Instead of using a separate outputs array, make the "end" instruction
(or chmask) take the outputs as sources. This works better for the new
RA, because it better models the fact that outputs are consumed all at
the same time. With the old model, each output collect would be assumed
dead after it was processed and subsequent collects could use it when
inserting shuffle code, which wouldn't work, and the new RA also deletes
collect instructions after lowering them to moves so the information
would be gone after RA.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10591>
We need a stable order in order to create phi instructions. In the
future we can make this more sophisticated in order to make manipulating
the CFG easier, but for now that only happens after RA, so we won't have
to worry about it.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10591>
Originally I wrote this to support multiple ir3 blocks per NIR block,
but this turned out to be more useful for creating a stable ordering to
the predecessors. We compute the predecessors ourselves, rather than
relying on NIR, so that the array of predecessors we create in the next
commit has a stable order we can rely on when creating phi nodes.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10591>
There's an optimization here to sink direct (i.e. not relative) reads of
an array past unrelated direct writes. However, since each write
actually reads, modifies, and then writes again to the array, this means
that we need to read the latest updated array. The old RA used the array
id instead of the SSA information, so it didn't care, but the new RA
uses ->instr instead and ignores the array id because arrays are now SSA
so it needs to be correct.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10591>
This wasn't using the same calculation that add_reg_dep() was using to
get the index into state->regs, so it was using the wrong register. Fix
this by folding it into add_reg_dep().
This shouldn't fix anything, because it's just used for scheduler
priorities, but it should reduce nop's and syncs.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10591>
a0.x is written as a half-reg, but just interpreting it as "hr61.x" will
result in it overlapping with r30.z in merged mode, which is not what
the hardware does at all. This introduced a spurious dependency on
a write to r30.z which resulted in an assert tripping. Just pretend it's
a full reg instead.
This fixes
spec@arb_tessellation_shader@execution@variable-indexing@vs-output-array-vec3-index-wr-before-tcs
with the new RA.
Fixes: 0f78c32 ("freedreno/ir3: post-RA sched pass")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10591>
Scheduling don't like address being in the different block from
the instruction.
Fixes a crash in the trace of "War Thunder" (DX11)
Signed-off-by: Danylo Piliaiev <dpiliaiev@igalia.com>
Reviewed-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10355>
iteration needs to be added to the offset now
Fixes: dae3113c3d ("gallium: split drawid out of pipe_draw_info and as a separate draw_vbo param")
Tested-by: Mark Janes <markjanes@swizzler.org>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10555>
There were two bugs which crep in here as part of 64551610d1:
forgetting that exec sizes in HW are in log2 space and having the
exec_size condition for the subtype backwards.
Fixes: 64551610d1 "intel/compiler: rework message descriptors..."
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10588>
f2f16 needs special treatment since it can access multiple 32-bit words.
Corresponds to the two-op instruction V2F32_TO_V2F16.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10392>
Cleans up swizzle lowering, and will be used for other cleanup as
well (fancy texturing tends to create a lot of foldable code).
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10392>
Disabling the check allows swapchains to be created on a remote
X Server using the xlib backend, which in turn allows Vulkan apps,
such as swapchain_images in Vulkan Samples, to run.
Closes#4323
Reviewed-by: Adam Jackson <ajax@redhat.com>
Acked-by: Michel Dänzer <mdaenzer@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10349>
When compiling with a C++ compiler, invalid conversions are treated as
errors unless the fpermissive flag is provided. These changes fix all
invalid conversions encountered while including libpanfrost in a C++
project.
Signed-off-by: Antonio Caggiano <antonio.caggiano@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Acked-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10468>
If the secondary has a list of CS buffers, it should be copied to
the primary.
Fixes dEQP-VK.api.command_buffers.record_many_draws_secondary_2.
Cc: 21.1 mesa-stable
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10547>
gcc warning:
../src/gallium/drivers/nouveau/nvc0/nvc0_screen.c: In function ‘nvc0_screen_get_compute_param’:
../src/gallium/drivers/nouveau/nvc0/nvc0_screen.c:623:7: warning: this statement may fall through [-Wimplicit-fallthrough=]
623 | switch (obj_class) {
| ^~~~~~
../src/gallium/drivers/nouveau/nvc0/nvc0_screen.c:634:4: note: here
634 | case PIPE_COMPUTE_CAP_MAX_PRIVATE_SIZE: /* l[] */
| ^~~~
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Pierre Moreau <dev@pmoreau.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10544>
gcc warning:
../src/gallium/drivers/nouveau/nv50/nv50_query_hw_metric.c: In function ‘nv50_hw_metric_get_query_result’:
../src/gallium/drivers/nouveau/nv50/nv50_query_hw_metric.c:140:26: warning: ‘sm11_hw_metric_calc_result’ accessing 64 bytes in a region of size 32 [-Wstringop-overflow=]
140 | *(uint64_t *)result = sm11_hw_metric_calc_result(hq, res64);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
../src/gallium/drivers/nouveau/nv50/nv50_query_hw_metric.c:140:26: note: referencing argument 2 of type ‘uint64_t *’ {aka ‘long unsigned int *’}
../src/gallium/drivers/nouveau/nv50/nv50_query_hw_metric.c:105:1: note: in a call to function ‘sm11_hw_metric_calc_result’
105 | sm11_hw_metric_calc_result(struct nv50_hw_query *hq, uint64_t res64[8])
| ^~~~~~~~~~~~~~~~~~~~~~~~~~
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Pierre Moreau <dev@pmoreau.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10544>
panfrost_batch_submit can recurse to hundreds of levels to submit
dependencies, so split the actual submit code from the dependency
recursion, saving over a kilobyte of stack space per recursion
level. Enforce this with ATTRIBUTE_NOINLINE.
Use ATTRIBUTE_NOINLINE on panfrost_batch_submit itself as well to
prevent GCC from inlining the function into itself, which would use a
few hundred bytes of stack.
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10574>
Otherwise, we need a FMASK_DECOMPRESS which is only supported
on the gfx queue.
Fixes rendering with Forza Horizon 4 on Polaris10.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10482>
