This is needed because the information stored on the ATTR file for
multipolygon fragment shaders isn't stored as a contiguous sequence in
the GRF, instead the ATTR source may be lowered by assign_urb_setup()
to use a <16;8,0> region, which reads 4 SIMD16 GRFs for a SIMD32
instruction, even though the result of fs_inst::size_read() is
expected to be 2 GRFs. Special case ATTR sources for multipolygon PS
shaders to calculate the number of physical GRFs that will actually be
read by the instruction after lowering, based on the number of
polygons processed by the instruction.
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26606>
This fixes a number of assumptions made by the multipolygon input
attribute handling code from assign_urb_setup() so it also works on
Xe2+, which has additional multipolygon dispatch modes (like SIMD4x8
and SIMD2x16) and uses a different more compact representation of the
plane parameters.
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26606>
The X and Y barycentric vectors are no longer interleaved in SIMD8
chunks (yay), so this is mostly a matter of disabling the
lower_barycentrics() pass and switching to a simpler implementation of
fetch_barycentric_reg() that simply calls fetch_payload_reg() instead
of the SIMD8 shuffling we had to do in previous generations.
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26606>
This extends fetch_payload_reg() to support fetching vector registers
like barycentrics stored on the payload as a contiguous sequence of
SIMD-wide vectors. In the SIMD32 case, both halves of the SIMD16
vector registers specified as regs[0] and regs[1] are zipped to
construct a single SIMD32-wide vector.
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26606>
We only need it for indirect draws.
Improves performance on an i7-12700 and A770:
- Piglit's drawoverhead base case +150.639% +/- 2.86933% (n=15).
- gfxbench5 gl_driver2_off +19.7219% +/- 1.13778% (n=15)
- SPECviewperf2020 catiav5test1 +1.6831% +/- 0.552052% (n=10).
Cc: mesa-stable
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26806>
Whenever we use a BO in a batch, we need to find its corresponding exec
list entry, either to a) record that it's been used, b) update whether
it's being written, c) check for cross-batch implicit dependencies.
bo->index exists to accelerate these lookups. If a BO is used multiple
times by a batch, bo->index is its location in the list. Because the
field is global, and a BO can in theory be used concurrently by multiple
contexts, we need to double-check whether it's still there. If not, we
fall back to a linear search of all BOs in the list, looking to see if
our index was simply wrong (but presumably right for another context).
However, there's one glaringly obvious case that we missed here. If
bo->index is -1, then it's wrong for /all/ contexts, and in fact implies
that said BO has never been added to any exec list, ever. This is quite
common in fact: a new BO, never been used before, say from the BO cache,
or streaming uploaders, gets used for the first time.
In this case we can simply conclude that it's not in the list and skip
the linear walk through all buffers referenced by the batch.
Improves performance on an i7-12700 and A770:
- SPECviewperf2020 catiav5test1: 72.9214% +/- 0.312735% (n=45)
Cc: mesa-stable
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26806>
These restrictions don't seem to be applicable anymore, and limiting
to SIMD8 wouldn't work since we're no longer building shaders with
that dispatch width.
[ Francisco: This one-liner change was squashed by Rohan Garg into a
previous version of my patch "Stop building SIMD8 programs", but it
makes more sense as a separate commit -- Formatted as a separate
patch. ]
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26605>
SIMD8 kernels are no longer able to utilize the ALUs efficiently,
since they have twice the vector width as previous platforms. However
even though there aren't many reasons to use it, SIMD8 is still
supported by the instruction set technically, and it will still be
used for some SIMD-lowering sequences.
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26605>
Similar to other FS dispatch modes, attempt to build a dual-SIMD8
program if the regular SIMD8 program didn't spill and doubling the
amount of space for varyings doesn't cause us to go over the thread
payload limit. Dual-SIMD8 builds in combination with coarse pixel
shading are currently not handled.
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26585>
The copy would be discarded immediately. Until now we were relying on
DCE to eliminate these, but it seems like in some cases MOVs into the
null register emitted by lower_simd_width() are never eliminated,
likely because a lower_simd_width() call has been introduced close to
the bottom of optimize() which isn't follow by any additional DCE
passes.
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26585>
