The instruction has different regsizes for wave32 vs. wave64.
To ensure cases with cooperative matrix load/store without any
actual wmma instructions get handled correctly, also require
full subgroups if subgroup invocation/id are used. Not sure
those could be transparently changed anyway.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24683>
si_init_cs_preamble_state() function does not exist anymore and
PA_SC_WINDOW_SCISSOR_TL is set to 0,0. Update the comments with
this information.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25148>
We have competent lowering in NIR already available.
Drivers exposing CAP_DOUBLES but not SHADER_CAP_DROUND:
- d3d12 (NIR lowers ~0 if the underlying impl doesn't do floats)
- svga (Now sets the NIR lowering options)
- softpipe (Doesn't do GL4 so you can't use doubles anyway)
- llvmpipe (Lowers dround_even in NIR and passees the rest through
successfully)
- zink (NIR lowers ~0 if the underlying impl doesn't do floats,
otherwise passes things through successfully, except needed
dround_even lowering to avoid lavapipe regression with
native doubles)
- r600 (sets NIR rounding lowering flags, and lowers all fsign)
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25777>
Right now some drivers are doing dsign lowering in GLSL and haven't had to
have a NIR path due to there not being a corresponding vulkan driver. We
want this in NIR now so that we can retire that batch of GLSL lowering
code.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25777>
Avoids a regression when disabling GLSL-level lowering of the dround class
of ops, while passing through doubles to llvm for the other rounding ops.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25777>
Most drivers that can expose GL4 were claiming the cap anyway (llvmpipe,
softpipe, zink, iris, nvc0, radeonsi, r600, freedreno, d3d12), and just
doing lowering in NIR if nessary.
crocus was only claiming the cap for gen8, but the backend compiler
enables NIR lowering regardless.
svga is the only other GL4 driver that didn't set it, and we can just set
the NIR lowering flag.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25777>
It was never actually async as it was doing a DRM_IOCTL_SYNCOBJ_WAIT
right after DRM_IOCTL_XE_VM_BIND but it was required to allow the
partial binds required by sparse.
But it is now fixed and we can switch back to sync vm bind.
In future we will switch back to async vm bind to improve performance
but this time it will be properly implemented.
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25300>
Sync xe_drm.h with commit xxxxx ("drm/xe/uapi: Fix naming of XE_QUERY_CONFIG_MAX_EXEC_QUEUE_PRIORITY").
One not so straght forward change is that sync VM binds now don't
require a syncobj anymore, the uAPI will return as soon the VM bind
operations are done.
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25300>
Previous behavior was to default to "main"/fs, this wasn't nice
when the SPIR-V module had a single shader that didn't match that spec.
New behavior is to look at the available shaders:
- if there's only one, use just use it
- if multiple, narrow down using --stage and --entry as criteria
- if still multiple after narrowing down, print the list and fail
Note you can use just one --stage or --entry if that already narrows
down to a single match. Note that in SPIR-V it is valid to have a
shader module with two shaders sharing the same entry-point name but
different stages. Because of that in rare cases both --stage and
--entry will be needed.
This patch should remove the need of using --stage and --entry for most
of the uses of spirv2nir.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25461>
When there's ambiguity about what shader to use, list the shaders.
Conveniently print in the command line argument for, so can be copied
pasted.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25461>
This are the abbreviations we use elsewhere in Mesa. For convenience we
make them case insensitive. Old names still work for compatibility.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25461>
Refactor it to not fail, just return MESA_SHADER_NONE. Caller
takes care of handling error. Exposed so can be used by spirv2nir
program.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25461>
Fixes UBSan error:
src/amd/vulkan/radv_shader_info.c:78:41: runtime error: left shift of 15 by 28 places cannot be represented in type 'int'
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/25432>
These accesses (and similar) in ac_nir_exprot_position were out-of-bounds:
if (!outputs[VARYING_SLOT_PSIZ][0])
outputs_written &= ~VARYING_BIT_PSIZ;
I don't think this caused any real issue, but this silences ASan:
==40091==ERROR: AddressSanitizer: stack-use-after-return on address 0x7f8ffa6b1cb8 at pc 0x7f900da99068 bp 0x7f8ffb8871d0 sp 0x7f8ffb8871c8
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/25432>
Fixes UBSan:
src/amd/vulkan/radv_pipeline.c:1181:4: runtime error: null pointer passed as argument 2, which is declared to never be null
src/amd/vulkan/radv_shader.c:2243:4: runtime error: null pointer passed as argument 2, which is declared to never be null
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/25432>
Stop allocating CCS at the end of some BOs. Anv no longer uses that
memory range.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Jianxun Zhang <jianxun.zhang@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25003>
At image bind time, we require BOs to meet aux-map alignment
requirements in order to enable CCS on images. This is a heuristic
controlled by anv_bo_allows_aux_map().
To improve the chances of getting a properly aligned BO, we make use of
the dedicated allocation extension. Firstly, we report to applications a
preference for dedicated memory if an image would like to use the aux
map. Secondly, we align the VMA for dedicated allocations to meet
aux-map requirements.
To make enabling modifiers much easier on integrated gfx12, report
dedicated allocations as a requirement for modifiers which specify CCS.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> (v1)
Reviewed-by: Jianxun Zhang <jianxun.zhang@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25003>
Instead of requiring that a BO has the has_implicit_ccs flag set, simply
require that the BO is aligned according to aux-map requirements.
Reviewed-by: Jianxun Zhang <jianxun.zhang@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25003>
At image bind time, if an image's addresses can be placed into the
aux-map without causing conflicts with a pre-existing mapping, do so.
The code aux management code in the binding function operates on a
per-plane basis. So, use the per-plane CCS memory range from the image
rather than the CCS memory region for the entire BO.
Another way to avoid aux-map conflicts is to rely solely on having a
dedicated allocation for an image. Unfortunately, not all workloads
change their behavior when drivers report a preference for dedicated
allocations. In particular, 3DMark Wild Life Extreme does not make more
dedicated allocations and such a solution was measured to perform ~16%
worse than this solution. With this solution, I did not measure a loss
of CCS on that benchmark.
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/6304
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com> (v1)
Reviewed-by: Jianxun Zhang <jianxun.zhang@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25003>
This makes images a bit larger by reserving space to store the
compression control surface when the device uses an aux-map.
This space is not used currently because anv still maps main surface
addresses to space at the end of the anv_bo.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Jianxun Zhang <jianxun.zhang@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25003>
Move the determination of the image binding for CCS to a larger scope,
so that it can be reused for other aux usages in
add_aux_surface_if_supported().
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Jianxun Zhang <jianxun.zhang@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25003>
Make intel_aux_map_add_mapping return false if a mapping is attempted
that would conflict with an existing one. If this function doesn't
return false, it will either fail to return or return true.
The Vulkan driver will make use of this feature to opportunistically
enable CCS if a BO's VMA range has not been already mapped.
Reviewed-by: Jianxun Zhang <jianxun.zhang@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25003>
