Work in progress (disabled).
USE_8x2_TILE_BACKEND define in knobs.h enables AVX512 code paths
(emulated on non-AVX512 HW).
Signed-off-by: Tim Rowley <timothy.o.rowley@intel.com>
src2 was being given the wrong modifier, and we were not properly
managing the modifier on the SHL source either.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Rename to gl_vertex_attrib_array::BufferBindingIndex because this field
is an index into the array of buffer binding points. This makes some
code a little easier to follow since there's also a "VertexBinding" field
in gl_vertex_array_object.
Reviewed-by: Mathias Fröhlich <mathias.froehlich@web.de>
Use a bitmask to indicate which color buffers are integer-valued, rather
than a bool. Also, the old field was mis-computed. If an integer buffer
was followed by a non-integer buffer, the _IntegerColor field was wrongly
set to false.
This fixes the new piglit gl-3.1-mixed-int-float-fbo test.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
None of the drivers which implement this hook do anything with the
texture parameter value. Drivers just look at the pname and set a
dirty flag if needed.
We were doing some ugly casting and type conversion to setup the
argument so that all goes away.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Previously, the plan was "if the width/height we have to load/store isn't
the size the user is planning on writing, then we need to load the old
contents out beforehand to prevent writing back undefined".
However, when we're doing glTexImage() we often end up aligning the
width/height into the padding of the texture, and we don't actually
need to read out that padding.
Improves x11perf -aatrapezoid100 performance from ~460/sec to
~700/sec.
Regression introduced by
ba0274c7d6
Check the resource exists before assigning it
a flag (and use This->base.resource instead
of pResource, since the former may have a newly
allocate resource, while the latter would be
NULL).
This should reintroduce the behaviour of previous
code.
Signed-off-by: Axel Davy <axel.davy@ens.fr>
Since 1604efa6fd,
lconsti and lconstb don't need to be initialized.
Remove some leftovers from the previous code (which
has now invalid use of ARRAY_SIZE on a pointer instead
of an array).
Reported by Coverity.
Signed-off-by: Axel Davy <axel.davy@ens.fr>
Use uint64_t instead of int64_t in the calculation,
as the result is uint64_t.
Signed-off-by: Axel Davy <axel.davy@ens.fr>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
All ARB_enhanced_layouts piglit tests pass without any changes
in our compiler.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
These were changed in LLVM r284024.
v2:
- Only use float types for vdata of llvm.amdgcn.image.store. LLVM doesn't
support integer types for this intrinsic.
Signed-off-by: Dave Airlie <airlied@redhat.com>
The identity swizzle should operate exactly
like an .r = R, .g = G, .b = B, .a = A swizzle.
This fixes a bunch of the 16-bit BGRA blit tests
dEQP-VK.api.copy_and_blit.blit_image.all_formats.b4g4r4a4*
Signed-off-by: Dave Airlie <airlied@redhat.com>
This fix was found in the radv codebase when running dota2,
no idea if anyone has reported it on anv, but the same problem
occurs.
Once an image is acquired we need to mark it busy.
Acked-by: Edward O'Callaghan <funfunctor@folklore1984.net>
Cc: "12.0" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Dave Airlie <airlied@redhat.com>
dota2 does multiple acquires followed by multiple queues,
this bug manifested itself as a hang in the xshmfence code
randomly when dota2 was doing it's menus. It also occured
when running dota2 under phoronix-test-suite.
The fix is once the image is acquired to mark it busy then
so nobody else can acquire. We have to trust vulkan apps
that they will eventually submit it.
Acked-by: Edward O'Callaghan <funfunctor@folklore1984.net>
Signed-off-by: Dave Airlie <airlied@redhat.com>
The table was copied from the Vulkan driver. The comment lines are as long
as the table for cosmetic reasons.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
This is a serious performance fix. Discovered by luck.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94354
Cc: 12.0 <mesa-stable@lists.freedesktop.org>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
so that decompress blits aren't needed and depth texturing needs less
memory bandwidth.
Z16 and Z24 are promoted to Z32_FLOAT by the driver, because TC-compatible
HTILE only supports Z32_FLOAT. This doubles memory footprint for Z16.
The format promotion is not visible to state trackers.
This is part of TC-compatible renderbuffer compression, which has 3 parts:
DCC, HTILE, FMASK. Only TC-compatible FMASK compression is missing now.
I don't see a measurable increase in performance though.
(I tested Talos Principle and DiRT: Showdown, the latter is improved by
0.5%, which is almost noise, and it originally used layered Z16,
so at least we know that Z16 promoted to Z32F isn't slower now)
Tested-by: Edmondo Tommasina <edmondo.tommasina@gmail.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
For performance tuning in drivers. It filters out window system
framebuffers and OpenGL renderbuffers.
radeonsi will use this to guess whether a depth buffer will be read
by a shader. There is no guarantee about what will actually happen.
This is a departure from PIPE_BIND flags which are defined to be strict
but they are useless in practice.
Acked-by: Roland Scheidegger <sroland@vmware.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Whether one or two slots are taken up by one API array depends on the
vertex shader, not on how the array is configured. When an array is
set up with fewer components than the shader expects, the high components
are undefined.
Fixes GL45-CTS.vertex_attrib_binding.basic-inputL-case1.
Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Dave Airlie <airlied@redhat.com>
Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
This fixes a bug with offsets from uniforms which seems to have only been
noticed as a crash in piglit's
arb_gpu_shader5/compiler/builtin-functions/fs-gatherOffset-uniform-offset.frag
on radeonsi.
Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Fixes GL45-CTS.shader_image_load_store.basic-allTargets-atomic*
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
If pPhysicalDevices is too small for all physical devices,
the driver must return VK_INCOMPLETE. Since only a single
physical device is supported, this is only the case when
pPhysicalDeviceCount == 0 && pPhysicalDevices != NULL.
Signed-off-by: Dave Airlie <airlied@redhat.com>
Gallium is completely oblivious to whether the fbo is flipped or not.
Only flip the stipple pattern when the fbo is flipped as well. Otherwise
the driver has no idea when to unflip the pattern.
Fixes bin/gl-2.1-polygon-stipple-fs -fbo
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Brian Paul <brianp@vmware.com>
Tested-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Recent fix for non-const offsets broke the case of a single offset (vs 4
offsets). The later code relies on the offs array to contain null values
to tell whether they should be added onto the srcs list.
Fixes: 5239bd592 ("nvc0/ir: fix overwriting of value backing non-constant gather offset")
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Cc: mesa-stable@lists.freedesktop.org