Kenneth Graunke [Tue, 12 Jul 2016 08:46:53 +0000 (01:46 -0700)]
nir: Add nir_load_interpolated_input lowering code.
Now nir_lower_io can optionally produce load_interpolated_input
and load_barycentric_* intrinsics for fragment shader inputs.
flat inputs continue using regular load_input.
v2: Use a nir_shader_compiler_options flag rather than ad-hoc boolean
passing (in response to review feedback from Chris Forbes).
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Chris Forbes <chrisforbes@google.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Kenneth Graunke [Tue, 12 Jul 2016 08:46:43 +0000 (01:46 -0700)]
nir: Add new intrinsics for fragment shader input interpolation.
Backends can normally handle shader inputs solely by looking at
load_input intrinsics, and ignore the nir_variables in nir->inputs.
One exception is fragment shader inputs. load_input doesn't capture
the necessary interpolation information - flat, smooth, noperspective
mode, and centroid, sample, or pixel for the location. This means
that backends have to interpolate based on the nir_variables, then
associate those with the load_input intrinsics (say, by storing a
map of which variables are at which locations).
With GL_ARB_enhanced_layouts, we're going to have multiple varyings
packed into a single vec4 location. The intrinsics make this easy:
simply load N components from location <loc, component>. However,
working with variables and correlating the two is very awkward; we'd
much rather have intrinsics capture all the necessary information.
Fragment shader input interpolation typically works by producing a
set of barycentric coordinates, then using those to do a linear
interpolation between the values at the triangle's corners.
We represent this by introducing five new load_barycentric_* intrinsics:
- load_barycentric_pixel (ordinary variable)
- load_barycentric_centroid (centroid qualified variable)
- load_barycentric_sample (sample qualified variable)
- load_barycentric_at_sample (ARB_gpu_shader5's interpolateAtSample())
- load_barycentric_at_offset (ARB_gpu_shader5's interpolateAtOffset())
Each of these take the interpolation mode (smooth or noperspective only)
as a const_index, and produce a vec2. The last two also take a sample
or offset source.
We then introduce a new load_interpolated_input intrinsic, which
is like a normal load_input intrinsic, but with an additional
barycentric coordinate source.
The intention is that flat inputs will still use regular load_input
intrinsics. This makes them distinguishable from normal inputs that
need fancy interpolation, while also providing all the necessary data.
This nicely unifies regular inputs and interpolateAt functions.
Qualifiers and variables become irrelevant; there are just
load_barycentric intrinsics that determine the interpolation.
v2: Document the interp_mode const_index value, define a new
BARYCENTRIC() helper rather than using SYSTEM_VALUE() for
some of them (requested by Jason Ekstrand).
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Chris Forbes <chrisforbes@google.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Kenneth Graunke [Mon, 18 Jul 2016 23:13:36 +0000 (16:13 -0700)]
anv: Properly call gen75_emit_state_base_address on Haswell.
This should fix MOCS values. Caught by Coverity.
CID:
1364155
Cc: "12.0" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Kenneth Graunke [Mon, 18 Jul 2016 23:00:20 +0000 (16:00 -0700)]
genxml: Rename "API Rendering Disable" to "Rendering Disable".
Gen7/7.5 call it "Rendering Disable" while Gen8/9 prefix it with "API".
Pick one for consistency, and so we can share code between generations.
Cc: "12.0" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Kenneth Graunke [Mon, 18 Jul 2016 21:27:35 +0000 (14:27 -0700)]
anv: Unify 3DSTATE_CLIP code across generations.
The bulk of this is the same. There are just a couple fields that only
exist on one generation or another, and we can easily handle those with
an #ifdef.
Cc: "12.0" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Kenneth Graunke [Mon, 18 Jul 2016 20:52:07 +0000 (13:52 -0700)]
anv: Enable early culling on Gen7.
We set the cull mode, but forgot the enable bit. Gen8 uses this.
Cc: "12.0" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Kenneth Graunke [Mon, 18 Jul 2016 21:15:49 +0000 (14:15 -0700)]
anv: Fix near plane clipping on Gen7/7.5.
The Gen7/7.5 clip code used APIMODE_OGL, while the Gen8+ clip code used
APIMODE_D3D. The meaning hasn't changed, so one of these must be wrong.
It appears that the hardware documentation is completely wrong. It
claims that the "API Mode" bit means:
0h APIMODE_OGL NEAR_VP boundary == 0.0 (NDC)
1h APIMODE_D3D NEAR_VP boundary == -1.0 (NDC)
However, DirectX typically uses 0.0 for the near plane, while unextended
OpenGL uses -1.0. i965's gen6_clip_state.c uses APIMODE_D3D for the
GL_ZERO_TO_ONE case, so I believe the meanings are backwards from what
the documentation says.
Section 23.2 ("Primitive Clipping") of the Vulkan 1.0.21 specification
contains the following equations:
-w_c <= x_c <= w_c
-w_c <= y_c <= w_c
0 <= z_c <= w_c
This means that Vulkan follows D3D semantics.
Cc: "12.0" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Kenneth Graunke [Mon, 18 Jul 2016 20:56:23 +0000 (13:56 -0700)]
genxml: Add APIMODE_D3D missing enum values and improve consistency.
Cc: "12.0" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Kenneth Graunke [Mon, 18 Jul 2016 22:36:43 +0000 (15:36 -0700)]
genxml: Add CLIPMODE_* prefix to 3DSTATE_CLIP's "Clip Mode" enum values.
Gen6-7.5 use CLIPMODE_REJECT_ALL, while Gen8+ just used REJECT_ALL.
Being consistent will let me unify code, and I prefer having the prefix.
Cc: "12.0" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Tim Rowley [Fri, 15 Jul 2016 18:23:46 +0000 (12:23 -0600)]
swr: [rasterizer core] introduce simd16intrin.h
Refactoring to leave existing simd_* intrinsics in "simdintrin.h" unchanged,
adding corresponding simd16_* intrinsics in "simd16intrin.h" on the side,
with emulation, that we can use piecemeal, rather than the all-or-nothing
approach to bring up avx512.
Signed-off-by: Tim Rowley <timothy.o.rowley@intel.com>
Tim Rowley [Thu, 14 Jul 2016 18:10:39 +0000 (12:10 -0600)]
swr: [rasterizer core] fix for possible int32 overflow condition
Signed-off-by: Tim Rowley <timothy.o.rowley@intel.com>
Tim Rowley [Thu, 14 Jul 2016 18:02:51 +0000 (12:02 -0600)]
swr: [rasterizer core] rename *_MAX enum values to *_COUNT
Makes these names semantically correct.
Signed-off-by: Tim Rowley <timothy.o.rowley@intel.com>
Tim Rowley [Wed, 13 Jul 2016 23:34:03 +0000 (17:34 -0600)]
swr: [rasterizer core] centroid correction
Signed-off-by: Tim Rowley <timothy.o.rowley@intel.com>
Tim Rowley [Wed, 13 Jul 2016 21:06:13 +0000 (15:06 -0600)]
swr: [rasterizer core] support range of values in TemplateArgUnroller
Fixes Linux warnings.
Signed-off-by: Tim Rowley <timothy.o.rowley@intel.com>
Tim Rowley [Tue, 12 Jul 2016 23:04:44 +0000 (17:04 -0600)]
swr: [rasterizer core] ensure adjacent topologies use the cut-aware PA
Signed-off-by: Tim Rowley <timothy.o.rowley@intel.com>
Tim Rowley [Tue, 12 Jul 2016 21:03:42 +0000 (15:03 -0600)]
swr: [rasterizer] attribute swizzling and linkage
Add support for enhanced attribute swizzling. Currently supports constant
source overrides to handle PrimitiveID support. No support yet for input
select swizzling or wrap shortest. Removes obsoleted linkageMask and
associated code.
Signed-off-by: Tim Rowley <timothy.o.rowley@intel.com>
Tim Rowley [Tue, 12 Jul 2016 16:33:58 +0000 (10:33 -0600)]
swr: [rasterizer common] icc declspec definitions
Signed-off-by: Tim Rowley <timothy.o.rowley@intel.com>
Tim Rowley [Fri, 8 Jul 2016 19:08:20 +0000 (13:08 -0600)]
swr: [rasterizer jitter] rework vertex/instance ID storage in fetch
Moved the setting into the existing component control code. Fixes bad
interaction between attribute/component setting for vertex/instance ID
and component packing.
Signed-off-by: Tim Rowley <timothy.o.rowley@intel.com>
Tim Rowley [Thu, 7 Jul 2016 23:41:58 +0000 (17:41 -0600)]
swr: [rasterizer core] avx512 simd utility work
Enabling KNOB_SIMD_WIDTH = 16 for AVX512 pre-work and low level simd utils
Signed-off-by: Tim Rowley <timothy.o.rowley@intel.com>
Tim Rowley [Thu, 7 Jul 2016 23:32:39 +0000 (17:32 -0600)]
swr: [rasterizer core] viewport rounding for disabled scissor
Adjust viewport rounding when scissor rect is disabled during macro
tile scissor setup.
Signed-off-by: Tim Rowley <timothy.o.rowley@intel.com>
Jason Ekstrand [Mon, 18 Jul 2016 23:25:12 +0000 (16:25 -0700)]
i965: Stop muging cube array lengths by 6
From the Sky Lake PRM:
"For SURFTYPE_CUBE: For Sampling Engine Surfaces and Typed Data Port
Surfaces, the range of this field is [0,340], indicating the number of
cube array elements (equal to the number of underlying 2D array elements
divided by 6). For other surfaces, this field must be zero."
In other words, the depth field for cube maps is in number of cubes not
number of 2-D slices so we need to divide by 6. ISL will do this correctly
for us assuming that we provide it with the correct array bounds which it
expects to be in 2-D slices. It appears as if we've been doing this wrong
ever since we first added cube map arrays for Sandy Bridge and the change
to ISL made things slightly worse. While we're at it, we now need to remoe
the shader hacks we've always done since they were only needed because we
were setting the depth field six times too large.
v2: Fix the vec4 backend as well (not sure how I missed this).
Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Reviewed-by: Chris Forbes <chrisforbes@google.com>
Jason Ekstrand [Tue, 19 Jul 2016 05:00:30 +0000 (22:00 -0700)]
i965/miptree: Set logical_depth0 == 6 for cube maps
This matches what we do for cube maps where logical_depth0 is in number of
face-layers rather than number of cubes. This does mean that we will
temporarily be setting the surface bounds too loose for cube map textures
but we are already setting them too loose for cube arrays and we will be
fixing that in the next commit anyway.
Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Reviewed-by: Chris Forbes <chrisforbes@google.com>
Cc: "12.0 11.2 11.1" <mesa-stable@lists.freedesktop.org>
Jason Ekstrand [Tue, 19 Jul 2016 01:46:43 +0000 (18:46 -0700)]
i965/miptree: Enforce that height == 1 for 1-D array textures
The GL API and mesa internals do this differently than we do. In GL, there
is no depth parameter for 1-D arrays and height is used. In the i965
miptree code we do the sane thing and make height == 1 and use depth for
number of slices. This makes for a mismatch every time we create a 1-D
array texture from GL. Instead of actually solving this problem, we just
said "1-D is hard, let's make sure it works no matter which way we pass the
parameters" and called it a day.
This commit fixes the one GL -> i965 transition point where we weren't
already handling 1-D array textures to do the right thing and then replaces
the magic fixup code with an assert that you're doing the right thing.
Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Reviewed-by: Chris Forbes <chrisforbes@google.com>
Cc: "12.0 11.2 11.1" <mesa-stable@lists.freedesktop.org>
Stefan Dirsch [Thu, 14 Jul 2016 13:21:20 +0000 (15:21 +0200)]
Avoid overflow in 'last' variable of FindGLXFunction(...)
This 'last' variable used in FindGLXFunction(...) may become negative,
but has been defined as unsigned int resulting in an overflow,
finally resulting in a segfault when accessing _glXDispatchTableStrings[...].
Fixed this by definining it as signed int. 'first' variable also needs to be
defined as signed int. Otherwise condition for while loop fails due to C
implicitly converting signed to unsigned values before comparison.
Cc: <mesa-stable@lists.freedesktop.org>
Signed-off-by: Stefan Dirsch <sndirsch@suse.de>
Reviewed-by: Eric Engestrom <eric.engestrom@imgtec.com>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Tomasz Figa [Fri, 15 Jul 2016 07:53:50 +0000 (16:53 +0900)]
egl/android: Stop leaking DRI images
Current implementation of the DRI image loader does not free the images
created in get_back_bo() and so leaks memory. Moreover, it creates a new
image every time the DRI driver queries for buffers, even if the backing
native buffer has not changed. leaking memory again.
This patch adds missing call to destroyImage() in droid_enqueue_buffer()
and a check if image is already created to get_back_bo() to fix the
above.
Cc: "11.2 12.0" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Tomasz Figa [Fri, 15 Jul 2016 07:53:49 +0000 (16:53 +0900)]
egl/android: Add some useful error messages
It is much easier to debug issues when the application gives some
meaningful error messages. This patch adds few to the EGL Android
platform backend.
Signed-off-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Tomasz Figa [Fri, 15 Jul 2016 07:53:48 +0000 (16:53 +0900)]
egl/android: Check return value of dri2_get_dri_config()
It might return NULL if specific config variant is unsupported.
Cc: "11.2 12.0" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Emil Velikov [Fri, 15 Jul 2016 07:27:09 +0000 (16:27 +0900)]
i965: store reference to the context within struct brw_fence (v2)
As the spec allows for {server,client}_wait_sync to be called without
currently bound context, while our implementation requires context
pointer.
v2: Add a mutex and acquire it for the duration of
brw_fence_client_wait() and brw_fence_is_completed() as suggested
by Chad.
Cc: "11.2 12.0" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Emil Velikov <emil.l.velikov@gmail.com>
Signed-off-by: Tomasz Figa <tfiga@chromium.org>
Nicolas Boichat [Fri, 15 Jul 2016 08:24:20 +0000 (16:24 +0800)]
egl/dri2: dri2_make_current: Set EGL error if bindContext fails
Without this, if a configuration is, say, available only on GLES2/3, but
not on GLES1, and is rejected by the dri module's bindContext call,
eglMakeCurrent fails with error "EGL_SUCCESS".
In this patch, we set error to EGL_BAD_MATCH, which is what CTS/dEQP
dEQP-EGL.functional.surfaceless_context expect.
Cc: "11.2 12.0" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Nicolas Boichat <drinkcat@chromium.org>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Tomasz Figa [Wed, 13 Jul 2016 03:33:24 +0000 (11:33 +0800)]
egl/android: Remove unused variables
There are some unused variables left after previous clean-ups triggering
compiler warnings. Let's remove them.
Cc: "12.0" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Tomasz Figa <tfiga@chromium.org>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Tomasz Figa [Wed, 13 Jul 2016 03:29:45 +0000 (11:29 +0800)]
gallium/dri: Add shared glapi to LIBADD on Android
An earlier patch fixed the problem for classic drivers, however Gallium
was still left broken. This patch applies the same workaround to
Gallium, when compiled for Android. Following is a quote from the
original patch:
0cbc90c57cfc mesa: dri: Add shared glapi to LIBADD on Android
/system/vendor/lib/dri/*_dri.so actually depend on libglapi: without
this, loading the so file fails with:
cannot locate symbol "__emutls_v._glapi_tls_Context"
On non-Android (non-bionic) platform, EGL uses the following
workflow, which works fine:
dlopen("libglapi.so", RTLD_LAZY | RTLD_GLOBAL);
dlopen("dri/<driver>_dri.so", RTLD_NOW | RTLD_GLOBAL);
However, bionic does not respect the RTLD_GLOBAL flag, and the dri
library cannot find symbols in libglapi.so, so we need to link
to libglapi.so explicitly. Android.mk already does this.
Cc: "12.0" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Tomasz Figa <tfiga@chromium.org>
Signed-off-by: Nicolas Boichat <drinkcat@chromium.org>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Emil Velikov [Mon, 18 Jul 2016 18:28:09 +0000 (19:28 +0100)]
mesa: scons: remove left over src/glsl include
The path no longer exists.
Signed-off-by: Emil Velikov <emil.velikov@collabora.com>
Emil Velikov [Mon, 18 Jul 2016 18:23:02 +0000 (19:23 +0100)]
mesa: scons: list builddir before srcdir
Analogous to previous commit.
Note: scons always uses OOT builds, while the in-tree generated files
could be created either manually or by the autoconf build.
Cc: "11.2 12.0" <mesa-stable@lists.freedesktop.org>
Cc: Alexander von Gluck IV <kallisti5@unixzen.com>
Signed-off-by: Emil Velikov <emil.velikov@collabora.com>
Emil Velikov [Mon, 18 Jul 2016 18:12:17 +0000 (19:12 +0100)]
mesa: automake: list builddir before srcdir
In the case of building in out-of-tree fashion, while having generated
in-tree sources, the latter [likely stale] files will be used.
Flip the order to prevent that.
Cc: "11.2 12.0" <mesa-stable@lists.freedesktop.org>
Signed-off-by: Emil Velikov <emil.velikov@collabora.com>
Józef Kucia [Tue, 19 Jul 2016 11:07:26 +0000 (13:07 +0200)]
radeonsi: advertise 8 bits subpixel precision for viewport bounds
Signed-off-by: Józef Kucia <joseph.kucia@gmail.com>
Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Józef Kucia [Tue, 19 Jul 2016 11:07:25 +0000 (13:07 +0200)]
r600: advertise 8 bits subpixel precision for viewport bounds
Signed-off-by: Józef Kucia <joseph.kucia@gmail.com>
Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Józef Kucia [Tue, 19 Jul 2016 11:07:24 +0000 (13:07 +0200)]
gallium: add a cap for VIEWPORT_SUBPIXEL_BITS (v2)
This allows Gallium drivers to advertise the subpixel precision
for floating point viewports bounds.
v2:
- Set ViewportSubpixelBits in st_init_limits.
Signed-off-by: Józef Kucia <joseph.kucia@gmail.com>
Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Samuel Pitoiset [Tue, 5 Jul 2016 20:43:14 +0000 (22:43 +0200)]
nvc0: disable MS images on GM107+
MS images have to be handled explicitly and I don't plan to implement
them for now.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Samuel Pitoiset [Mon, 4 Jul 2016 23:53:56 +0000 (01:53 +0200)]
nv50/ir: print OP_SUREDB subops in debug mode
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Samuel Pitoiset [Fri, 24 Jun 2016 20:35:59 +0000 (22:35 +0200)]
gm107/ir: add emission for SUREDx
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Samuel Pitoiset [Fri, 24 Jun 2016 20:34:52 +0000 (22:34 +0200)]
gm107/ir: add emission for SUSTx and SULDx
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Samuel Pitoiset [Thu, 19 May 2016 09:59:25 +0000 (11:59 +0200)]
gm107/ra: fix constraints for surface operations
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Samuel Pitoiset [Tue, 10 May 2016 10:50:07 +0000 (12:50 +0200)]
gm107/ir: lower surface operations
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Samuel Pitoiset [Mon, 4 Jul 2016 17:15:02 +0000 (19:15 +0200)]
nvc0: bind images for 3d/cp shaders on GM107+
On Maxwell, images binding is slightly different (and much better)
regarding Fermi and Kepler because a texture view needs to be uploaded
for each image and this is going to simplify the thing a lot.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Samuel Pitoiset [Sun, 26 Jun 2016 00:00:40 +0000 (02:00 +0200)]
nvc0: increase the tex handles area size in the driver cb
Currently, we can store 32 tex handles of 32-bits integer each and
that fits perfectly with the underlying hardware except on GM107+
which requires to upload a texture view for each images.
This patch increases the number of storable texture handles in the
driver constant buffer from 32 to 40 because we expose 8 images.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Kenneth Graunke [Tue, 19 Jul 2016 05:42:44 +0000 (22:42 -0700)]
nir: Fix uninitialized use of 'replacement'.
For intrinsics we don't care about, just skip to the next loop iteration
and process the next instruction. We don't want to execute the rest of
the code.
This was a bug in commit
cdfc05ea6e8c87876cdbf588aa8e03d70f3da4bb.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Anuj Phogat <anuj.phogat@gmail.com>
Kenneth Graunke [Mon, 18 Jul 2016 23:55:28 +0000 (16:55 -0700)]
i965: Use tex_mocs instead of rb_mocs for GL images.
Fixes a 10-20% performance regression in OglCSDof caused by commit
5a8c89038abab0184ea72664ab390ec6ca58b4d6, which made images (in the
image load/store sense) use BDW_MOCS_PTE instead of BDW_MOCS_WB.
This seems sketchy, as the default PTE value is supposed to be
WB LLC eLLC, which is the same as our MOCS WB setting. It's only
supposed to change when using a surface for display, which won't
ever happen for images. Something may be wrong in the kernel...
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Marek Olšák [Sun, 17 Jul 2016 11:23:53 +0000 (13:23 +0200)]
winsys/amdgpu: use pb_cache buckets for fewer pb_cache misses
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Sun, 17 Jul 2016 11:23:53 +0000 (13:23 +0200)]
winsys/radeon: use pb_cache buckets for fewer pb_cache misses
This makes Bioshock Infinite with deferred flushing 2.2% faster.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Sat, 16 Jul 2016 23:27:08 +0000 (01:27 +0200)]
gallium/pb_cache: reduce the number of pointer dereferences
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Sat, 16 Jul 2016 22:53:55 +0000 (00:53 +0200)]
gallium/pb_cache: divide the cache into buckets for reducing cache misses
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Sun, 17 Jul 2016 09:59:40 +0000 (11:59 +0200)]
gallium/pb_cache: check parameters that are more likely to fail first
This makes Bioshock Infinite with deferred flushing 2% faster.
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Sat, 16 Jul 2016 11:41:54 +0000 (13:41 +0200)]
radeonsi: emit PS exports last
This effectively removes s_waitcnt instructions after FP16 exports.
Before:
v_cvt_pkrtz_f16_f32_e32 v0, v0, v1 ;
5E000300
v_cvt_pkrtz_f16_f32_e32 v1, v2, v3 ;
5E020702
exp 15, 0, 1, 0, 0, v0, v1, v0, v0 ;
F800040F 00000100
s_waitcnt expcnt(0) ;
BF8C0F0F
v_cvt_pkrtz_f16_f32_e32 v0, v4, v5 ;
5E000B04
v_cvt_pkrtz_f16_f32_e32 v1, v6, v7 ;
5E020F06
exp 15, 1, 1, 0, 0, v0, v1, v0, v0 ;
F800041F 00000100
s_waitcnt expcnt(0) ;
BF8C0F0F
v_cvt_pkrtz_f16_f32_e32 v0, v8, v9 ;
5E001308
v_cvt_pkrtz_f16_f32_e32 v1, v10, v11 ;
5E02170A
exp 15, 2, 1, 0, 0, v0, v1, v0, v0 ;
F800042F 00000100
s_waitcnt expcnt(0) ;
BF8C0F0F
v_cvt_pkrtz_f16_f32_e32 v0, v12, v13 ;
5E001B0C
v_cvt_pkrtz_f16_f32_e32 v1, v14, v15 ;
5E021F0E
exp 15, 3, 1, 1, 1, v0, v1, v0, v0 ;
F8001C3F 00000100
s_endpgm ;
BF810000
After:
v_cvt_pkrtz_f16_f32_e32 v0, v0, v1 ;
5E000300
v_cvt_pkrtz_f16_f32_e32 v1, v2, v3 ;
5E020702
v_cvt_pkrtz_f16_f32_e32 v2, v4, v5 ;
5E040B04
v_cvt_pkrtz_f16_f32_e32 v3, v6, v7 ;
5E060F06
exp 15, 0, 1, 0, 0, v0, v1, v0, v0 ;
F800040F 00000100
v_cvt_pkrtz_f16_f32_e32 v4, v8, v9 ;
5E081308
v_cvt_pkrtz_f16_f32_e32 v5, v10, v11 ;
5E0A170A
exp 15, 1, 1, 0, 0, v2, v3, v0, v0 ;
F800041F 00000302
v_cvt_pkrtz_f16_f32_e32 v6, v12, v13 ;
5E0C1B0C
v_cvt_pkrtz_f16_f32_e32 v7, v14, v15 ;
5E0E1F0E
exp 15, 2, 1, 0, 0, v4, v5, v0, v0 ;
F800042F 00000504
exp 15, 3, 1, 1, 1, v6, v7, v0, v0 ;
F8001C3F 00000706
s_endpgm ;
BF810000
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Wed, 13 Jul 2016 20:34:54 +0000 (22:34 +0200)]
radeonsi: set optimal settings in COMPUTE_RESOURCE_LIMITS
ported from Vulkan
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Fri, 15 Jul 2016 14:04:03 +0000 (16:04 +0200)]
radeonsi: really wait for the second EOP event and not the first one
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Marek Olšák [Thu, 14 Jul 2016 23:15:42 +0000 (01:15 +0200)]
gallium/radeon: remove RADEON_FLUSH_KEEP_TILING_FLAGS flag
always set
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Ian Romanick [Mon, 27 Jun 2016 18:38:15 +0000 (11:38 -0700)]
nir/algebraic: Optimize fabs(u2f(x))
I noticed this when I tried to do frexp(float(some_unsigned)) in the
ir_unop_find_lsb lowering pass. The code generated for frexp() uses
fabs, and this resulted in an extra instruction. Ultimately I ended up
not using frexp.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Fri, 24 Jun 2016 08:58:18 +0000 (01:58 -0700)]
st/mesa: Enable MESA_shader_integer_functions on all GLSL 1.30 platforms
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Thu, 23 Jun 2016 23:19:45 +0000 (16:19 -0700)]
i965: Enable MESA_shader_integer_functions on all GLSL 1.30 platforms
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Thu, 9 Jun 2016 23:35:30 +0000 (16:35 -0700)]
i965: Don't lower uaddCarry and usubBorrow in both GLSL IR and NIR
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Tue, 28 Jun 2016 21:48:22 +0000 (14:48 -0700)]
i965: Update assertion to account for Gen < 7
Previously SHADER_OPCODE_MULH could only exist on Gen7+, so the
assertion assumed the Gen7+ accumulator rules. A future patch will
allow this instruction on at least Gen6, so update the assertion.
v2: Use get_lowered_simd_width instead of open coding it. Suggested by
Curro.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com> [v1]
Ian Romanick [Wed, 22 Jun 2016 20:12:26 +0000 (13:12 -0700)]
i965: Use LZD to implement nir_op_find_lsb on Gen < 7
v2: Rebase on changes to previous two patches.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Wed, 22 Jun 2016 00:18:04 +0000 (17:18 -0700)]
i965: Use LZD to implement nir_op_ifind_msb on Gen < 7
v2: Retype LZD source as UD to avoid potential problems with 0x80000000.
Suggested by Matt. Also update comment about problem values with
LZD(abs(x)). Suggested by Curro.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Tue, 21 Jun 2016 22:14:03 +0000 (15:14 -0700)]
i965: Use LZD to implement nir_op_ufind_msb
This uses one less instruction.
v2: Move emit_find_msb_using_lzd out of the visitor classes. Suggested
by Curro.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Tue, 21 Jun 2016 18:14:58 +0000 (11:14 -0700)]
i965: Always enable GL_ARB_shading_language_packing
With the existing lowering passes, the functions from this extension
become a bunch of bit twiddling operations that have always been
supported.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Tue, 21 Jun 2016 17:56:23 +0000 (10:56 -0700)]
i965: Move enable of EXT_shader_integer_mix
This extension does not depend on the Gen. It only depends on the
availability of GLSL 1.30.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Mon, 27 Jun 2016 22:21:21 +0000 (15:21 -0700)]
glsl: Add lowering pass for ir_bin_imul_high
This isn't the lowering pass you want. Most GPUs that can support GLSL
1.30 have a multiply unit that can do something more interesting than
32x32->32. Many have 32x16->48. Any GPU that does, should do the
lowering in the backend. This is just the thing that will always work.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Fri, 24 Jun 2016 08:53:33 +0000 (01:53 -0700)]
glsl: Add lowering pass for ir_unop_find_msb
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Fri, 24 Jun 2016 08:17:23 +0000 (01:17 -0700)]
glsl: Add lowering pass for ir_unop_find_lsb
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Fri, 24 Jun 2016 07:11:26 +0000 (00:11 -0700)]
glsl: Add lowering pass for ir_unop_bitfield_reverse
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Fri, 24 Jun 2016 06:16:10 +0000 (23:16 -0700)]
glsl: Add lowering pass for ir_quadop_bitfield_insert
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Thu, 23 Jun 2016 23:57:23 +0000 (16:57 -0700)]
glsl: Add lowering pass for ir_triop_bitfield_extract
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Thu, 23 Jun 2016 23:16:21 +0000 (16:16 -0700)]
glsl: Add lowering pass for ir_unop_bit_count
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Tue, 21 Jun 2016 17:29:49 +0000 (10:29 -0700)]
MESA_shader_integer_functions: Allow new function overload matching rules
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Tue, 21 Jun 2016 17:26:34 +0000 (10:26 -0700)]
MESA_shader_integer_functions: Allow implicit int->uint conversions
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Tue, 21 Jun 2016 17:21:47 +0000 (10:21 -0700)]
MESA_shader_integer_functions: Expose new built-in functions
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Mon, 20 Jun 2016 23:35:32 +0000 (16:35 -0700)]
MESA_shader_integer_functions: Boiler plate extension tracking
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Ian Romanick [Mon, 20 Jun 2016 23:28:34 +0000 (16:28 -0700)]
MESA_shader_integer_functions: Add extension specification
v2: Fix typo in #extension line noticed by Ken.
v3: Update spec status.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Samuel Pitoiset [Tue, 19 Jul 2016 12:47:57 +0000 (14:47 +0200)]
gm107/ir: make use of ADD32I for all immediates
ADD only allows to emit 19-bits immediates.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: <mesa-stable@lists.freedesktop.org>
Samuel Pitoiset [Tue, 19 Jul 2016 12:47:56 +0000 (14:47 +0200)]
gm107/ir: add missing NEG modifier for IADD32I
Like FADD32I, the NEG modifier of src0 is at position 56.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: mesa-stable@lists.freedesktop.org
Andreas Boll [Tue, 19 Jul 2016 10:43:38 +0000 (12:43 +0200)]
ddebug: Fix trivial typo in stderr message
Signed-off-by: Andreas Boll <andreas.boll.dev@gmail.com>
Andreas Boll [Tue, 19 Jul 2016 10:30:40 +0000 (12:30 +0200)]
configure.ac: Use ${datarootdir} for --with-vulkan-icddir help string too
The help string wasn't updated in
cbc37f7.
Fixes: cbc37f7 ("anv: install the intel_icd.json to ${datarootdir} by
default")
Signed-off-by: Andreas Boll <andreas.boll.dev@gmail.com>
Reviewed-by: Eric Engestrom <eric.engestrom@imgtec.com>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Cc: mesa-stable@lists.freedesktop.org
Eric Engestrom [Wed, 13 Jul 2016 21:50:54 +0000 (22:50 +0100)]
vl: fix memory leak
CovID:
1363008
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Nayan Deshmukh <nayan26deshmukh@gmail.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Boyuan Zhang [Mon, 18 Jul 2016 22:43:37 +0000 (18:43 -0400)]
vl: add entry point
Add entrypoint to distinguish H.264 decode and encode. For example, in patch
5/11 when is calling "VaCreateContext", "pps" and "sps" shouldn't be allocated
for H.264 encoding. So we need to use the entry_point to determine this is
H.264 decode or H.264 encode. We can use config to determine the entrypoint
since config_id is passed to us for VaCreateContext call. However, for
VaDestoyContext call, only context_id is passed to us. So we need to know the
entrypoint in order to not free the pps/sps for encoding case.
Signed-off-by: Boyuan Zhang <boyuan.zhang@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Ilia Mirkin [Sun, 17 Jul 2016 21:14:24 +0000 (17:14 -0400)]
nv50,nvc0: srgb rendering is only available for rgba/bgra
Mark both L8_SRGB and L8A8_SRGB as non-renderable (the latter already
didn't have the bind flags). This makes the state tracker pick a
different format when rendering is required, or mark the fb as
incomplete. This fixes:
bin/getteximage-formats init-by-clear-and-render -auto -fbo
bin/getteximage-formats init-by-rendering -auto -fbo
which previously ran into srgb-encoding differences.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Cc: mesa-stable@lists.freedesktop.org
Ilia Mirkin [Sat, 16 Jul 2016 19:07:21 +0000 (15:07 -0400)]
nvc0: add support for BGRA8 images
This is useful for pbo downloads, which are now accelerated with images.
BGRA8 is a moderately common format to do that in.
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Jason Ekstrand [Mon, 18 Jul 2016 16:13:01 +0000 (09:13 -0700)]
i965: Skip update_texture_surface when the plane doesn't exist
Thanks to rebase fail, recent surface state changes (commits
7e951cd56,
8521ce1a7, and
69c0dc5c53) effectively reverted
727a9b24933 and
367cf3a2e3e
which was unintentional. This should bring it back.
Signed-off-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Timothy Arceri [Mon, 11 Jul 2016 02:11:42 +0000 (12:11 +1000)]
glsl: use linked shaders rather than compiled shaders
At this point there is no reason not to be using the linked shaders,
using the linked shaders should be faster and will make things simpler
for upcoming shader cache work.
The previous variable name suggests the linked shaders were intended
to be used here anyway.
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Lars Hamre [Mon, 18 Jul 2016 23:20:27 +0000 (01:20 +0200)]
The extension is already exposed, this simply marks it as done.
Signed-off-by: Lars Hamre <chemecse@gmail.com>
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Anuj Phogat [Mon, 18 Jul 2016 22:53:24 +0000 (15:53 -0700)]
docs: Fix typo in extension name
Signed-off-by: Anuj Phogat <anuj.phogat@gmail.com>
Anuj Phogat [Mon, 18 Jul 2016 22:42:18 +0000 (15:42 -0700)]
docs: Add support for GL_KHR_texture_compression_astc_sliced_3d
Signed-off-by: Anuj Phogat <anuj.phogat@gmail.com>
Reported-by: Ilia Mirkin <imirkin@alum.mit.edu>
Anuj Phogat [Mon, 18 Jul 2016 22:17:53 +0000 (15:17 -0700)]
Revert "docs: Mark KHR_texture_compression_astc_sliced_3d done on i965"
This reverts commit
82f8c239506ef126dcad266156f8945c62dc6bc9.
KHR_texture_compression_astc_sliced_3d is not a requirement for
GLES 3.2.
Reported-by: Ilia Mirkin <imirkin@alum.mit.edu>\
Signed-off-by: Anuj Phogat <anuj.phogat@gmail.com>
Anuj Phogat [Fri, 8 Jul 2016 00:05:02 +0000 (17:05 -0700)]
docs: Mark KHR_texture_compression_astc_sliced_3d done on i965
Signed-off-by: Anuj Phogat <anuj.phogat@gmail.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Anuj Phogat [Fri, 8 Jul 2016 00:04:17 +0000 (17:04 -0700)]
i965/gen9: Enable KHR_texture_compression_astc_sliced_3d
Signed-off-by: Anuj Phogat <anuj.phogat@gmail.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Anuj Phogat [Fri, 8 Jul 2016 00:03:19 +0000 (17:03 -0700)]
mesa: Add the infrastructure for KHR_texture_compression_astc_sliced_3d
V2: Drop the changes to gl.xml.
Signed-off-by: Anuj Phogat <anuj.phogat@gmail.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Christian König [Thu, 7 Jul 2016 12:28:06 +0000 (14:28 +0200)]
radeon/uvd: add session context buffer for polaris 10/11 v2
This way we have unlimited UVD sessions.
v2: only enable it when kernel supports it as well.
Signed-off-by: Christian König <christian.koenig@amd.com>
Reviewed-by: Leo Liu <leo.liu@amd.com>
Leo Liu [Thu, 14 Jul 2016 13:19:59 +0000 (09:19 -0400)]
vl/dri3: fix a memory leak from front buffer
Inspired by fix for mem leak of vdpau interop, resource_from_handle
set texture reference count, that need to be decreased and released,
recall there is a similar case for DRI3, that is with VA-API glx
extension, there is temporary TFP(texture from pixmap), we target it
through dma-buf. leak happens when without count down the reference.
Checked and found with mpv vo=opengl case, there only one static TFP,
the leak happens once, but for totem player using gstreamer VA-API glx,
the dynamic TFP for each frame, so leak quite a bit.
This fixes mem leak for mpv and totem.
Signed-off-by: Leo Liu <leo.liu@amd.com>
Cc: "12.0" <mesa-stable@lists.freedesktop.org>
Iago Toral Quiroga [Fri, 15 Jul 2016 08:55:05 +0000 (10:55 +0200)]
i965/tes/scalar: fix 64-bit indirect input loads
We totally ignored this before because there were no piglit tests for
indirect loads in tessellation stages with doubles.
Reviewed-by: Timothy Arceri <timothy.arceri@collabora.com>
Iago Toral Quiroga [Fri, 15 Jul 2016 08:48:03 +0000 (10:48 +0200)]
i965/tcs/scalar: only update imm_offset for second message in 64bit input loads
Our indirect URB read messages take both a direct and an indirect offset
so when we emit the second message for a 64-bit input load we can just
always incremement the immediate offset, even for the indirect case.
Reviewed-by: Timothy Arceri <timothy.arceri@collabora.com>
Kenneth Graunke [Thu, 14 Jul 2016 03:16:11 +0000 (20:16 -0700)]
i965: Move pulls_bary setting to emit_pixel_interpolator_send().
pulls_bary should be set when the shader uses a pixel interpolator
message. So, setting it from the function that emits pixel interpolator
messages makes a lot of sense.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Timothy Arceri <timothy.arceri@collabora.com>