The intrinsics are now totally dead and can be removed.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Emma Anholt <emma@anholt.net>
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23036>
committed has to be a constant so there is no need to have a src and
depend on constant folding to remove the i2b.
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Acked-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22963>
Currently, we have an atomic intrinsic for each combination of memory type
(global, shared, image, etc) and atomic operation (add, sub, etc). So for m
types of memory supported by the driver and n atomic opcodes, the driver has to
handle O(mn) intrinsics. This makes a total mess in every single backend I've
looked at, without fail.
It would be a lot nicer to unify the intrinsics. There are two obvious ways:
1. Make the memory type a constant index, keep different intrinsics for
different operations. The problem with this is that different memory types
imply different intrinsic signatures (number of sources, etc). As an
example, it doesn't make sense to unify global_atomic_amd with
global_atomic_2x32, as an example. The first takes 3 scalar sources, the
second takes 1 vector and 1 scalar. Also, in any single backend, there are a
lot more operations than there are memory types.
2. Make the opcode a constant index, keep different intrinsics for different
operations. This works well, with one exception: compswap and fcompswap
take an extra argument that other atomics don't, so there's an extra axis of
variation for the intrinsic signatures.
So, the solution is to have 2 intrinsics for each memory type -- for atomics
taking 1 argument and atomics taking 2 respectively. Both of these intrinsics
take an nir_atomic_op enum to describe its operation. We don't use a nir_op for
this purpose, as there are some atomics (cmpxchg, inc_wrap, etc) that don't
cleanly map to any ALU op and it would be weird to force it.
The plan is to transition to these new opcodes gradually. This series adds a
lowering pass producing these opcodes from the existing opcodes, so that
backends can opt-in to the new forms one-by-one. Then we can convert backends
separately without any cross-tree flag day. Once everything is converted, we can
convert the producers and core NIR as a flag day, but we have far fewer
producers than backends so this should be fine. Finally we can drop the old
stuff.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rob Clark <robclark@freedesktop.org>
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22914>
When rendering a scaled tile, we need to use the original, hardware
FragCoord when accessing input attachments that are on-tile (i.e. were
rendered to in a previous subpass) because they are also scaled in the
same way that FragCoord is scaled. For input attachments that aren't
already on-tile, however, we need to use the fixed gl_FragCoord. Add a
new intrinsic and a bitfield of input attachments which should use it.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20304>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Qiang Yu <yuq825@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22690>
Contains a global wave ID of legacy GS waves.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Qiang Yu <yuq825@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22690>
This intrinsic is going to be used for simplifying GS code.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Qiang Yu <yuq825@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22690>
For GFX11 export dual source blend outputs when ACO.
ACO need a pseudo instruction to emit a block of
code which can't be done in nir currently.
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22199>
Previously the passthrough gs shader loaded some values with uniform
loads using sevaral hardcoded values.
This was not flexible for other drivers and started becoming too
unflexible for zink itself.
Use system values instead and use a lowering pass in zink.
Acked-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22667>
They use same instruction. Just because when the time
nir_load_smem_buffer_amd was introduced, radeonsi didn't support
pass buffer descriptor to nir_load_ubo directly.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22523>
With independent sets, we're not able to compute immediate values for
the index at which to read anv_push_constants::dynamic_offsets to get
the offset of a dynamic buffer. This is because the pipeline layout
may not have all the descriptor set layouts when we compile the
shader.
To solve that issue, we insert a layer of indirection.
This reworks the dynamic buffer offset storage with a 2D array in
anv_cmd_pipeline_state :
dynamic_offsets[MAX_SETS][MAX_DYN_BUFFERS]
When the pipeline or the dynamic buffer offsets are updated, we
flatten that array into the
anv_push_constants::dynamic_offsets[MAX_DYN_BUFFERS] array.
For shaders compiled with independent sets, the bottom 6 bits of
element X in anv_push_constants::desc_sets[] is used to specify the
base offsets into the anv_push_constants::dynamic_offsets[] for the
set X.
The computation in the shader is now something like :
base_dyn_buffer_set_idx = anv_push_constants::desc_sets[set_idx] & 0x3f
dyn_buffer_offset = anv_push_constants::dynamic_offsets[base_dyn_buffer_set_idx + dynamic_buffer_idx]
It was suggested by Faith to use a different push constant buffer with
dynamic_offsets prepared for each stage when using independent sets
instead, but it feels easier to understand this way. And there is some
room for optimization if you are set X and that you know all the sets in
the range [0, X], then you can still avoid the indirection. Separate
push constant allocations per stage do have a CPU cost.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15637>
Add more system values for XFB. This should be good enough for lowering GL3.1 +
transform_feedback2 + transform_feedback3. More will probably be needed for
geom/tess but that will be easier to work with when I'm actually bringing up
geom/tess. At any rate, we're splitting out XFB from the rasterization pipeline
and since XFB happens only in the last shader pre-rasterization stage, VS+XFB is
an orthogonal problem from e.g. VS+GS+XFB. Yeah, the combinatorics suck.
These will be used by Asahi, and hopefully eventually Panfrost.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Acked-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22123>
This involves two new system values.
Reviewed-by: Faith Ekstrand <faith@gfxstrand.net>
Reviewed-by: Emma Anholt <emma@anholt.net>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20303>
RADV used these to emulate firstTask for NV_mesh_shader.
They are no longer needed.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22139>
Mali's LD_TILE instruction (mapping to NIR's load_output) requires a "conversion
descriptor" specifying how to convert from the register foramt to the tilebuffer
format. To implement framebuffer fetch on OpenGL without shader variants, we
generate these descriptors in the driver and pass them in a uniform. However, to
comply with the Ekstrand Rule, we can't have magically materialized system
values -- they should come only from the NIR where the driver can lower as it
pleases (e.g. PanVK can lower to a constant because it knows the framebuffer
format at pipeline create time). Add intrinsics to model this.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20906>
We want to lower this in NIR instead of the backend IR to give the driver a
chance to lower the "is multisampled?" system value, which makes more sense to
do in NIR. This gets rid of one of the magic compiler materialized sysvals.
Plus, this will let us constant fold away the lowering in Vulkan when we know
that the pipeline is single-sampled / multi-sampled.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20906>
This new intrinsic maps to the MTBUF instruction format on AMD GPUs
and represents a typed buffer load in NIR.
Also add an unsigned upper bound for the new intrinsic.
Code for that ported from aco_instruction_selection_setup.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Konstantin Seurer <konstantin.seurer@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16805>
This will emulate VGT_ESGS_RING_ITEMSIZE, which does the multiplication
for us. It's beneficial to stop setting VGT_ESGS_RING_ITEMSIZE to reduce
context rolls, and also the register will be removed in the future.
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21525>
It's unused and if we ever want to use it again we should make it an alu
opcode instead.
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Acked-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21445>
This is a form of lowered I/O, it needs I/O semantics so we can know the
location to store to instead of passing via a sideband.
Over in !20906, we will use the BASE to lower blend shader with multisampling in
NIR instead of passing the number of samples and framebuffer format along a
sideband to the Midgard compiler. That's not needed for this series (this patch
was cherry-picked to avoid regressions in the lower_blend changes) but it's good
to model the full form of the I/O lowered intrinsic here.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reviewed-by: Italo Nicola <italonicola@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20836>
Some drivers may encode constant offsets in the instruction, so
make it possible for the drivers to request lowering the atomic
uniform offset into the range_base variable of the intrinsic.
v2: drop patch to use build-in array offset evaluation, it makes
problems with zink, and update the code accordingly
v3: always initialize range base
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19980>
Add the intrinsic range_base value to the image intrinsics and add
the option to store the image array offset into range_base instead
of adding it to the image array index if the driver requests it.
v2: Always initialize range_base
v3: fix for bindless intrinsics
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/19980>
This works like store_global, but lets us optimize address arithmetic. Like
load_agx, it is formatted to match the hardware semantic. We don't make use of
any clever formats in this series, though.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20558>
Like nir_texop_fragment_mask_fetch_amd, this is used to load multi
sample image fmask data for AMD GPU.
We will lower multi sample image load and samples_identical intrinsics
to use it latter for radeonsi. RADV does not need this because it
always expand fmask images before dispatch compute shader.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18666>
For used by legacy GS to store output to different ring according
to stream id.
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20158>
Used by radeonsi for lower nir_atomic_add_gen/xfb_prim_count_amd.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18010>
For radeonsi which use 32bit address in ac_build_load_to_sgpr().
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18010>
