When splitting a v6b vector into v1 and v2b components, we should ensure
the v1 definition doesn't start at the upper half.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4772>
Doom Eternal explicitly allows overallocation via this extension
but that shouldn't change anything because it's the default RADV
behavior.
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/4785>
By default, RADV supports overallocation by the sense that it doesn't
reject an allocation if the target heap is full.
With VK_AMD_overallocation_behaviour, apps can disable overallocation
and the driver should account for all allocations explicitly made by
the application, and reject if the heap is full.
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/4785>
The reason behind this is that FMASK requires CMASK and also that
FMASK for non color attachments looks unnecessary. It's currently
much easier to add this simple check because the driver tries to
always enable DCC first and if we enable FMASK only if CMASK, we
might loose some FMASK compressions.
This helps fixing some new robustness2 tests which fails because
only FMASK is enabled.
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/4783>
This would be necessary for an application to figure out if the
memory was allocated using a memory type with VK_MEMORY_PROPERTY_PROTECTED_BIT.
It also allows one to determine VRAM vs. GTT etc.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4751>
Lots of extra coding was involved in managing them.
And for protected memory I was thinking of making a function that
goes from domain+flags to memory types, which can reuse this array.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4751>
On APUs, the memory is unified (all heaps are equally fast) and
apps should count all memory heaps together. But some games like
Id Tech games (Youngblood and such) don't manage memory correctly
on APUs and they spill everything when one VRAM heap is full.
Instead of spilling buffers, they should just allocate new buffers
in the second heap but it seems like these games are confused if
two memory heaps have the DEVICE_LOCAL_BIT set.
This is probably a first step towards better memory management on
APUs but there is still some work to do if we want to run most apps
with a small dedicated VRAM (256MB or so).
This gives a huge boost for Id Tech games on APUs, and doesn't
seem to reduce Feral games performance.
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/4771>
Also reverse the BO list removal loop. This way typical WSI usage
should find the entry in O(active swapchains) iterations, which
should not be a performance issues. Tested with Doom(2106) which
found the entry in 1 iteration every time.
Acked-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4306>
Use it instead of the libdrm provided amdgpu_drm.h header. I used
the kernel revision from the README to get the header so the
header versions should be consistent.
Tested by removing /usr/include/libdrm/amdgpu_drm.h from my dev-machine.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4749>
It can be enabled via pEnabledFeatures or via vkPhysicalDeviceFeatures2.
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/4706>
With this, Doom Eternal should now run with ACO on GFX8+.
The generated 8/16-bit storage code is okay but the generated int8/int16
code is currently pretty bad but it works and apparently Doom Eternal
doesn't actually use it (even though it requires it).
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4707>
dEQP-VK.spirv_assembly.type.* passes with the features and extensions
enabled.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4707>
split_store_data() splits a vector and p_as_uniforms it if needed.
scan_write_mask()/advance_write_mask() are similar to
u_bit_scan_consecutive_range(), but makes it easier to only clear part of
the range and will also give ranges for zero'd bits.
split_buffer_store() is a helper for splitting VMEM/SMEM stores.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4639>
This helper is used for recombining split loads, passing the result to
p_as_uniform, aligning the offset down and shifting it right if needed and
handling large constant offsets.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4639>
Eventually, we'll probably want to replace the current
RegClass(type, size) constructor with this.
This has a functional change in that get_reg_class() now creates v1/v2
instead of v4b/v8b.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4639>
Fixes dEQP-VK.ssbo.phys.layout.random.16bit.scalar.13 hang with ACO
(features needed for the test are implemented in a later commit)
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4639>
This is needed to prevent bounds checking issues when load 8/16-bit values
with dword loads.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4639>
Previously the setprio was inside the branch, so it would only reset
the priority on the first wave, but not the others.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4536>
The TCS inputs and outputs must always fit into the LDS,
which implies that their addresses also always fit 24 bits.
On AMD GPUs, 24-bit multiplication is much faster than 32-bit
multiplication, so we can take the opportunity to use that
for TCS I/O instead.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4536>
Previously, it was just unreachable, which means it will generate
invalid shaders when it encounters a situation when it can't allocate
registers for eg. a large load.
This commit makes it slightly easier to notice such problems without
triggering a GPU hang.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4536>
