Replace use of x86 intrinsic with general llvm IR instruction.
Generates the same final assembly.
Reviewed-by: Bruce Cherniak <bruce.cherniak@intel.com>
Add BASE_NUMA_NODE, BASE_CORE, BASE_THREAD parameters to
SwrCreateContext.
Add optional SWR_API_THREADING_INFO parameter to SwrCreateContext to
control reservation of API threads.
Add SwrBindApiThread() function to allow binding of API threads to
reserved HW threads.
Reviewed-by: Bruce Cherniak <bruce.cherniak@intel.com>
Since we have HW contexts on gen4/5, we could take advantage of them, as
done for gen6+ in commit e32cd5ffbb ("i965: Rely on hardware contexts
for query objects on Gen6+."), to only emit a pair of counters at
begin/end queryobj, rather than around every primitive. However, to keep
queryobj working in the meantime as we bringup support for HW ctx on
gen4/5, we can keep using the existing code.
References: e32cd5ffbb ("i965: Rely on hardware contexts for query objects on Gen6+.")
Cc: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Add a new helper that drivers can use to emulate various things that
need special handling in particular in transfer_map:
1) z32_s8x24.. gl/gallium treats this as a single buffer with depth
and stencil interleaved but hardware frequently treats this as
separate z32 and s8 buffers. Special pack/unpack handling is
needed in transfer_map/unmap to pack/unpack the exposed buffer
2) fake RGTC.. GPUs designed with GLES in mind, but which can other-
wise do GL3, if native RGTC is not supported it can be emulated
by converting to uncompressed internally, but needs pack/unpack
in transfer_map/unmap
3) MSAA resolves in the transfer_map() case
v2: add MSAA resolve based on Eric's "gallium: Add helpers for MSAA
resolves in pipe_transfer_map()/unmap()." patch; avoid wrapping
pipe_resource, to make it possible for drivers to use both this
and threaded_context.
Signed-off-by: Rob Clark <robdclark@gmail.com>
Following dEQP cases pass:
dEQP-EGL.functional.get_proc_address.extension.gl_ext_disjoint_timer_query
dEQP-EGL.functional.client_extensions.disjoint
Piglit test 'ext_disjoint_timer_query-simple' passes with these changes.
No changes/regression observed in Intel CI.
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Patch adds GL_GPU_DISJOINT_EXT and enables to use timer queries when
EXT_disjoint_timer_query is enabled.
v2: enable extension only when EXT_disjoint_timer_query set
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> (v1)
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Most entrypoints already available via other extensions like
GL_EXT_occlusion_query_boolean, GL_EXT_timer_query.
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
This state will be used by EXT_disjoint_timer_query. As first
usage, patch sets DisjointOperation true when gpu reset happens.
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Fixes almost all of piglit's arb_shader_texture_lod grad tests, except for
the base -texgrad/texgradcube ones which fail on what appear to be
precision problems.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
We want the clamping of the coordinate to apply after the offset, so we
need to do math to lower the offset out of the instruction. Fixes texwrap
offset cases for GL_CLAMP with GL_NEAREST on vc5.
Note: I moved the get_texture_size() verbatim, so that it was defined
before use.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
The spec says the missing texel (when we wrap around both x and y axis)
should be synthesized as the average of the 3 other texels. For bilinear
filtering however we instead adjusted the filter weights (because, while
the complexity looks similar, there would be 4 times as many color values
to fix up than weights). Obviously this could not work for gather (hence
accurate corner filtering was disabled with gather).
Implement this by just doing it as the spec implies - calculate the 4th
texel as the average of the other 3. With gather of course there's only
one color to worry about, so it's not all that many instructions neither
(albeit surely the whole cube map filtering is hilariously complex).
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Cube texture wrapping is a bit special since the values (post face
projection) always are within [0,1], so we took advantage of that and
omitted some clamps.
However, we can still get NaNs (either because the coords already had NaNs,
or the face projection generated them), and in fact we didn't handle them
quite safely. I've seen -INT_MAX + 1 been propagated through as the final int
coord value, albeit I didn't observe a crash. (Not quite a coincidence, since
any stride mul with -INT_MAX or -INT_MAX+1 will turn up as a small positive
number - nevertheless, I'd rather not try my luck, I'm not entirely sure it
can't really turn up negative neither due to seamless coord swapping, plus
ifloor of a NaN is not guaranteed to return -INT_MAX by any standard. And
we kill off NaNs similarly with ordinary texture wrapping too.)
So kill off the NaNs by using the common max against zero method.
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Jose Fonseca <jfonseca@vmware.com>
Unfortunately, in aubinator and aubinator_error_decode we don't always
know how many of a given state we have, so we must guess. One day,
we'll come up with a way to annotate the batch to solve this problem.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
The shared framework can now do everything that aubinator_error_decode
ever did and more. It's time to make the switch.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Previously, if a group was nested in another group such that it didn't
start on a dword boundary, we would decode it as if it started at the
start of its first dword. This changes things to work even more in
terms of bits so that we can properly decode these structs. This
affects MOCS, attribute swizzles, and several other things.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>