on sm70+ where we don't have a native bfe instruction. This
implementation is fewer instructions than the nir lowering.
This also implements the bfe semantics that vkd3d-proton wants. d3d12
wants specific behavior for out-of-bounds ibfe like
bitfieldExtract(-1, 15, 20) while spirv considers this undefined
behavior. Tested with VKD3D_TEST_FILTER=test_shader_instructions
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/13795
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37592>
In case of a unbound subchannel usage, the hardware will route it to the
GPFIFO class.
NVIDIA blobs use this and this was causing an assertion to be fired up
in nv_push_dump.
This adds support for that and also add mapping for cls_gpfifo in
nv_push_dump.
Signed-off-by: Mary Guillemard <mary@mary.zone>
Reviewed-by: Mel Henning <mhenning@darkrefraction.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37475>
Note that this changes the output so it lists the method as being in the
class where it most recently changed rather than always in the class of
the running gpu. Personally, I find this more useful than the old
behavior.
Reviewed-by: Mary Guillemard <mary@mary.zone>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37475>
Customers suggested that Xe KMD should change all possible interfaces
visible to users to canonical address, with that we need some changes
to keep the decode of devcoredump working.
A old version of the tool will not be able to decode secondary batch
buffers when parsing a new version of the file but the new version of
this tool will be able to parse both versions of devcoredump file.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37570>
Labels set via VK_EXT_debug_utils are in a separate track due to the
following part of the spec:
"An application may open a debug label region in one command buffer and
close it in another, or otherwise split debug label regions across
multiple command buffers or multiple queue submissions."
This means labels can start in one renderpass and end in another command
buffer, which breaks our assumption that stages can be modeled as a stack.
While applications aren't expected to use labels in such extreme ways,
even simpler cases can break our assumptions.
Having annotations in a separate track prevents the main track(s) from
entering an invalid state.
Signed-off-by: Danylo Piliaiev <dpiliaiev@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37028>
Using NaN doesn't usually allow any extra optimizations, and 0 is an inline
constant on AMD hw where this opcode is used with undef for fragment shader
exports.
Foz-DB GFX1201:
Totals from 889 (1.11% of 80287) affected shaders:
Instrs: 1676365 -> 1676348 (-0.00%)
CodeSize: 8827040 -> 8821760 (-0.06%)
Latency: 13346728 -> 13346699 (-0.00%)
InvThroughput: 1799283 -> 1799262 (-0.00%)
Copies: 108125 -> 108102 (-0.02%)
VALU: 974875 -> 974852 (-0.00%)
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37552>
There are too many reports of instability in the wild,
even in scenarios where anti-lag isn't really being actively used,
making it questionable to load the layer by default.
By using enable_environment, a certain environment variable
must be set for loader to consider loading the layer.
This could be removed once the layer stabilizes.
Cc: mesa-stable
Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37509>
This reduces duplication: we only need to distinguish between Windows
and Unix in one place.
The previous code was inconsistent about using either the `platforms`
option, or the `host_machine`. Following the logic described in
commit 94379377 "lavapipe: build "Windows" check should use the host machine, not the `platforms` option.",
I've assumed that checking the host machine is the more-correct version
and used that.
Signed-off-by: Simon McVittie <smcv@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37576>
This consistently uses `NAME.dll` on Windows, `libNAME.dylib` on Darwin
derivatives such as macOS, and `libNAME.so` on Linux, *BSD and so on.
It's also consistent about using the local variable name `icd_file_name`
for this name in every Vulkan driver, which was already the case in many
but not all drivers.
Some of these drivers probably don't make sense (or don't work) on
Windows and/or macOS, but if this is kept consistent for all drivers,
it should avoid the need for driver-specific commits like
commit 611e9f29e "lavapipe: fix icd generation for windows",
commit 951f3287 "lavapipe: set empty dll prefix",
commit 13e7a39f "lavapipe: fixes for macOS support",
commit 7008e655 "radv: Update JSON generator if Windows" and so on,
each time a driver is found to be relevant on more platforms than
previously believed.
Signed-off-by: Simon McVittie <smcv@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37576>
The hardware support for stencil texturing is unclear from RE and
the feature databases. Enable this extension on halti5 GPUs as a
conservative starting point.
This also enables ARB_texture_stencil8.
Passes:
- dEQP-GLES31.functional.stencil_texturing.format.stencil_index8*
- dEQP-GLES31.functional.stencil_texturing.format.depth24_*
- arb_texture_stencil8 piglit
- arb_stencil_texture piglit
Signed-off-by: Christian Gmeiner <cgmeiner@igalia.com>
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/37578>
