Marek Olšák [Sun, 22 Mar 2020 03:47:08 +0000 (23:47 -0400)]
mesa: don't ever bind NullBufferObj to glBindBuffer(Base,Range) slots
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4466>
Marek Olšák [Sun, 22 Mar 2020 02:49:03 +0000 (22:49 -0400)]
mesa: don't ever bind NullBufferObj for glBindBuffer targets
Since VAOs don't use NullBufferObj for vertex attribs anymore, let's remove
more uses of NullBufferObj.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4466>
Marek Olšák [Sun, 22 Mar 2020 01:36:28 +0000 (21:36 -0400)]
mesa: don't ever set NullBufferObj in gl_vertex_array_binding
This improves performance by 5% in the game "torcs", FPS: 98.83 -> 103.73
It does a lot of glPush/PopClientAttrib, which exacerbates the overhead
of setting NullBufferObj.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4466>
Marek Olšák [Sun, 22 Mar 2020 00:18:02 +0000 (20:18 -0400)]
mesa: optimize initialization of new VAOs
Precompute the default state in gl_context, and just copy it when we create
a VAO.
This also helps glPushClientAttrib function, which always creates a VAO,
which has a substantial CPU overhead in profiles.
Reviewed-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4466>
Mauro Rossi [Sat, 4 Apr 2020 22:24:19 +0000 (00:24 +0200)]
android: aco: add various compiler statistics
Fixes a building error due to compiler/aco_statistics.cpp
missing in src/amd/Makefile.sources
Fixes: b1544352 ("aco: add various compiler statistics")
Signed-off-by: Mauro Rossi <issor.oruam@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Hyunjun Ko [Mon, 6 Apr 2020 04:55:19 +0000 (04:55 +0000)]
nir: fix wrong assignment to buffer in xfb_varyings_info
Tested with dEQP-VK.transform_feedback.fuzz.various_buffers.buffers100_instance_array_vertex
Signed-off-by: Hyunjun Ko <zzoon@igalia.com>
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Cc: mesa-stable@lists.freedesktop.org
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4459>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4459>
Tapani Pälli [Wed, 1 Apr 2020 09:08:41 +0000 (12:08 +0300)]
mesa/st: release variants for active programs before unref
Programs can be shared among many contexts and each program holds a
variant list which has context specific variants. When context gets
destroyed it must make sure it relases all variants, otherwise remaining
context that utilizes same program will attempt to save a zombie shader
for already deleted context when releasing program and its variants.
Fixes:
dEQP-EGL.functional.sharing.gles2.program.render
and other flaky multihread dEQP-EGL failures.
v2: pass program pointer via & (Marek)
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Cc: mesa-stable@lists.freedesktop.org
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4386>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4386>
Tapani Pälli [Thu, 2 Apr 2020 09:54:17 +0000 (12:54 +0300)]
mesa/st: unbind shader state before deleting it
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Cc: mesa-stable@lists.freedesktop.org
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4386>
Alyssa Rosenzweig [Wed, 1 Apr 2020 16:59:53 +0000 (12:59 -0400)]
pan/bit: Add mode to run unit tests
Probably the most useful of the bunch going forward.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Sun, 5 Apr 2020 22:45:00 +0000 (18:45 -0400)]
pan/bit: Make run more useful
..by printing some output.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Sun, 5 Apr 2020 21:48:01 +0000 (17:48 -0400)]
pan/bit: Add csel tests
..and pull out common instruction generation to reduce duplication in
tests a bit.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Wed, 1 Apr 2020 22:50:27 +0000 (18:50 -0400)]
pan/bit: Add CSEL to interpreter
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Wed, 1 Apr 2020 22:27:54 +0000 (18:27 -0400)]
pan/bit: Add FMA tests
Now that the earlier reg ctrl issue is fixed these should pass.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Wed, 1 Apr 2020 20:45:55 +0000 (16:45 -0400)]
pan/bit: Add 16-bit fmod tests
These raise another set of issues -- indeed, not all of these tests are
passing, since it turns out I have an actual bug in the packing code. So
after all this work, test bringup has identified an actual issue :)
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Wed, 1 Apr 2020 20:45:09 +0000 (16:45 -0400)]
pan/bit: Add verbose printing for tests
We'd like to dump both the generated IR (so we know exactly what's being
tested) as well as the compiled program (so we know what's running for
comparison).
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Wed, 1 Apr 2020 20:24:15 +0000 (16:24 -0400)]
pan/bit: Add helper for generating floating mod tests
We can iterate them, isn't that adorable!
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Wed, 1 Apr 2020 18:40:33 +0000 (14:40 -0400)]
pan/bit: Add packing test framework
Given an instruction, we'd like to wrap it in a clause with some I/O on
each end so we can pack it up and send it to the hardware to compare
against the simulator.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Wed, 1 Apr 2020 17:13:50 +0000 (13:13 -0400)]
pan/bit: Implement floating source mods
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Wed, 1 Apr 2020 17:08:00 +0000 (13:08 -0400)]
pan/bit: Implement outmods
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Wed, 1 Apr 2020 14:04:13 +0000 (10:04 -0400)]
pan/bit: Add preliminary FMA/ADD/MOV implementations
Missing some details about modifiers but the core structure should
look like this for 32 and 16-bit, I think. My sincerest apologies for
the macro magic, I tried to make it the least bad I could but trying to
keep down repitition.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Wed, 1 Apr 2020 13:50:38 +0000 (09:50 -0400)]
pan/bit: Handle read/write
We case the various sources and destinations to model register file
access and passthrough in particular.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Wed, 1 Apr 2020 13:41:20 +0000 (09:41 -0400)]
pan/bit: Stub out BIR interpreter
We'd like to step through a BIR program to evaluate it for testing.
Let's stub out some infrastructure for modeling Bifrost.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Sun, 5 Apr 2020 23:22:01 +0000 (19:22 -0400)]
pan/bi: Match CSEL argument order with hw
It turns out ports need to be in order of the arguments of an
instruction (port 3, that is), which breaks on instructions whose IR
argument order is different from the packed order, like csel. So fix
that.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Sun, 5 Apr 2020 22:06:08 +0000 (18:06 -0400)]
pan/bi: Add helper to debug port assignment
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Wed, 1 Apr 2020 22:22:01 +0000 (18:22 -0400)]
pan/bi: Handle BIFROST_FIRST_WRITE_FMA_P2_READ_P3
It's a special case for unclear reasons, and if you mess it up you get
INSTR_INVALID_ENC. Isn't hardware fun?
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Wed, 1 Apr 2020 22:13:55 +0000 (18:13 -0400)]
pan/bi: Allow BI_FMA to take mods
It doesn't take abs but it can take outmod/neg.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Wed, 1 Apr 2020 22:08:32 +0000 (18:08 -0400)]
pan/bi: Don't gobble zero ports
In case we've reading/writing R0.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Wed, 1 Apr 2020 20:51:30 +0000 (16:51 -0400)]
pan/bi: Fix negation in ADD.v2f16
When we flip the sources we need to flip the negates as well to stay
consistent.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Wed, 1 Apr 2020 20:51:17 +0000 (16:51 -0400)]
pan/bi: Fix duplicated source in ADD.v2f16
Typo.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Alyssa Rosenzweig [Wed, 1 Apr 2020 20:23:12 +0000 (16:23 -0400)]
pan/bi: Export bi_class_name
For use in naming tests.
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4458>
Vasily Khoruzhick [Fri, 3 Apr 2020 09:17:06 +0000 (02:17 -0700)]
lima: avoid situations when scissor minx > maxx or miny > maxy
Clip scissor to viewport and then to framebuffer to avoid that since
hardware can't handle this case.
Reviewed-by: Qiang Yu <yuq825@gmail.com>
Signed-off-by: Vasily Khoruzhick <anarsoul@gmail.com>
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4427>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4427>
Christian Gmeiner [Tue, 23 Jul 2019 20:02:56 +0000 (22:02 +0200)]
etnaviv: convert perfmon queries to acc queries
Signed-off-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/1530>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/1530>
Christian Gmeiner [Fri, 19 Jul 2019 13:27:39 +0000 (15:27 +0200)]
etnaviv: move generic perfmon functionality into own file
This change removes the basic infrastructure to work with perfmon
from the perfmon query impl and puts it into its own place.
Makes the whole series easier to review and ends smaller changes.
Signed-off-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/1530>
Christian Gmeiner [Wed, 31 Jul 2019 20:40:45 +0000 (22:40 +0200)]
etnaviv: extend acc sample provide with an allocate(..)
We might be able to sub-class etna_acc_query.
Signed-off-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/1530>
Christian Gmeiner [Fri, 19 Jul 2019 10:57:11 +0000 (12:57 +0200)]
etnaviv: extend result(..) to return if data is ready
For the upcoming conversion of perfmon queries to the acc query
framework we need a way to tell that the data is not ready.
Signed-off-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/1530>
Christian Gmeiner [Fri, 19 Jul 2019 10:43:43 +0000 (12:43 +0200)]
etnaviv: make use of a fixed size array to track of all acc query provider
Signed-off-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/1530>
Christian Gmeiner [Fri, 19 Jul 2019 09:45:36 +0000 (11:45 +0200)]
etnaviv: extend acc query provider with supports(..) function
Move the logic if a query provider supports a query_type
directly to the provider.
Signed-off-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/1530>
Christian Gmeiner [Wed, 31 Jul 2019 10:38:53 +0000 (12:38 +0200)]
etnaviv: rework wait/flush logic
Saves us from doing an extra flush in !wait case and seems more
logical now. Also evaluate etna_bo_cpu_prep(..) retun value.
Signed-off-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/1530>
Christian Gmeiner [Fri, 26 Jul 2019 10:32:40 +0000 (12:32 +0200)]
etnaviv: reset no_wait_cnt after triggered flush
Signed-off-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/1530>
Christian Gmeiner [Wed, 31 Jul 2019 18:10:14 +0000 (20:10 +0200)]
etnaviv: explicitly call resource_written(..)
We might end in cases where etna_acc_get_query_result(..) gets called
within one draw call (aka before flushing). At this point the status
of the resource was not set but gets used in etna_acc_get_query_result(..)
to handle different wait cases. Fix this issue by calling resource_written(..)
explicitly.
Signed-off-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/1530>
Christian Gmeiner [Fri, 26 Jul 2019 08:18:44 +0000 (10:18 +0200)]
etnaviv: rework etna_acc_sample_provider
Simplify the interface a sampler provider needs to implement. The start(..)
and stop(..) functions got called by resume(..) and suspend(..) so lets
get rid of start(..) and stop(..). Also the way we count and use samples
is much easier to follow now.
Signed-off-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/1530>
Christian Gmeiner [Fri, 26 Jul 2019 08:01:15 +0000 (10:01 +0200)]
etnaviv: rename hw queries to acc queries
The name hw queries was choosen as occlusion queries are 'feeling'
like nothing special. It is possible to interact with them only
via the command stream - unlike perfom queries where some kernel
magic is needed.
Accumulated HW queries is a much better name for this type of queries.
We read some hardware values over some draw calls and need to accumulate
them to get the final result.
This is some prep work for the following perfmon changes.
Signed-off-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/1530>
Eric Engestrom [Sun, 2 Feb 2020 18:31:26 +0000 (18:31 +0000)]
glx: use anonymous namespace to avoid -Wodr issues when building with LTO enabled
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Adam Jackson <ajax@redhat.com>
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/2597>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/2597>
Eric Engestrom [Sun, 2 Feb 2020 18:31:36 +0000 (18:31 +0000)]
glx: fix 630 times -Wlto-type-mismatch when building with LTO enabled
The prototypes are simply copied from include/GL/gl*.h
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Adam Jackson <ajax@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/2597>
Jason Ekstrand [Sat, 4 Apr 2020 14:47:00 +0000 (09:47 -0500)]
Revert "spirv: Rewrite CFG construction"
This reverts commit
fa5a36dbd474fb3c755da51553c6ca18dab76a06.
Dave Airlie [Fri, 3 Apr 2020 01:09:20 +0000 (11:09 +1000)]
Revert "gallivm: disable rgtc/latc SNORM accellerated fetches"
This reverts commit
4897e70ccd3987d470ec8622d473ee3405f6e96f.
Fixed in previous commits.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4425>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4425>
Dave Airlie [Fri, 3 Apr 2020 04:25:51 +0000 (14:25 +1000)]
gallivm/rgtc: enable fast path for snorm types.
As per Roland's suggestions it should be easy to enable the
fast path fetch for rgtc snorm as well here.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4425>
Dave Airlie [Fri, 3 Apr 2020 03:54:17 +0000 (13:54 +1000)]
gallivm/rgtc: fix the truncation to 8-bit
The 8 bit type wasn't 8-bit so when doing signed work we lost
the sign bit. This fixes it to use a proper vector type,
even if we just end up in here with the 1-wide path for now.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4425>
Rob Clark [Thu, 2 Apr 2020 21:08:54 +0000 (14:08 -0700)]
glsl: don't limit fp16 lowering to frag
This restriction doesn't belong in core code.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4423>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4423>
Rob Clark [Thu, 2 Apr 2020 21:07:51 +0000 (14:07 -0700)]
freedreno: limit fp16 to frag and compute
To avoid dealing w/ some backend varying linking issues when mixing
precision vs geom/tess.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4423>
Rob Clark [Thu, 2 Apr 2020 19:13:38 +0000 (12:13 -0700)]
freedreno/ir3: also precompile compute shaders for shaderdb
Similar as with draw shaders, nothing will trigger the final variant in
shader-db.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4423>
Rob Clark [Thu, 2 Apr 2020 19:12:32 +0000 (12:12 -0700)]
freedreno: fix missing locking
Fixes: d0b3ccb0607 ("freedreno: Fix detection of being in a blit for acc queries.")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4423>
Rob Clark [Wed, 1 Apr 2020 17:40:35 +0000 (10:40 -0700)]
freedreno/a6xx: add some compute logging
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4423>
Rob Clark [Mon, 16 Mar 2020 22:34:08 +0000 (15:34 -0700)]
freedreno/ir3/cf: use ssa-uses
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4423>
Rob Clark [Thu, 12 Mar 2020 21:18:04 +0000 (14:18 -0700)]
freedreno/ir3: add a pass to collect SSA uses
We don't really track these as the ir is transformed, but it would be a
useful thing for some passes to have. So add a pass to collect this
information. It uses instr->data (generic per-pass ptr), with the
hashsets hanging under a mem_ctx for easy disposal at the end of the
pass.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4423>
Rob Clark [Mon, 16 Mar 2020 21:50:32 +0000 (14:50 -0700)]
freedreno/ir3/cf: skip array load/store
Don't fold conversions into array (incl phi lowered to regs/array).
These aren't SSA. Avoids crashes in particular in frag shaders with
flow control, which would leave a dangling array write disconnect from
the original cov src.
Possibly this could be slightly relaxed, if there is no other consumer
of the src, and it were in the same block. But it would require
updating block->keeps, and taking care of barrier state. Which isn't a
thing the cf pass does currently.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4423>
Rob Clark [Mon, 16 Mar 2020 14:05:01 +0000 (07:05 -0700)]
freedreno/ir3: fixup cat3 32b vs 16b
These should be keyed on src arg type.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4423>
Rob Clark [Mon, 16 Mar 2020 13:47:05 +0000 (06:47 -0700)]
freedreno/ir3/cf: handle widening too
We can also fold f16->f32 conversions.
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4423>
Rob Clark [Wed, 11 Mar 2020 20:55:17 +0000 (13:55 -0700)]
nir: fix definition of imadsh_mix16 for vectors
Fixes: c27b3758fa0 ("nir/opcodes: Add new 'umul_low' and 'imadsh_mix16' opcodes")
Signed-off-by: Rob Clark <robdclark@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4423>
Daniel Schürmann [Thu, 27 Feb 2020 16:52:21 +0000 (17:52 +0100)]
aco: use MUBUF to load subdword SSBO
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Fri, 14 Feb 2020 16:53:11 +0000 (17:53 +0100)]
aco: implement 8bit/16bit store_ssbo
Currently without alignment check, so that
we can only use the _byte and _short versions
and multi-component stores are split.
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Fri, 14 Feb 2020 14:54:56 +0000 (15:54 +0100)]
aco: implement 8bit/16bit load_buffer
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Thu, 13 Feb 2020 15:51:38 +0000 (16:51 +0100)]
aco: implement storagePushConstant8 & storagePushConstant16
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Thu, 2 Apr 2020 16:50:46 +0000 (17:50 +0100)]
aco: implement vec2/3/4 with subdword operands
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Thu, 2 Apr 2020 16:26:00 +0000 (17:26 +0100)]
aco: prepare helper functions for subdword handling
- get_alu_src()
- emit_extract_vector()
- emit_split_vector()
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Wed, 1 Apr 2020 12:34:33 +0000 (13:34 +0100)]
aco: add byte_align_scalar() & trim_subdword_vector() helper functions
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Fri, 28 Feb 2020 19:17:44 +0000 (20:17 +0100)]
aco: add missing conversion operations for small bitsizes
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Tue, 25 Feb 2020 10:52:08 +0000 (11:52 +0100)]
aco: don't vectorize 8/16bit load/store_ssbo
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Thu, 27 Feb 2020 12:06:36 +0000 (13:06 +0100)]
aco: don't assume split_vector(create_vector) has the same number of elements when optimizing
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Fri, 21 Feb 2020 16:06:32 +0000 (17:06 +0100)]
aco: don't propagate SGPRs into subdword PSEUDO instructions
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Thu, 27 Feb 2020 12:07:21 +0000 (13:07 +0100)]
aco: lower subdword shuffles correctly.
Note that subdword swaps are not yet implemented
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Thu, 27 Feb 2020 12:04:39 +0000 (13:04 +0100)]
aco: add builder function for subdword copy()
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Thu, 20 Feb 2020 10:34:40 +0000 (11:34 +0100)]
aco: small refactoring of shuffle code lowering
Uses now bytes instead of 32bit size
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Wed, 25 Mar 2020 11:06:41 +0000 (12:06 +0100)]
aco: align subdword registers during RA when necessary
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Tue, 25 Feb 2020 20:40:38 +0000 (21:40 +0100)]
aco: adapt register allocation for subdword registers
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Thu, 2 Apr 2020 18:13:03 +0000 (19:13 +0100)]
aco: create helper function to collect variables from register area
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Thu, 2 Apr 2020 17:27:50 +0000 (18:27 +0100)]
aco: add notion of subdword registers to register allocator
To not having to split the register file into single bytes,
we maintain a map with registers which contain subdword variables.
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Thu, 2 Apr 2020 17:07:22 +0000 (18:07 +0100)]
aco: remove unnecessary reg_file.fill() operation in get_reg_create_vector()
No pipelinedb changes
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Wed, 25 Mar 2020 11:15:54 +0000 (12:15 +0100)]
aco: fix Temp and assignment of renamed operands during RA
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Wed, 25 Mar 2020 10:32:18 +0000 (11:32 +0100)]
aco: print subdword registers
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Wed, 25 Mar 2020 10:32:47 +0000 (11:32 +0100)]
aco: validate RA of subdword assignments
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Wed, 25 Mar 2020 10:03:33 +0000 (11:03 +0100)]
aco: validate uninitialized operands
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Tue, 24 Mar 2020 17:24:23 +0000 (18:24 +0100)]
aco: validate register alignment of subdword operands and definitions
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Thu, 27 Feb 2020 12:08:45 +0000 (13:08 +0100)]
aco: validate p_create_vector with subdword elements properly
Also allows for undef operands
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Wed, 19 Feb 2020 08:39:42 +0000 (09:39 +0100)]
aco: refactor regClass setup for subdword VGPRs
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Rhys Perry [Fri, 7 Feb 2020 12:08:09 +0000 (12:08 +0000)]
aco: add emission support for register-allocated sdwa sels
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Mon, 17 Feb 2020 16:34:45 +0000 (17:34 +0100)]
aco: add sub-dword regclasses
Co-authored-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Rhys Perry [Thu, 30 Jan 2020 11:41:34 +0000 (11:41 +0000)]
aco: print and validate opsel
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Rhys Perry [Wed, 4 Dec 2019 20:18:05 +0000 (20:18 +0000)]
aco: add SDWA_instruction
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Thu, 27 Feb 2020 12:05:24 +0000 (13:05 +0100)]
aco: add comparison operators for PhysReg
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Rhys Perry [Fri, 7 Feb 2020 11:55:43 +0000 (11:55 +0000)]
aco: make PhysReg in units of bytes
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Daniel Schürmann [Fri, 14 Feb 2020 09:12:03 +0000 (10:12 +0100)]
nir: fix unpack_64_4x16 in lower_alu_to_scalar()
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-By: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4002>
Lionel Landwerlin [Fri, 3 Apr 2020 12:13:43 +0000 (15:13 +0300)]
drm-shim: stub libdrm's use of realpath()
libdrm started using realpath to get the type of bus associated with a
given device. This stubs the very specific usage that prevents
drm-shim's device from being listed.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4429>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4429>
Lionel Landwerlin [Mon, 10 Feb 2020 14:15:58 +0000 (16:15 +0200)]
drm-shim: return device platform as specified
v2: Embed the libdrm dependency inside the drm-shim dependency
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Acked-by: Eric Anholt <eric@anholt.net> (v1)
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/4429>
Jason Ekstrand [Thu, 13 Feb 2020 05:30:58 +0000 (23:30 -0600)]
spirv: Rewrite CFG construction
This commit completely rewrites the way we extract a structured CFG from
SPIR-V. The new approach is different in a few ways:
1. It does a breadth-first search instead of depth-first. This means
that we've visited the merge node for a construct before we visit
any of the nodes inside the construct. This makes it easier to
validate things like loop and switch nesting.
2. We record more information in the CFG. Earlier commits added a
parent pointer to vtn_cf_node but we now record all of the merge and
other special blocks for each CFG node. This lets us validate
things more precisely.
3. It makes heavy use of merge blocks for walking the CFG. Previously,
we sort of used them as hints for trying to guess the CFG structure
but things got dicey whenever a merge was missing. We had some
heuristics for how to handle short-circuiting if statements but it
was a bunch of special cases.
Now, we make them a fundamental part of walking the CFG. When we
encounter a control-flow construct, we add the body components of
the construct to the BFS work list and then jump to the merge block
if one exists to continue scanning the current CFG nesting level.
If no merge block exists, we assume that means that control-flow
never re-converges in a normal way and that the only way to get back
to normality is with a direct jump such as a loop break or continue.
This should make things far more robust when trying to deal with the
more creative placement (or lack thereof) of merge instructions.
Reviewed-by: Alan Baker <alanbaker@google.com>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3820>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3820>
Jason Ekstrand [Wed, 12 Feb 2020 21:31:50 +0000 (15:31 -0600)]
spirv: Add a parent field to vtn_cf_node
This makes it easier to crawl up the CF tree when trying to validate the
incoming SPIR-V control-flow.
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3820>
Jason Ekstrand [Wed, 12 Feb 2020 21:28:46 +0000 (15:28 -0600)]
spirv: Make vtn_function a vtn_cf_node
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3820>
Jason Ekstrand [Wed, 12 Feb 2020 21:19:20 +0000 (15:19 -0600)]
spirv: Make vtn_case a vtn_cf_node
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3820>
Jason Ekstrand [Wed, 12 Feb 2020 21:00:30 +0000 (15:00 -0600)]
spirv: Add cast and loop helpers for vtn_cf_node
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3820>
Jason Ekstrand [Wed, 12 Feb 2020 20:00:23 +0000 (14:00 -0600)]
spirv: Add a vtn_block() helper
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3820>
projects / mesa.git / log