Add memcpy function to convert linear data to Tile 4 format.
Tile 4 format consists of 4KB block divided into chunks of 512B.
Each 512B chunk/block is comprised of 8 64B blocks arranged in
Y-tile format.
Signed-off-by: Aditya Swarup <aditya.swarup@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13391>
Add unittests for linear to tiled and tiled to linear texture
conversions for Ytile. The test prints the source/output buffer
in hex format with debug flags to verify the result.
Linear to tile conversion fills the linear buffer with values
based on the OWORD index number i.e., OWORD3 will contain
all values filled as 0x03 and
OWORD3 = 0x03030303030303030303030303030303.
The Y-tile to Linear tile conversion uses a similar logic to place
the tiled values in a manner that will result in a linear buffer with
OWORDs filled according to index number as mentioned above.
Signed-off-by: Aditya Swarup <aditya.swarup@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13391>
Until someone does the work to eliminate faults, PanVK will be inherently flaky
and should not be in CI. deqp-runner can eat a lot of flakes, and then retrying
the whole job eats more flakes, but neither is a substitute for not testing
known broken (and hence flaky) code and both increase runtime unacceptably. the
g52-vk job earned 2 spots on the latest leaderboard for slowest jobs, I clicked
on https://gitlab.freedesktop.org/mesa/mesa/-/jobs/48142375 to see a jawdropping
54 flakes reported by deqp-runner.
If people insist on keeping the job, then panfrost-g52-vk needs to be demoted to
manual until after someone fixes all these bugs on the driver side. If that's
not going to happen, then there's no point in it being in CI at all. It's broken
code. After a buggy MR, it'll still be broken code. CI doesn't matter if we're
ok with it being broken.
Bottom line is, we can't be running known broken code in CI (bugs = faults =
flakes = unhappy developers), at least for non-robust stacks (panfrost.ko
included). This needs to be policy if it isn't already. Merging this single
character change deals with the hot problem without any fanfare or adverse
effects.
This turns the job into a nightly as David suggested to get it out of the
premerge path until someone is committed to supporting it and does the work to
make it happen.
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/9721
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Acked-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24943>
We kept those tilings disabled up to know. Now that ISL has proper
support for them, remove this.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23620>
Ys & Yf are both implemented in ISL now, we still have some Yf issues
to investigate. Instead of disabling them in ISL, we disable them in
the two drivers.
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23620>
The data in Ys/Yf/Tile64 tiled images is arranged differently for 2D &
3D images. Therefore we cannot assume that we will use 2D images for
blits/copies.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23620>
A number of CTS tests are failing, like :
dEQP-VK.ycbcr.format.b8g8r8g8_422_unorm.vertex_optimal
Failures are reproduced on simulation.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23620>
This commit adds the code for choosing where to start the miptail and
enables miptails by default unless the client driver passes
info->min_miptail_start_level >= info->levels.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23620>
Since the input & output arguments can point to the same location in
memory, if you ever access the input after writing the output you're
in trouble.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23620>
This commit just adds a miptail start field to isl_surf and wires it up
in the RENDER_SURFACE_STATE and 3DSTATE_DEPTH code. We also add a
minimum miptail LOD so that client drivers have a knob to control the
miptails a bit.
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23620>
We're about to add separate code for Yf/Ys and this helps keep the diff
reasonable.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23620>
With these tilings, everything is aligned to a tile and the tiled
surface size calculations will handle the array stride for us. We need
to provide an accurate 4D size so that 3D and multisampled images get
tiled correctly.
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23620>
This makes things a tiny bit stickier in isl_calc_phys_total_extent_el
but will be worth it when we enable Yf and Ys.
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23620>
The ICL+ PRMs show that this is not a supported thing anymore for
Ys/Yf and there isn't really much use for it in Vulkan/Sparse.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23620>
The tile size calculations use a clever bit of math to make them short
and simple. We add unit tests to assert that they identically match the
tables in the PRM.
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23620>
The Yf and Ys tilings change a bit between SKL and later generations so
we have to be able to distinguish between them.
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23620>
Since this value is 0, it doesn't change anything, but it's just good
practice like we did for Gfx12.5 right above.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: Nanley Chery <nanley.g.chery@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23620>
