Replace calls to create hash tables and sets that use
_mesa_hash_pointer/_mesa_key_pointer_equal with the helpers
_mesa_pointer_hash_table_create() and _mesa_pointer_set_create().
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Acked-by: Eric Engestrom <eric@engestrom.ch>
This function is modeled after the aux_op functions except that it has a
lot more parameters because it deals with two images as well as source
and destination regions.
The original idea was that the backend compiler could eliminate
surfaces, so we would have it mark which ones are actually used,
then shrink the binding table accordingly. Unfortunately, it's a
pretty blunt mechanism - it can only prune things from the end,
not the middle - since we decide the layout before we even start
the backend compiler, and only limit the size. It also basically
gives up if it sees indirect array access.
Besides, we do the vast majority of our surface elimination in NIR
anyway, not the backend - and I don't see that trend changing any
time soon. Vulkan abandoned this plan a long time ago, and I don't
use it in Iris, but it's still been kicking around in i965.
I hacked shader-db to print the binding table size in bytes, and
observed no changes with this patch. So, this code appears to do
nothing useful.
Acked-by: Jason Ekstrand <jason@jlekstrand.net>
The num_components value passed into get_mul_for_src is used to only
compose the parts of the swizzle that we know will be used so we don't
compose invalid swizzle components. However, we had a bug where we
passed the number of components of the add all the way through. For the
given source, we need the number of components read from that source.
In the case where we have a narrow add, say 2 components, that is
sourced from a chain of wider instructions, we may not compose all the
swizzles. All we really need to do is pass through the right number of
components at each level.
Fixes: 2231cf0ba3 "nir: Fix output swizzle in get_mul_for_src"
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
This will allow drivers to pin shader buffers if necessary.
i965 and anv do not need to do this today, but iris will.
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Currently, BLORP expects drivers to provide two functions for dealing
with buffers: blorp_emit_reloc and blorp_surface_reloc. Both record a
relocation and combine the BO address and offset into a full 64-bit
address. Traditionally, blorp_surface_reloc has written that combined
address to an implicitly-known buffer where surface states are stored.
(In contrast, blorp_emit_reloc returns the value.)
The upcoming Iris driver stores surface states in multiple buffers,
which makes it impossible for blorp_surface_reloc to write the combined
address - it only takes an offset, not the actual buffer to write to.
This commit adds a third function, blorp_get_surface_address, which
combines and returns an address, which is then passed to ISL's surface
state fill functions. Softpin-only drivers can return a real address
here and skip writing it in blorp_surface_reloc. Relocation-based
drivers are have options. They can simply return 0 from the new
function, and continue writing the address from blorp_surface_reloc.
Or, they can return a presumed address from blorp_get_surface_address,
and have other relocation processing write the real value later.
For now, i965 and anv simply return 0.
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
This adds a second level of caching for the pre-lowered NIR that's only
based off of the shader module, entrypoint and specialization constants.
This is enough for spirv_to_nir as well as our first round of lowering
and optimization. Caching at this level should allow for faster shader
recompiles due to state changes.
The NIR caching does not get serialized to disk via either the
VkPipelineCache serialization mechanism or the transparent on-disk
cache. We could but it's usually not that expensive to fall back to
SPIR-V for the odd cache miss especially if it only happens once for
several misses and it simplifies the cache.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
The stuff hashed by anv_pipeline_hash_shader is exactly the inputs to
anv_shader_compile_to_nir so it can be used for NIR caching.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Thanks to the new NIR load_descriptor intrinsic added by the UBO/SSBO
lowering series, we weren't getting UBO pushing because the UBO range
detection pass couldn't see the constants it needed. This fixes that
problem with a quick round of constant folding. Because we're folding
we no longer need to go out of our way to generate constants when we
lower the vulkan_resource_index intrinsic and we can make it a bit
simpler.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Patch moves intel_tiled_memcpy[_sse41] libraries to isl, renames some
functions and types and makes the required build system changes for
meson, automake and Android. No functional changes are introduced.
v2: code cleanups, move isl_get_memcpy_type to i965 (Jason)
v3: move isl_mem_copy_fn to priv header, cleanups (Jason, Dylan)
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Dylan Baker <dylan@pnwbakers.com>
Acked-by: Kenneth Graunke <kenneth@whitecape.org>
Shaders containing software implementations of double-precision
operations can be very large such that we cannot stack-allocate
an array of grf_count*16.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Shaders containing software implementations of double-precision
operations can be very large such that we have more the 2^16 virtual
registers during optimization.
Move the 'nr' field to the union containing the immediate storage and
expand it to 32-bits.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
The next patch replaces an unsigned bitfield with a plain unsigned,
which triggers gcc to begin warning on signed/unsigned comparisons.
Keeping this patch separate from the actual move allows bisectablity and
generates no additional warnings temporarily.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
A follow on commit will move nr to the same union as the immediate
data, so we should assert these invariants before we overwrite the nr
field.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
A follow on patch will move the 'nr' field to the union containing the
immediate field, so prepare by checking that we're only testing these
assertions if the .file is correct.
The assertions with != ARF were kind of silly to begin with because the
<128 check is specifically only for things in the GRF.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
These are broken on a future platform, but it turns out we don't need
to fix them, since they're just type-converting moves with strided
source. Kill them.
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
This legalization pass is meant to handle situations where the source
or destination regioning controls of an instruction are unsupported by
the hardware and need to be lowered away into separate instructions.
This should be more reliable and future-proof than the current
approach of handling CHV/BXT restrictions manually all over the
visitor. The same mechanism is leveraged to lower unsupported type
conversions easily, which obsoletes the lower_conversions pass.
v2: Give conditional modifiers the same treatment as predicates for
SEL instructions in lower_dst_modifiers() (Iago). Special-case a
couple of other instructions with inconsistent conditional mod
semantics in lower_dst_modifiers() (Curro).
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Currently the visitor attempts to enforce the regioning restrictions
that apply to double-precision instructions on CHV/BXT at NIR-to-i965
translation time. It is possible though for the copy propagation pass
to violate this restriction if a strided move is propagated into one
of the affected instructions. I've only reproduced this issue on a
future platform but it could affect CHV/BXT too under the right
conditions.
Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
I triggered this bug while prototyping code for a future platform on
IVB. Could be a problem today though if a strided move is
copy-propagated into a type-converting move with DF destination.
Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
This seems to be a problem in combination with the lower_regioning
pass introduced by a future commit, which can modify a SIMD-split
instruction causing its execution size to become illegal again. A
subsequent call to lower_simd_width() would hit this bug on a future
platform.
Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Align16 is no longer a thing, so a new implementation is provided
using Align1 instead. Not all possible swizzles can be represented as
a single Align1 region, but some fast paths are provided for
frequently used swizzles that can be represented efficiently in Align1
mode.
Fixes ~90 subgroup quad swap Vulkan CTS tests.
Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
lower_integer_multiplication() implements 32x32-bit multiplication on
some platforms by bit-casting one of the 32-bit sources into two
16-bit unsigned integer portions. This can give incorrect results if
the original instruction specified a source modifier. Fix it by
emitting an additional MOV instruction implementing the source
modifiers where necessary.
Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Looks like it is impossible that 'last' variable is a null
because at least the get_vs_prog_data shouldn't return a null pointer.
So this check is unnecessary starts from commit:
99d497c5b6 "anv/pipeline: Replace get_fs_input_map with ..."
This small issue is found by cppcheck.
Signed-off-by: Andrii Simiklit <andrii.simiklit@globallogic.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
the naming is a bit confusing no matter how you look at it. Within SPIR-V
"global" memory is memory accessible from all threads. glsl "global" memory
normally refers to shader thread private memory declared at global scope. As
we already use "shared" for memory shared across all thrads of a work group
the solution where everybody could be happy with is to rename "global" to
"private" and use "global" later for memory usually stored within system
accessible memory (be it VRAM or system RAM if keeping SVM in mind).
glsl "local" memory is memory only accessible within a function, while SPIR-V
"local" memory is memory accessible within the same workgroup.
v2: rename local to function as well
v3: rename vtn_variable_mode_local as well
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
In the following scenario :
1. Create image format R8G8B8A8_UNORM
2. Create image view format R8G8B8A8_SRGB
3. Clear the view through a sub pass to a particular color
4. Barrier on the image to from color attachment to source transfer
5. Copy the image into a linear buffer to check the content
The step 4 resolving the clear color is unaware of the SRGB format of
the view, because the blorp resolve operations operate on images the
color associated with the resolve will not operate on SRGB format but
UNORM. Leading to the wrong color being written into surfaces.
This change forces a clear color resolve at the end of the render pass
so following resolves won't have to deal with the clear color with a
format that doesn't match the image's format.
On gfxbench vulkan_5_normal 1280x720, this appear to cost us ~0.5fps,
from 49.316 down to 48.949.
v2: Only fast clear resolve when image & view have different formats
(Lionel)
v3: Update warning (Jason)
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108911
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Suggested-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Cc: mesa-stable@lists.freedesktop.org
For now, it's hidden behind a cap. Hopefully, we can eventually drop
that along with all the manual offset code in spirv_to_nir.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Tested-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Instead of baking in uvec2 for UBO and SSBO pointers and uint for push
constant and shared memory pointers, make it configurable.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
We're going to want to do more deref optimizations going forward and
this gives us a central place to do them. Also, cast propagation will
get a bit more complicated with the addition of ptr_as_array derefs.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
SPIR-V allows for matrix and array types to be decorated with explicit
byte stride decorations and matrix types to be decorated row- or
column-major. This commit adds support to glsl_type to encode this
information. Because this doesn't work nicely with std430 and std140
alignments, we add asserts to ensure that we don't use any of the std430
or std140 layout functions with explicitly laid out types.
In SPIR-V, the layout information for matrices is applied to the parent
struct member instead of to the matrix type itself. However, this is
gets rather clumsy when you're walking derefs trying to compute offsets
because, the moment you hit a matrix, you have to crawl back the deref
chain and find the struct. Instead, we take the same path here as we've
taken in spirv_to_nir and put the decorations on the matrix type itself.
This also subtly adds support for strided vector types. These don't
come up in SPIR-V directly but you can get one as the result of taking a
column from a row-major matrix or a row from a column-major matrix.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
The loop through instructions doesn't set the cursor for us so unless we
set it somewhere, we may end up emitting instructions in the wrong
place. The only reason why we haven't been bitten by this in the past
is that it only happens in a few variable pointers cases and the CTS
tests for those don't use much control flow so things were getting
emitted in the correct order by accident.
Cc: mesa-stable@lists.freedesktop.org
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Caio Marcelo de Oliveira Filho