1362ae38d4
asahi: optimize "no changes" case
...
drawoverhead case 1
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
8fc373370f
asahi: collapse stage uniform upload
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
8ba151aa16
asahi: dirty track stage uniforms
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
6be7c5f889
asahi: split up stage uniform upload
...
so we can update incrementally
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
23b4503225
asahi: rewrite queries
...
1. always keep the query in gpu memory, so we can implement qbos properly.
2. use a lightweight data structure for tracking writers to reduce overhead
3. allow many writers per query to eliminate stalls
4. use context-wide occlusion heap, to satisfy #1 without introducing
flushes or silly copies. this is what the pvr mesa driver does :-)
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
ca58bc239a
asahi: drop silly else
...
default
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
6ffbf77983
asahi: assert invariant
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
24b7fbca9d
asahi: allow disk cache with compblit
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
8ab443d549
asahi: enable compblit behind dbg flag
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
07a4ff5810
asahi: track bit count, not word count
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
0aa3eaa944
asahi: rm dead
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
46c70b72ca
asahi: skip set if tested
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
5982ae9025
asahi: fix vbo dirty track
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
668bf461b1
asahi: don't use util_resource_size
...
drawoverhead.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
d9c4fcce5f
asahi: log geometry shaders separate from xfb
...
different perf issues.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
c6c8262ce1
asahi: implement pipeline stats as a checkbox
...
real impl is blocked on uapi to plumb thru hw perf counters.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
7825044c39
asahi: honour discard_whole | persistent
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
793ac04077
asahi: handle read-only SSBOs
...
reduces silliness in Yuzu.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
97a945246c
asahi: fix valid buffer tracking for SSBO/image/XFB
...
smaller ranges.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
6689b083d8
asahi: don't sync for uninitialized buffer
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
9e8ce4550c
asahi: enable tcs caching
...
works fine
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
19da2f6d30
asahi: sync with query mismatches
...
otherwise the following assertion can fail. fixes crash in yuzu trace.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
3b927567ac
Revert "asahi: don't canonicalize nans/flush denorms when copying"
...
This reverts commit ab7fb3d400https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
74110ef21d
asahi: batch: Trace before waiting for syncobj
...
If the render hangs, at least this way we get the trace.
Signed-off-by: Asahi Lina <lina@asahilina.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
ff900ceffe
asahi: Enable scratch debugging
...
Via ASAHI_MESA_DEBUG=scratch. This will assert if enabled and the
scratch workgroup allocation count turns out not to be sufficient (that
is, there were failed allocations), to help debug the max occupancy
calculation.
Signed-off-by: Asahi Lina <lina@asahilina.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
8845702f8c
asahi: Allocate scratch for shaders
...
Finally, now that scratch is available, tell the hardware how much we
need and allocate the scratch buffers as necessary.
We only do the max subgroup calculation for compute right now, and it's
probably conservative (we could probably calculate a reduced occupancy
depending on register pressure). Getting this too low won't break, the
GPU will just be less efficient if there is not enough scratch
allocated. Vertex and fragment just get the max 96 for now.
Signed-off-by: Asahi Lina <lina@asahilina.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
bb5277aa3d
asahi: Hook up scratch
...
Instantiate our 3 scratch managers for each shader type, and pass them
to the hardware if a batch uses scratch.
Signed-off-by: Asahi Lina <lina@asahilina.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:30 +00:00
62001e175f
asahi: fix UB in qbo's
...
upper bits may be uninitialized. fixes
KHR-GL46.transform_feedback_overflow_query_ARB when built with gcc (passed by
chance with clang).
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:29 +00:00
a06b51559b
asahi: plug geometry heap leak
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:29 +00:00
06cf222830
asahi: plug so target leak
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:29 +00:00
e2c5a93358
asahi: plug early_serialized_nir leak
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:29 +00:00
ffac4e7179
asahi: plug pre-gs leak
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:29 +00:00
7b44d15e5f
asahi: plug geometry shader leaks
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:29 +00:00
1e973dd5a9
asahi: rework meta shader infra
...
this fixes the leaks, and is also a lot more pleasant to work with.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:29 +00:00
7eda3da983
asahi: plug passthrough tcs leak
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:29 +00:00
e91c0b6423
asahi: delete bogus assertion
...
dEQP-GLES3.functional.fragment_ops.scissor.outside_render_line at certain render
sizes.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:29 +00:00
5261962186
asahi: fix prim restart unrolling with indirects
...
need to account for draw->start.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:29 +00:00
9287bec892
asahi: fix unbound ssbos
...
fixes null ptr dereference in arb_shader_storage_buffer_object-array-ssbo-binding
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:29 +00:00
3a6083dea3
asahi: enable robustness
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:29 +00:00
591ce607e0
asahi: implement reset queries
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:29 +00:00
5dc0f5ccba
asahi: implement VBO robustness
...
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 >
2024-02-14 21:02:29 +00:00
4aadf67523
asahi: fix metadata for images with VS lowered to GS
...
KHR-GL46.shader_image_load_store.basic-allTargets-atomicVS
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:28 +00:00
9753cd44f7
asahi: Implement skeleton for tessellation
...
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 >
2024-02-14 21:02:28 +00:00
2d37d1b704
asahi: lower poly stipple
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:28 +00:00
2d913892b2
asahi: gut macOS related code
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27616 >
2024-02-14 21:02:28 +00:00
5022e5f4bf
iris: Fix iris_batch_is_banned() check
...
iris_batch_is_banned() expects that errno is negative.
Fixes: 665d30b544paulo.r.zanoni@intel.com >
Signed-off-by: José Roberto de Souza <jose.souza@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27619 >
2024-02-14 19:43:55 +00:00
0a129d8e1f
iris: Use intel_engines_supported_count()
...
Signed-off-by: José Roberto de Souza <jose.souza@intel.com >
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25233 >
2024-02-14 17:29:54 +00:00
b7e39657f6
zink: only add arrays to indirect non-tcs variables
...
these are already sized accurately
Reviewed-by: Dave Airlie <airlied@redhat.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27534 >
2024-02-13 16:13:13 +00:00
5438b19104
iris: enable generated indirect draws
...
This mirror the ring buffer mode we have in Anv.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26797 >
2024-02-13 00:06:45 +00:00
d754ed5330
iris: add an option for not emit draw parameters
...
When we start generating indirect draws, we'll generate values ourself
and point the HW vertex buffer entries to right location from the
device.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26797 >
2024-02-13 00:06:45 +00:00
Alyssa Rosenzweig