look at what the program actually does instead of hardcoding a worst-case.
SIMD16:
Totals from 1965 (74.23% of 2647) affected shaders:
Instrs: 2603230 -> 2539932 (-2.43%); split: -3.44%, +1.01%
CodeSize: 38826160 -> 37811904 (-2.61%); split: -3.59%, +0.97%
Number of spill instructions: 1206 -> 555 (-53.98%)
Number of fill instructions: 1194 -> 551 (-53.85%)
SIMD32:
Totals from 1974 (74.57% of 2647) affected shaders:
Instrs: 3998126 -> 3033333 (-24.13%); split: -24.18%, +0.05%
CodeSize: 59563952 -> 45580448 (-23.48%); split: -23.52%, +0.05%
Number of spill instructions: 43534 -> 37471 (-13.93%); split: -13.97%, +0.04%
Number of fill instructions: 43118 -> 36412 (-15.55%)
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41872>
These queries need to be used for partitioning too. And also this degunks the
core RA logic in jay_register_allocate.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41872>
panvk previously reported DRM format modifiers only through
VkDrmFormatModifierPropertiesListEXT.
Report them through VkDrmFormatModifierPropertiesList2EXT as well.
Cc: mesa-stable
Signed-off-by: Gyeyoung Baek <gye976@gmail.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41772>
VkFormatProperties uses VkFormatFeatureFlags, whose valid bits are limited to
VK_ALL_FORMAT_FEATURE_FLAG_BITS (0x7fffffffu).
Without this mask, the last bit leaks out.
Use vk_format_features2_to_features() helper when filling VkFormatProperties so
flags2-only bits are not leaked through legacy feature fields.
Cc: mesa-stable
Signed-off-by: Gyeyoung Baek <gye976@gmail.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41772>
This test has been marked as flaking on G925, but I've also seen it
flaking on G610 recently. Let's just move it to the common flake-file
instead. Also drop it from the fails-file on G925, as having it in both
isn't really needed.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40398>
This only fails sometimes, and it doesn't seem to take the whole system
down with it. Let's mark it as a flake instead of skipping it.
Acked-by: Eric R. Smith <eric.smith@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40398>
Skips accumulate over time, but rarely gets reevaluated to see if
they're still relevant. To combat this problem, I've dropped all skips,
and added back those that actually serve a practical use.
The result might be a bit more instability in the short term. But
hopefully this pays off in the long term.
Acked-by: Eric R. Smith <eric.smith@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40398>
These are known fails due to CTS bugs. Patches are on the way. Let's
skip them, like we do with the other ones in the same category.
Acked-by: Eric R. Smith <eric.smith@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40398>
When zink translates glCopySubImageData with a 2d image view of a 3d
image as the destination to a draw call the shader generated for the
load-op was not handling things correctly leading to the wrong
z-slice been loaded.
The fix is to mark which attachments within the load op are 2d image
views of a 3d image then when generating the load-op shader covert
the sample to 3d sample and update the coords to load the required
z-slice value from the tex meta data.
Fix for dEQP-GLES31.functional.copy_image.non_compressed.*_to_texture3d
Fixes: 7b28b6c43d ("pvr, pco: implement VK_EXT_image_2d_view_of_3d")
Signed-off-by: Nick Hamilton <nick.hamilton@imgtec.com>
Reviewed-by: Luigi Santivetti <luigi.santivetti@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41955>
With a decode-only build, the si_init_gfx_context is stubbed and returns
false, which causes si_create_context to fail when a decoder is created
(since si_dec_init_decode sets the PIPE_CONTEXT_COMPUTE_ONLY flag).
With this change, the stubbed si_init_gfx_context function returns true,
which allows si_create_context to continue, and a decoder to be
successfully created.
Signed-off-by: Thong Thai <thong.thai@amd.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41973>
Since shader support is not built when with_gfx_compute is false, libelf
is not needed.
Signed-off-by: Thong Thai <thong.thai@amd.com>
Reviewed-by: Marek Olšák <maraeo@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41973>
The fragment state is stored just before ZS_CRC_EXTENSION, so move the
pointer accordingly.
Fixes: af35fc44a7 ("pan/desc: Implement pan_emit_fbd for v14+")
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Reviewed-by: Lars-Ivar Hesselberg Simonsen <lars-ivar.simonsen@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41643>
Implement the v14+ paths needed to copy IR framebuffer layer state and
re-emit it from the tiler OOM exception handler.
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Reviewed-by: Lars-Ivar Hesselberg Simonsen <lars-ivar.simonsen@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41643>
Postpone emitting the fragment layer state in the fragment job issue path
until just before RUN_FRAGMENT2 is emitted.
This state is loaded from FBD_POINTER which might change due to IR.
Therefore, postponing is required.
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Reviewed-by: Lars-Ivar Hesselberg Simonsen <lars-ivar.simonsen@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41643>
The cs_builder.h helper that records RUN_FRAGMENT[2] also records a flush,
so there's no need for flushing again before calling it.
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Reviewed-by: Lars-Ivar Hesselberg Simonsen <lars-ivar.simonsen@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41643>
This is implemented in common code in d8ef386f98 ("vulkan: add support
for VK_KHR_internally_synchronized_queues").
Passes dEQP-VK.synchronization2.internally_synchronized_queues.*
Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41926>
This will be used for CmdDrawByteCountIndirect on v13, which requires
dividing the byte count by the vertex stride to get the number of
vertices in the draw.
Signed-off-by: Olivia Lee <olivia.lee@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41655>
All we really need for udiv32 is a 32x32->64 multiply, but the most
efficient way to implement that is to move the 32-bit reg into a 64-bit
reg anyway. So, I figured it simpler to just have the caller do that
than passing a scratch reg into the helper.
Signed-off-by: Olivia Lee <olivia.lee@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41655>
v13 adds some register add/sub instructions, and I'd like to use
cs_{add,sub}{32,64} for those to match the naming convention for other
reg/reg instructions. So the existing immediate functions are renamed to
cs_add_imm{32,64}, matching the name of the actual instruction.
Signed-off-by: Olivia Lee <olivia.lee@collabora.com>
Reviewed-by: Christoph Pillmayer <christoph.pillmayer@arm.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41655>
Not sure if any workload uses this. This mostly allows us to document
the functionality of HSD 22011236099 on gfx20+.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41712>
These platforms don't support CCS on MCS/HIZ/STC. There's nothing we can
do about this. So, stop warning about it.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/41712>
