feabbddc2a
asahi: calculate validity when unpacking
...
for smarter printing.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
ac726ae5a9
asahi: mark eMRT loads as in-bounds
...
for layer clamping purposes.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
ac114030a7
ail: constify everything
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
efa9f242a8
agx: fix UB in cursor comparison
...
padding here is implementation-defined, do the cleaner thing. fixes invalid IR
generated with gcc but not clang.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Reported-by: Janne Grunau <janne-fdr@jannau.net >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
bcffc84306
agx: optimize elect()
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
bc26e11c2a
agx: lower more quad ops
...
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
7aa17a122f
agx: implement quad_ballot
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
8a656b29f3
agx: handle quad reduce
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
1be0e8e348
agx: stash early_fragment_test info
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
1c8aab388c
agx: speed-up dce
...
Follows aco changes, there shouldn't be any loop header phis that are
dead code (as nir_opt_dce ensure that)
Signed-off-by: Mary Guillemard <mary@mary.zone >
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
5b03e7bab3
agx: fix bogus unit test
...
broken SSA.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
aad82f4265
agx: optimize txf with lod 0
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
5c898e56b2
agx: reserve scratch registers for mem<-->mem swaps
...
Trying to spill/fill a temp on the fly has pathologically bad performance in bad
cases, reserving a scratch reg is much more well-behaved. Fixes a fragment
shader timeout in dEQP-VK.graphicsfuzz.spv-stable-maze-flatten-copy-composite
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
f7ff0041c1
agx: document another sample_mask restriction
...
hit this with force early fragment tests.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
840394c169
agx: expose agx_link_libagx
...
for deduplication.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
5a3ac73747
agx: report uses_txf
...
so driver can optimize usc binding.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
54ec9512ef
agx: flesh out subgroup lowering
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
659db5049c
agx: lower 8-bit subgroups
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
00cfe84fd9
agx: forbid uniforms on ballots
...
needs more investigation..
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
c2c49b261c
agx: add missing b2b16 implementation
...
will show up with a subgroup lowering.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
a3cb0cbfda
agx: handle quad swaps
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
f4a5ac3554
agx: handle quad_broadcast
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
7b33c549b9
agx: handle non-immediate shuffles in divergent CF
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
589c69a646
agx: lower shuffle
...
per dougallj's notes in applegpu.py
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
fbcd9a83e4
agx: model more subgroup ops
...
additional shuffles, scans, reduces.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
e718a536ac
agx: delete unreachable blocks
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
3efa723b63
agx: lower nir_intrinsic_load_num_subgroups
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
765bf9a25b
agx: switch to demote internally
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
35d6f4a394
agx: fix spilling inside sample loop
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
bdd200a202
agx: handle subgroup barriers
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
d183b76fd4
agx: fix frag sidefx with sample shading
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
6269a1474d
agx: fix load_helper_invocation with sample shading
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
94f0209fb2
agx: fix phi translation corruption
...
we can't stomp over srcs[], where we allocated our space for sources. unclear
how this worked before but it definitely breaks once you have a phi with 7
sources.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
f21dbfe5ae
agx: allow 8-bit bcsel
...
can be generated from our lowerings but it just works with the implicit
conversion semantics we have.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
a948244058
agx: handle cross-workgroup memory barriers
...
there's no prior art for this, but experimentally this seems to do the right
thing.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
c22ce3cab9
agx: fix some ms texture packing
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
ec47f325f8
agx: fix query LOD of array
...
need to ignore the layer
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
8df39ac49b
agx: enable more lowering
...
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
69d7063ec0
agx: optimize and/or with booleans
...
Beneficial so we can fuse the comparison.
total instructions in shared programs: 2188179 -> 2185535 (-0.12%)
instructions in affected programs: 392512 -> 389868 (-0.67%)
helped: 894
HURT: 9
Instructions are helped.
total alu in shared programs: 1706063 -> 1703445 (-0.15%)
alu in affected programs: 275063 -> 272445 (-0.95%)
helped: 880
HURT: 9
Alu are helped.
total fscib in shared programs: 1702385 -> 1699743 (-0.16%)
fscib in affected programs: 276199 -> 273557 (-0.96%)
helped: 894
HURT: 9
Fscib are helped.
total ic in shared programs: 462494 -> 462490 (<.01%)
ic in affected programs: 124 -> 120 (-3.23%)
helped: 1
HURT: 0
total bytes in shared programs: 14476964 -> 14464512 (-0.09%)
bytes in affected programs: 2870824 -> 2858372 (-0.43%)
helped: 888
HURT: 155
Bytes are helped.
total regs in shared programs: 662444 -> 662461 (<.01%)
regs in affected programs: 1025 -> 1042 (1.66%)
helped: 14
HURT: 12
Inconclusive result (value mean confidence interval includes 0).
total uniforms in shared programs: 1638301 -> 1638374 (<.01%)
uniforms in affected programs: 17778 -> 17851 (0.41%)
helped: 22
HURT: 54
Uniforms are HURT.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
c43413f729
compiler: add ACCESS_IN_BOUNDS_AGX
...
useful for internal shaders on agx.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
eb5f82d221
nir,agx: fix load_active_subgroup_index
...
It can't be reordered globally, since its value is control-flow dependent.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Acked-by: Faith Ekstrand <faith.ekstrand@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
7fb60c4c81
nir,agx: add depth=never workaround
...
There seems to be a hardware issue where fragment shaders with side effects get
skipped if depth testing with NEVER. Add a workaround for this case where we
discard programmatically instead.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Acked-by: Faith Ekstrand <faith.ekstrand@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:25 +00:00
9d824bd123
nir: add quad_ballot_agx intrinsic
...
to lower quad votes in nir.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Acked-by: Faith Ekstrand <faith.ekstrand@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:24 +00:00
2912f531a7
nir: add texops for AGX border colour emulation
...
AGX has limited border colour hardware. To support full
customBorderColorWithoutFormat semantics, we're forced to emulate in shaders at
a substantial performance penalty. Actually, that's needed just to pass CTS
because of other hardware issues stacking on top of each others... Hooray!
Add the texops we need to facilitate efficient custom border colour lowering.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Acked-by: Faith Ekstrand <faith.ekstrand@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:24 +00:00
8b9ed851ec
nir: add is_first_fan_agx sysval
...
needed for correct flatshading with fans, without falling back on software input
assembly.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io >
Acked-by: Faith Ekstrand <faith.ekstrand@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29179 >
2024-05-14 04:57:24 +00:00
8bc694223e
zink: Set workarounds.can_do_invalid_linear_modifier for NVK
...
This fixes most of the egl_image_dma_buf* piglit tests. The remaining
fails are YCbCr tests which are likely unrelated to core dma-buf
import/export.
Reviewed-by: Dave Airlie <airlied@redhat.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24795 >
2024-05-14 04:04:34 +00:00
e6f77defec
nvk/wsi: Advertise modifier support
...
Reviewed-by: Dave Airlie <airlied@redhat.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24795 >
2024-05-14 04:04:34 +00:00
28342a581f
vulkan/wsi: Bind memory planes, not YCbCr planes.
...
Reviewed-by: Joshua Ashton <joshua@froggi.es >
Fixes: f5433e4d6chttps://gitlab.freedesktop.org/mesa/mesa/-/issues/10176
Reviewed-by: Dave Airlie <airlied@redhat.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24795 >
2024-05-14 04:04:34 +00:00
cd428e01d7
nvk: Advertise VK_EXT_image_drm_format_modifier
...
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/9636
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/9480
Reviewed-by: Dave Airlie <airlied@redhat.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24795 >
2024-05-14 04:04:34 +00:00
d8e200c0d9
nvk: Advertise VK_EXT_queue_family_foreign
...
Reviewed-by: Dave Airlie <airlied@redhat.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24795 >
2024-05-14 04:04:34 +00:00
Alyssa Rosenzweig