The way we handle spilling for fp64 in vec4 is to emit a series of MOVs
which swizzles the data around and then a pair of 32-bit spills. This
works great except that the next time we go to pick a spill reg, the
compiler isn't smart enough to figure out that the register has already
been spilled. Normally we do this by looking at the sources of spill
instructions (or destinations of fills) but, because it's separated from
the actual value by a MOV, we can't see it. This commit adds a new
opcode VEC4_OPCODE_MOV_FOR_SCRATCH which is identical to MOV in
semantics except that it lets RA know not to spill again.
Fixes: 82c69426a5 "i965/vec4: support basic spilling of 64-bit registers"
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10571>
The vec4 back-end can't push UBOs just yet but it soon will be able.
When it starts pushing UBOs, it will have a lower limit than scalar due
to a crummy register allocator. Mirror that limit in ANV so we don't
run into asserts due to ANV and the back-end making different choices.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10571>
This change adds a gallium D3D10 state tracker that works as a WDDM UMD
software driver, similar to Microsoft WARP, but using llvmpipe/softpipe.
The final deliverable is a d3d10sw.dll, which is similar to WARP's
d3d10warp.dll.
This has been used to run Microsoft Windows HCK wgf11* tests with
llvmpipe, and they were at one point passing 100%.
Known limitations:
- TGSI (no NIR)
- D3D10 only (no D3D11 support yet)
- no WINE integration (WINE doesn't implement WDDM DDI.)
For further details see:
- src/gallium/frontends/d3d10umd/README.md
- src/gallium/targets/d3d10sw/README.md
v2: Drop the DXBC-based disassembly. Add missing break statements.
v3: Incorporate Jesse's feedback.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Acked-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10687>
Another lavapipe leak found with LeakSanitizer.
This happens when using tessellation without geometry shader but with a
fragment shader that consumes primitive ID, therefore requiring
primitive assembler stage.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10835>
We've only enabled the extension on Gfx11+ so no need to care about
prior values.
Also fixup values of (min|max)FragmentShadingRateAttachmentTexelSize.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: 231651fd89 ("anv: implement VK_KHR_fragment_shading_rate")
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10607>
It seems this gives 2-3% improvements most of the time. This also
enables DCC for concurrent images.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10454>
Make use of some Chromebooks recently added to the Collabora LAVA lab to
test Panfrost on the G72 (Bifrost) GPU.
Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10785>
This version adds support for some Chromebooks with the MT8183 SoC that
we want to use to test Panfrost.
Signed-off-by: Tomeu Vizoso <tomeu.vizoso@collabora.com>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10785>
This prevents read buffer overflows in dup_vertex(), when draw stages
allocate extra shader outputs after the vertex buffers are allocated.
The original issue can be exercised with upcoming
piglit/tests/general/vertex-fallbacks.c test.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Cc: 21.0 21.1 <mesa-stable@lists.freedesktop.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10836>
Manually inline the functions, delete the duplicates, and use GenXML the
way it's meant to be used. Template structs should **never** cross
function boundaries.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10869>
The other part is |'d together. Do the happy path at compile time, and
reserve the draw time fixup for a v5 silicon issue.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10869>
These were already grouped nicely, just never got used. I also added
coverage writes to the list of reasons not to use early-z for
completeness. At the moment this doesn't do anything since this is a
Midgard flag and we haven't hooked up coverage writes on Midgard.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10869>
Now that we've moved everything but the blend shader up to the CSO, we
can just return a blend shader pointer (or zero to indicate the absence
thereof), and remove a source of name conflicts.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10869>
