AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
201,327 Commits 1 Branch 0 Tags
09b5de379cd47a025662459d03aed970da170676
Commit Graph

186467 Commits

Author SHA1 Message Date
Alyssa Rosenzweig bd89279dd4 nir: add lower_scratch_to_var pass 
to ease opencl pain.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32529>
 2024-12-12 21:16:13 +00:00
Alyssa Rosenzweig d5a4aa756f asahi: use mesa_prim_has_adjacency 
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32529>
 2024-12-12 21:16:13 +00:00
Alyssa Rosenzweig 8abb043c19 compiler: add mesa_prim_has_adjacency helper 
hk will use this, it's a pretty obvious thing to want.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32529>
 2024-12-12 21:16:12 +00:00
Alyssa Rosenzweig e4f61771d8 compiler: use libcl.h for CL 
instead of redefining BITFIELD_BIT.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32529>
 2024-12-12 21:16:12 +00:00
Alyssa Rosenzweig d695c84829 libagx: port to common libcl.h 
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32529>
 2024-12-12 21:16:12 +00:00
Alyssa Rosenzweig a0694fd5c3 libagx: drop pointless helper 
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32529>
 2024-12-12 21:16:12 +00:00
Alyssa Rosenzweig c34635c58d agx: implement halts 
just translate to a stop. seems to work fine.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32529>
 2024-12-12 21:16:12 +00:00
Alyssa Rosenzweig 21c16fe343 asahi,hk: wire up printf, abort 
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32529>
 2024-12-12 21:16:12 +00:00
Lionel Landwerlin 36623697d1 hk: fix timeline value type 
Signed-off-by: Lionel Landwerlin <llandwerlin@gmail.com>
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32529>
 2024-12-12 21:16:12 +00:00
Alyssa Rosenzweig dd4805fcc8 asahi/clc: remap __FILE__ 
important for reproducability. wondering if we can do this in common code but
not sure how yet.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32529>
 2024-12-12 21:16:12 +00:00
Alyssa Rosenzweig bfe1fd737b asahi: allow c23 extensions 
hk already does. this quiesches warnings with single argument static_assert
which we want for CL parity.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32529>
 2024-12-12 21:16:12 +00:00
Alyssa Rosenzweig 13a4186c96 util/bitpack_helpers: make partially CL safe 
add enough preprocessor guards that we can include this from CL and get basic
implementations of things. FIXED packs are missing due to llroundf (probably
fixable).

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32529>
 2024-12-12 21:16:12 +00:00
Alyssa Rosenzweig d64caf4161 libcl: add VkDraw(Indexed)IndirectCommand definitions 
this is helpful to indirect draw munging code, which applies to at least 3
stacks using driver CL stuff (current Intel, shortterm Asahi, mediumterm
Panfrost)

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32529>
 2024-12-12 21:16:12 +00:00
Alyssa Rosenzweig 12e27497b3 libcl: add a common header for CPU/GPU stuff 
In an attempt to make OpenCL shaders more "batteries included", start building
up a standard library. Based on libagx.h.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32529>
 2024-12-12 21:16:12 +00:00
Alyssa Rosenzweig 13b8af95fb clc: plumb cl_khr_subgroup_ballot 
although rusticl isn't lighting it up yet, it's helpful to get
sub_group_ballot for driver CL, which is all standard Vulkan-compatible spirv.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32529>
 2024-12-12 21:16:12 +00:00
Paulo Zanoni d4a54d4f92 brw: don't read past the end of old_src buffer in resize_sources() 
In this case, num_sources is bigger than this->sources, so if we loop
up to num_sources (instead of this->sources) we'll end up reading past
the end of old_src[]. Only copy up to what we originally had.

This was found by code inspection, I'm not aware of any applications
failing due to the lack of this patch.

Fixes: d9e737212d ("intel/brw: Add a src array for the common case in fs_inst")
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32600>
 2024-12-12 20:33:13 +00:00
Samuel Pitoiset c7a7f0244f radv: add radv_lower_terminate_to_discard and enable for Indiana Jones 
To workaround game bug.

This fixes the rendering issue with eyes.

Cc: mesa-stable
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32606>
 2024-12-12 19:54:39 +00:00
Samuel Pitoiset 4d4418dbb3 spirv: add an options to lower SpvOpTerminateInvocation to OpKill 
To workaround game bugs like Indiana Jones.

Original workaround found by Hans-Kristian.

Cc: mesa-stable
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32606>
 2024-12-12 19:54:39 +00:00
Erik Faye-Lund 976eb6825e panvk: do not require opt-in for panvk on v10 
As of writing, PanVK on v10 HW is in pretty good shape. It's not yet
conformant, but we were passing over 99.9% of the CTS last time I
checked. That's probably good enough to drop the opt-in here.

Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32561>
 2024-12-12 19:32:06 +00:00
Erik Faye-Lund 12067727fa panvk: soften the language around opt-in 
We already have and use vk_warn_non_conformant_implementation(), so
we're already being clear that PanVK is not yet conformant. Let's not
repeat that information here, and instead focus on it not being
well-tested.

This brings the wording more or less in-line with NVK.

Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32561>
 2024-12-12 19:32:06 +00:00
Timur Kristóf deab81fb0d radv: Configure implicit VS primitive ID to be per-primitive. 
This is beneficial to applications that rely on
the implicit primitive ID from VS.

- We don't have to disable provoking vertex reuse,
  which results in more efficient vertex processing.
- There is no LDS access needed to export the primitive ID,
  because it is already available to GS threads.
- As a consequence of not needing LDS, we can use this
  together with NGG passthrough mode.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32270>
 2024-12-12 18:11:47 +00:00
Timur Kristóf 95ac0f8d76 radv: Reorder FS primitive ID input after layer and viewport. 
We want to make the implicit VS primitive ID a per-primitive
output attribute, which means that this has to be last.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32270>
 2024-12-12 18:11:47 +00:00
Timur Kristóf 9224b9a752 ac/nir/ngg: Add ability to store primitive ID as per-primitive. 
This configuration will be enabled in RADV in a subsequent commit.

On GFX10.3:
Do this together with the primitive export, to avoid adding extra
CF, and to ensure optimal access of the export space.

On GFX11:
It's not an export but a memory store instruction, so always do
it earlier and ensure the optimal attribute ring access pattern.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32270>
 2024-12-12 18:11:45 +00:00
Timur Kristóf d670dc0c0b radv: Only set NGG_DISABLE_PROVOK_REUSE for VS. 
It doesn't do anything useful for other stages.

In VS, we use this when the implicit primitive ID is needed,
so that we can export that as a per-vertex attribute of the
provoking vertex.

In TES, the patch ID (which is used as the primitive ID) is
already a per-vertex input VGPR, so it doesn't make sense to
configure this.

In GS, the primitive ID is explicitly written by the shader,
so it makes no sense to disable provoking vertex reuse in the
input.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32270>
 2024-12-12 18:11:45 +00:00
Rhys Perry 9fe92689cc radv: increase maxComputeWorkGroupCount[0] 
Match AMDVLK and radeonsi.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32577>
 2024-12-12 17:38:47 +00:00
Rhys Perry 53d0187bab aco: decrease max_workgroup_size 
Match the limit of radeonsi and RADV.

No fossil-db changes.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32577>
 2024-12-12 17:38:46 +00:00
Rhys Perry 87f2f77960 aco: fix max_workgroup_count[0] 
This is necessary for radeonsi.

fossil-db (navi21):
Totals from 292 (0.37% of 79395) affected shaders:
Instrs: 305965 -> 306182 (+0.07%); split: -0.00%, +0.07%
CodeSize: 1624816 -> 1627212 (+0.15%); split: -0.00%, +0.15%
Latency: 5244652 -> 5243587 (-0.02%); split: -0.07%, +0.05%
InvThroughput: 1221089 -> 1225285 (+0.34%); split: -0.04%, +0.38%
Copies: 22712 -> 22702 (-0.04%)
PreSGPRs: 10713 -> 10712 (-0.01%)
PreVGPRs: 10918 -> 10920 (+0.02%)
VALU: 178613 -> 178836 (+0.12%)
SALU: 43490 -> 43493 (+0.01%); split: -0.02%, +0.03%

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32577>
 2024-12-12 17:38:46 +00:00
Lionel Landwerlin e0b5179869 blorp: use 2D dimension for 1D tiled images 
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: 31eeb72e45 ("blorp: Add support for blorp_copy via XY_BLOCK_COPY_BLT")
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32608>
 2024-12-12 17:10:45 +00:00
Erik Faye-Lund cfb5687cb3 panvk: disable imageCubeArray on bifrost 
We haven't wired this up correctly on Bifrost, so let's make this V10
only for now.

Fixes: 605c173fbd ("panvk: update feature support")
Reviewed-by: Eric R. Smith <eric.smith@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32610>
 2024-12-12 15:10:26 +00:00
Erik Faye-Lund 1766e676fe panvk: do not expose subgroup support 
We don't currently support it in the compiler, so we shouldn't claim
support for it either.

Fixes: a6e03ce428 ("panvk: advertise version 1.1 support")
Acked-by: Mary Guillemard <mary.guillemard@collabora.com>
Acked-by: Eric R. Smith <eric.smith@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32604>
 2024-12-12 14:50:25 +00:00
Hans-Kristian Arntzen e815d6523c radv: Add radv_invariant_geom=true for Indiana Jones. 
Water puddles expect invariant position, but does not declare such in
the vertex shaders, leading to random glitches.

Signed-off-by: Hans-Kristian Arntzen <post@arntzen-software.no>
Cc: mesa-stable
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32607>
 2024-12-12 13:54:27 +00:00
Eric R. Smith f8bc6c8663 panfrost: fix potential memory leak 
In the very unlikely case that the packed AFBC image will not
save (enough) memory, we abort packing. In this case we should
free the BO associated with the metadata.

Fixes: 5a928f7563 ("panfrost: Add env variable for max AFBC packing ratio")
Reviewed-by: Louis-Francis Ratté-Boulianne <lfrb@collabora.com>
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32597>
 2024-12-12 13:08:28 +00:00
Eric R. Smith b59e73e426 panfrost: fix read/write resource confusion in afbc_pack 
We read the source rather than write it, due to a typo we were
not setting this correctly though.

Fixes: bc55d150a9 ("panfrost: Add support for AFBC packing")
Reviewed-by: Louis-Francis Ratté-Boulianne <lfrb@collabora.com>
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32597>
 2024-12-12 13:08:28 +00:00
Christian Gmeiner 2ebd5fb978 etnaviv: rs: Add DBG(..) why blt usage was not possible 
Can be helpful to debug issues.

Signed-off-by: Christian Gmeiner <cgmeiner@igalia.com>
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32592>
 2024-12-12 12:52:37 +00:00
Christian Gmeiner faf562651a etnaviv: blt: Add DBG(..) why blt usage was not possible 
Can be helpful to debug issues.

Signed-off-by: Christian Gmeiner <cgmeiner@igalia.com>
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32592>
 2024-12-12 12:52:37 +00:00
Konstantin 815ca049cd vulkan: Fix the argument order of update_as 
Also moves the src argument before dst which is more consistent.

Reviewed-by: Friedrich Vock <friedrich.vock@gmx.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32488>
 2024-12-12 11:15:08 +00:00
Valentine Burley 8e54b77910 panfrost/ci: Convert to deqp-runner suite 
Convert the panfrost-g52-piglit-gles2:arm64 job to a deqp-runner
suite.

Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32461>
 2024-12-12 10:35:41 +00:00
Valentine Burley ca7df52af8 svga/ci: Convert to deqp-runner suite 
Convert the vmware-vmx-piglit:x86_64 job to a deqp-runner suite.

Signed-off-by: Valentine Burley <valentine.burley@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32461>
 2024-12-12 10:35:40 +00:00
Samuel Pitoiset 370886c898 Revert "radv: disable alphaToOne except for Zink" 
This reverts commit 3b010a9e60.

This should be fixed properly now.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32583>
 2024-12-12 10:07:25 +00:00
Samuel Pitoiset c3a050da07 radv: fix alpha-to-coverage with alpha-to-one without MRTZ 
This injects a MRTZ export with only the alpha channel to select it
with COVERAGE_TO_MASK_ENABLE for alpha-to-coverage.

Co-Authored-by: Rhys Perry <pendingchaos02@gmail.com>
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32583>
 2024-12-12 10:07:25 +00:00
Samuel Pitoiset 838b1cfcbd radv: simplify determining some fragment shader info with epilogs 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32583>
 2024-12-12 10:07:25 +00:00
Collabora's Gfx CI Team 8085984aa2 Uprev Piglit to 4c0fd15fd956ec70c5509bedee219d602b334464 
https://gitlab.freedesktop.org/mesa/piglit/-/compare/468221c722481c470e6a23760b914c33143c2af6...4c0fd15fd956ec70c5509bedee219d602b334464

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32478>
 2024-12-12 09:33:59 +00:00
Samuel Pitoiset 4d1aa9a2d0 radv: fix disabling DCC for stores with drirc 
Displayable DCC should also be disabled, otherwise it's asserting
somewhere in ac_surface.c

Fixes: e3d1f27b31 ("radv: add radv_disable_dcc_stores and enable for Indiana Jones: The Great Circle")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32584>
 2024-12-12 09:11:37 +00:00
Daniel Schürmann 26a3038b65 aco/lower_branches: remove edges between blocks if there is no direct branch 
This way, linear predecessors and successors better reflect the
actual control flow which improves wait state insertion and hazard
mitigation.

Totals from 10252 (12.91% of 79395) affected shaders: (Navi31)

Instrs: 18824540 -> 18803823 (-0.11%); split: -0.11%, +0.00%
CodeSize: 99025464 -> 98942028 (-0.08%); split: -0.08%, +0.00%
Latency: 169291854 -> 165781877 (-2.07%); split: -2.07%, +0.00%
InvThroughput: 29701086 -> 29228602 (-1.59%); split: -1.59%, +0.00%
SClause: 510587 -> 510586 (-0.00%)
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32389>
 2024-12-12 08:46:22 +00:00
Daniel Schürmann 22ffe72022 aco: move branch lowering optimization into separate file 'aco_lower_branches.cpp' 
No fossil changes.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32389>
 2024-12-12 08:46:22 +00:00
Friedrich Vock 845660f2b7 aco/lower_to_hw_instr: Check the right instruction's opcode 
instr is the branch instruction, its opcode won't ever be writelane. We
should check inst instead.

Found by inspection.

Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32389>
 2024-12-12 08:46:21 +00:00
Daniel Schürmann 28ab7f0168 aco/jump_threading: remove branch sequence optimization 
This optimization gets applied during postRA optimization, now.

No fossil changes.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32330>
 2024-12-12 08:11:22 +00:00
Daniel Schürmann fcd94a8ca7 aco: move try_optimize_branching_sequence() to postRA optimizations 
Totals from 196 (0.25% of 79206) affected shaders: (Navi31)

Instrs: 534343 -> 534438 (+0.02%); split: -0.00%, +0.02%
CodeSize: 2774852 -> 2775420 (+0.02%); split: -0.00%, +0.02%
Latency: 7103512 -> 7103021 (-0.01%); split: -0.01%, +0.00%
InvThroughput: 959477 -> 959447 (-0.00%)
Copies: 42646 -> 42648 (+0.00%)
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32330>
 2024-12-12 08:11:21 +00:00
Daniel Schürmann 95d44c7ce0 aco/optimizer_postRA: set branch()->never_taken if exec is constant non-zero 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32330>
 2024-12-12 08:11:21 +00:00
Daniel Schürmann d67932f69e aco/print_ir: don't print disconnected empty blocks 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32330>
 2024-12-12 08:11:21 +00:00