These don't really do anything. They're just a source and user of SSA
defs.
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/28301>
I'm not measuring a significant perf difference in
-bshading:shading=phong:model=bunny -bideas -brefract so this seems Good Enough
For Me.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28483>
unfortunately, shader stage merging is bogus when coherent images are used, so
we need an unmerged path. i'd rather not maintain two paths, so let's just
stop merging. as a bonus this makes ESO a lot easier, and lets us reuse the same
VS for both VS->GS and VS->TCS.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28483>
It was by pure luck that all sources (and the result) of nir_dpas_intel
had the same number of components. It is possible to support matrix
sizes where the accumlator matrix and the result matrix are larger
(e.g., 16x8 * 8x16 = 16x16).
This breaks all of the assumptions of NIR's infrastructure for code
generating intrinsics. Fix the by making the accumulator matrix be the
first source. The accumulator and the result will always have the same
dimensions (due to rules of matrix multiplication) and the same type
(due to restructions of the cooperative matrix extension). This forces
them to have the same number of components.
This doesn't fix all the potential problems. NIR expects that all
0-sized sources will have the same number of components. This just
ensures that the result has the correct number of components.
Fixes: 6b14da33ad ("intel/fs: nir: Add nir_intrinsic_dpas_intel")
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28404>
These will be needed to implement some tessellation dynamic
states within the TCS as opposed to using an epilog.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
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/28408>
This is just a little handle to tell the back-end where to do the copy.
Ideally, we'd have a NIR intrinsic that does the copy but we need to be
able to copy any number of registers up to 34 and NIR intrinsics just
aren't that flexible.
Reviewed-by: M Henning <drawoc@darkrefraction.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28300>
Instead of the previous fragile attempt to handle sparse_resident_and
by crawling deref chains, we now insert an is_sparse_resident_zink
intrinsic immediately after the tex or sparse_load intrinsic and define
Zink's sparse resident codes to always be 0/1. Then sparse_resident_and
becomes iand and is_sparse_texels_resident becomes != 0 and everything
is well-defined and robust.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28123>
This intrinsic helps to read the W coordinate stored in the QPU register
when initializing the input data for the fragment shaders.
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28072>
even with shobjs, we know the class of topology statically, so we just need to
select between the (up to) 3 compatible topologies, and luckily there are common
subexpressions we can factor out when calculating all 3 at once.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616>
GL semantics. GLES (weaker) and VK (stronger) semantics are left as a todo, with
explanations given. Enabled always to deal with null VBOs, this should be
optimized once we have soft fault.
This necessitates a rework of VBO keys, but hopefully for the best.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616>
This implements a rough skeleton of what's needed for tessellation. It contains
the relevant lowerings to merge the VS and TCS, running them as a compute
kernel, and to lower the TES to a new VS (possibly merged in with a subsequent
GS). This is sufficient for both standalone tessellation and tess + geom/xfb
together. It does not yet contain a GPU accellerated tessellator, simply falling
back to the CPU for that for now. Nevertheless the data structures are
engineered with that end goal in mind, in particular to be able to tessellate
all patches in parallel without needing any prefix sums etc (using simple
watermark allocation for the heap).
Work on fleshing out the skeleton continues in parallel. For now, this does pass
the tests and lets the harder stuff get regression tested more easily. And
merging early will ease rebase.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616>
Add a separate pass which uses the analyze_ubo_ranges machinery to
construct ranges of readonly globals accessed in the shader and push
them to constants in the preamble, using ldg.k if possible. This is
enough to handle inline uniforms in turnip but also provides a base for
OpenCL, although the pass would need further work for that.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26934>
Follow the blob and optimize subgroup operation using brcst.active and
getlast when supported.
The transformation consists of two parts. First, a NIR transform
replaces subgroup operations with a sequence of new brcst_active_ir3
intrinsics followed by a new [type]_clusters_ir3 intrinsic (where type
can be reduce, inclusive_scan, or exclusive_scan).
The brcst_active_ir3 intrinsic is lowered directly to a brcst.active
instruction. The other intrinsics get lowered to a new macro
(OPC_SCAN_CLUSTERS_MACRO) which later gets emitted as a loop (using
getlast/getone) that iterates all clusters and produces the requested
scan result.
OPC_SCAN_CLUSTERS_MACRO has a number of optional arguments. First, since
the exclusive scan result is not a natural by-product of the loop but
has to be calculated explicitly, its destination is optional. This is
necessary since adding it unconditionally will produce unused
instructions that won't be DCE'd anymore at this point. Second, when
performing 32b MUL_U reductions (that expand to multiple instructions),
an extra scratch register is necessary.
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/6387
Signed-off-by: Job Noorman <jnoorman@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26950>
Robust against separable shaders, and still makes sense for lowered I/O drivers,
whereas just counting FS variables and expecting them to match with the VS is...
questionable.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Signed-off-by: antonino <antonino.maniscalco@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26888>
we can replace varyings with point sprites, we just need to fix up .zw
appropriately. do that with some bcsels, ALU is cheap.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26963>
v2: Fix parameter order in nir_intrinsic_dpas_intel to DPAS conversion.
v3: Fix float16 destination DPAS on DG2.
v4: Use nir_component_mask(...) instead of 0xffff. Suggested by Caio.
v5: Rebase on !26323.
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25994>
In the wise words of Mike Blumenkrantz, "I hate gl_PointSize and so can you".
The mesa/st lowering won't mesh well with vertex shader epilogues, and it falls
over in various circumstances. I am too tired to go against the grain, so let's
just pretend to be a normal gallium driver and trust in the rasterizer CSO,
lowering point size internally. This properly handles transform feedback without
any hacks, both GL and GLES behaviours, etc.
Fixes:
KHR-GL31.transform_feedback.capture_vertex_separate_test
gl-2.0-large-point-fs
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26614>
in prep for tessellation (which will share the IA lowering), and for multidraw
indirect (which greatly complicates IA lowering with geom/tess).
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26614>
The NIR intrinsics now take and return a barrier whenever one is
modified instead of modifying in-place. In NAK, we give the internal
instructions the same treatment and convert everything to use barrier
SSA values and RegRefs. In nak_from_nir, we move all barriers to/from
GPRs. We'll clean up the massive pile of OpBMov later.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26463>
