fragment Fail -> Pass
dEQP-GLES31.functional.shaders.builtin_functions.common.frexp.*_vertex Fail -> Pass
dEQP-GLES31.functional.shaders.builtin_functions.precision.frexp.*_fragment.* Fail -> Pass
dEQP-GLES31.functional.shaders.builtin_functions.precision.frexp.*_vertex.* Fail -> Pass
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Rob Clark [Tue, 26 Feb 2019 19:46:45 +0000 (14:46 -0500)]
freedreno/ir3/cp: fix ldib bug
Something that we didn't hit earlier because of the extra shr.b
Signed-off-by: Rob Clark <robdclark@gmail.com>
Reviewed-by: Kristian H. Kristensen <hoegsberg@chromium.org>
James Zhu [Wed, 6 Mar 2019 17:36:37 +0000 (12:36 -0500)]
gallium/auxiliary/vl: Change weave compute shader implementation
Use 2D_ARRARY instead of RECT to fetch texels for weave compute
shader.
Problem 2,3: Fixed interpolation issue with weave de-interlace
Fixes: 9364d66cb7f7 (Add video compositor compute shader render)
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=109646
Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Tested-by: Bruno Milreu <bmilreu@gmail.com>
James Zhu [Wed, 6 Mar 2019 17:29:09 +0000 (12:29 -0500)]
gallium/auxiliary/vl: Change grid setting
Using draw area for grid setting instead of destination
buffer size.
Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Tested-by: Bruno Milreu <bmilreu@gmail.com>
James Zhu [Wed, 6 Mar 2019 17:01:07 +0000 (12:01 -0500)]
gallium/auxiliary/vl: Increase shader_params size
Increase shader_params size to pass sampler data to
compute shader during weave de-interlace.
Signed-off-by: James Zhu <James.Zhu@amd.com>
Acked-by: Leo Liu <leo.liu@amd.com>
Tested-by: Bruno Milreu <bmilreu@gmail.com>
Marek Olšák [Wed, 27 Feb 2019 22:19:55 +0000 (17:19 -0500)]
omx: add a compute path in enc_LoadImage_common
Acked-by: Leo Liu <leo.liu@amd.com>
Marek Olšák [Wed, 27 Feb 2019 22:19:54 +0000 (17:19 -0500)]
omx: clean up enc_LoadImage_common
- add *pipe
- add documentation
Acked-by: Leo Liu <leo.liu@amd.com>
Marek Olšák [Wed, 27 Feb 2019 22:19:53 +0000 (17:19 -0500)]
gallium: add pipe_grid_info::last_block
The OpenMAX state tracker will use this.
RadeonSI is adapted to use pipe_grid_info::last_block instead of its
internal state.
Acked-by: Leo Liu <leo.liu@amd.com>
Alejandro Piñeiro [Thu, 14 Mar 2019 10:02:52 +0000 (11:02 +0100)]
nir/xfb: move varyings info out of nir_xfb_info
When varyings was added we moved to use to dynamycally allocated
pointers, instead of allocating just one block for everything. That
breaks some assumptions of some vulkan drivers (like anv), that make
serialization and copying easier. And at the same time, varyings are
not needed for vulkan.
So this commit moves them out. Although it seems a little an overkill,
fixing the anv side would require a similar, or more, changes, so in
the end it is about to decide where do we want to put our effort.
v2: (from Jason review)
* Don't use a temp variable on the _create methods, just return
result of rzalloc_size
* Wrap some lines too long.
Fixes: cf0b2ad486c9 ("nir/xfb: adding varyings on nir_xfb_info and gather_info")
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Samuel Pitoiset [Fri, 15 Mar 2019 09:36:00 +0000 (10:36 +0100)]
radv: always load 3 channels for formats that need to be shuffled
This fixes a rendering issue with Hellblade and DXVK.
Fixes: a66b186bebf ("radv: use typed buffer loads for vertex input fetches")
Reported-by: Philip Rebohle <philip.rebohle@tu-dortmund.de>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Mathias Fröhlich [Thu, 14 Mar 2019 04:58:43 +0000 (05:58 +0100)]
mesa: Add assert to _mesa_primitive_restart_index.
Make sure the inde_size parameter is meant to be in bytes.
Reviewed-by: Brian Paul <brianp@vmware.com>
Signed-off-by: Mathias Fröhlich <Mathias.Froehlich@web.de>
Mathias Fröhlich [Fri, 1 Mar 2019 08:27:54 +0000 (09:27 +0100)]
vbo: Fix GL_PRIMITIVE_RESTART_FIXED_INDEX in display list compiles.
The maximum value primitive restart index is different for each index data
type. Use the appropriate fixed restart index value.
Reviewed-by: Brian Paul <brianp@vmware.com>
Signed-off-by: Mathias Fröhlich <Mathias.Froehlich@web.de>
Mathias Fröhlich [Fri, 1 Mar 2019 08:27:54 +0000 (09:27 +0100)]
vbo: Fix basevertex handling in display list compiles.
The standard requires that the primitive restart comparison happens before
the basevertex value is added. Do this now, drop a reference to the standard
why this happens at this place.
Reviewed-by: Brian Paul <brianp@vmware.com>
Signed-off-by: Mathias Fröhlich <Mathias.Froehlich@web.de>
Mathias Fröhlich [Fri, 1 Mar 2019 08:27:54 +0000 (09:27 +0100)]
mesa: Use mapping tools in debug prints.
Reviewed-by: Brian Paul <brianp@vmware.com>
Signed-off-by: Mathias Fröhlich <Mathias.Froehlich@web.de>
Mathias Fröhlich [Fri, 1 Mar 2019 08:27:53 +0000 (09:27 +0100)]
mesa: Remove _ae_{,un}map_vbos and dependencies.
Since mapping and unmapping the buffer objects in a VAO is handled
directly from the VAO, this part of the _NEW_ARRAY state is no longer
used. So remove this part of array element state.
Reviewed-by: Brian Paul <brianp@vmware.com>
Signed-off-by: Mathias Fröhlich <Mathias.Froehlich@web.de>
Mathias Fröhlich [Fri, 1 Mar 2019 08:27:53 +0000 (09:27 +0100)]
mesa: Replace _ae_{,un}map_vbos with _mesa_vao_{,un}map_arrays
Due to the use of bitmaps, the _mesa_vao_{,un}map_arrays functions
should provide comparable runtime efficienty to the currently used
_ae_{,un}map_vbos functions. So use this functions and enable
further cleanup.
Reviewed-by: Brian Paul <brianp@vmware.com>
Signed-off-by: Mathias Fröhlich <Mathias.Froehlich@web.de>
Mathias Fröhlich [Fri, 1 Mar 2019 08:27:53 +0000 (09:27 +0100)]
mesa: Use _mesa_array_element in dlist save.
Make use of the newly factored out _mesa_array_element function
in display list compilation. For now that duplicates out the
primitive restart logic. But that turns out to need a fix in
display list handling anyhow.
Reviewed-by: Brian Paul <brianp@vmware.com>
Signed-off-by: Mathias Fröhlich <Mathias.Froehlich@web.de>
Mathias Fröhlich [Fri, 1 Mar 2019 08:27:53 +0000 (09:27 +0100)]
mesa: Factor out _mesa_array_element.
The factored out function handles emitting the vertex attributes
at the given index. The now public accessible function gets used
in the following patches.
Reviewed-by: Brian Paul <brianp@vmware.com>
Signed-off-by: Mathias Fröhlich <Mathias.Froehlich@web.de>
Mathias Fröhlich [Fri, 1 Mar 2019 08:27:53 +0000 (09:27 +0100)]
mesa: Implement helper functions to map and unmap a VAO.
Provide a set of functions that maps or unmaps all VBOs held
in a VAO. The functions will be used in the following patches.
v2: Update comments.
Reviewed-by: Brian Paul <brianp@vmware.com>
Signed-off-by: Mathias Fröhlich <Mathias.Froehlich@web.de>
Jason Ekstrand [Sun, 10 Mar 2019 13:57:51 +0000 (08:57 -0500)]
st/mesa: Let NIR lower UBO and SSBO access when we have it
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Jason Ekstrand [Sat, 9 Mar 2019 15:08:44 +0000 (09:08 -0600)]
i965: Stop setting LowerBuferInterfaceBlocks
Instead, we do UBO and SSBO deref lowering in NIR after we've given it a
chance to optimize SSBO access:
Shader-db results on Kaby Lake:
total instructions in shared programs:
15235775 ->
15235484 (<.01%)
instructions in affected programs: 14992 -> 14701 (-1.94%)
helped: 19
HURT: 20
total cycles in shared programs:
339220331 ->
339027307 (-0.06%)
cycles in affected programs:
79831981 ->
79638957 (-0.24%)
helped: 540
HURT: 602
total loops in shared programs: 4402 -> 4348 (-1.23%)
loops in affected programs: 186 -> 132 (-29.03%)
helped: 27
HURT: 0
total spills in shared programs: 23261 -> 23234 (-0.12%)
spills in affected programs: 38 -> 11 (-71.05%)
helped: 1
HURT: 0
total fills in shared programs: 31442 -> 31371 (-0.23%)
fills in affected programs: 98 -> 27 (-72.45%)
helped: 1
HURT: 0
LOST: 12
GAINED: 12
Most of the help and hurt in instruction counts was just churn caused by
re-ordering of optimizations and the fact that the NIR deref lowering
code is emitting slightly different instructions. Nothing was hurt by
more than three instructions and most things weren't helped by more than
four. The primary exception to this is one Car Chase shader:
shaders/non-free/gfxbench4/carchase/341.shader_test CS SIMD32: 1144 -> 821 (-28.23%)
There is also one compute shader in Manhattan 3.1 and a fragment shader
in the UE4 Shooter Game demo that now get a loop partially unrolled.
Those showed up in the results as hurt instructions but were manually
removed to get the results above.
The lost/gained was a dozen Car Chase shaders that went from SIMD8 to
SIMD16 thanks to improved register pressure:
shaders/non-free/gfxbench4/carchase/366.shader_test CS
shaders/non-free/gfxbench4/carchase/368.shader_test CS
shaders/non-free/gfxbench4/carchase/370.shader_test CS
shaders/non-free/gfxbench4/carchase/372.shader_test CS
shaders/non-free/gfxbench4/carchase/376.shader_test CS
shaders/non-free/gfxbench4/carchase/378.shader_test CS
shaders/non-free/gfxbench4/carchase/380.shader_test CS
shaders/non-free/gfxbench4/carchase/382.shader_test CS
shaders/non-free/gfxbench4/carchase/384.shader_test CS
shaders/non-free/gfxbench4/carchase/388.shader_test CS
shaders/non-free/gfxbench4/carchase/4.shader_test CS
shaders/non-free/gfxbench4/carchase/6.shader_test CS
Given how much it appeared to be improved, I ran Car Chase on my laptop.
Unfortunately, I wasn't able to see any measurable improvement. It
might be helped by 1-2% but it's in the noise. It does render correctly
as far as I can tell so the improvement is legitimate.
All of the loops that got delete were in dolphin uber shaders. I've had
no opportunity to test them for correctness or performance.
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Jason Ekstrand [Sat, 9 Mar 2019 16:12:46 +0000 (10:12 -0600)]
glsl/nir: Add a pass to lower UBO and SSBO access
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Jason Ekstrand [Thu, 14 Mar 2019 17:00:04 +0000 (12:00 -0500)]
glsl/nir: Handle unlowered SSBO atomic and array_length intrinsics
We didn't have any of these before because all NIR consumers always
called lower_ubo_references. Soon, we want to pass the derefs straight
through to NIR so we need to handle these intrinsics directly.
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>