AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
180,023 Commits 1 Branch 0 Tags
21d3c1e0afbab334b9f356f8ea97054fe3dec676
Commit Graph

180023 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Alyssa Rosenzweig 21d3c1e0af asahi: Use the sampler heap 
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:55 +00:00
Alyssa Rosenzweig dc44619c62 asahi: Add sampler heap data structure 
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:55 +00:00
Alyssa Rosenzweig 9c575eb18a asahi: Handle load_sampler_handle 
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:55 +00:00
Alyssa Rosenzweig df2c145c91 agx: Handle bindless samplers 
Unified encoding.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:55 +00:00
Alyssa Rosenzweig ca42562c7f agx: Lower LOD bias earlier 
To make the extra descriptor accesses explicit for drivers.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:55 +00:00
Alyssa Rosenzweig 972f289740 asahi: Lower samplers to bindless if needed 
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:55 +00:00
Alyssa Rosenzweig 111e526f19 agx: Allow drivers to lower texture handles 
Rather than hardcoding u0_u1, this lets drivers map texture handles in whatever
way is convenient. In particular, this makes textures work properly with merged
shader stages (provided one of the stages is forced to use bindless access), by
giving each stage an independent texture heap.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:55 +00:00
Alyssa Rosenzweig b69ab37bdc asahi: Pack non-border colour sampler desc 
Apparently custom border colours don't work properly with bindless. Needs
investigation. Patch this out so we don't fault.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:55 +00:00
Alyssa Rosenzweig a74fbb3840 agx: Translate simple subgroup ops 
We'll use these for optimizing parallel prefix sums.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:55 +00:00
Alyssa Rosenzweig 77bb446e90 agx: Add scaffolding for subgroup ops 
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:55 +00:00
Alyssa Rosenzweig 5b754410da agx: Require 32-bit alignment for EOT offset 
Fixes piles of brokenness.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:55 +00:00
Alyssa Rosenzweig 7d7f5013f8 agx: Cleanup 8-bit math before lowering 
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:55 +00:00
Alyssa Rosenzweig 3b84f371a8 docs/features: Mark ARB_mdi done on asahi 
Sync with reality.

I think all gallium drivers support, it's a cpu-only thing unlike gl4.6's
indirect multidraws or the similarly named vk feature.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:55 +00:00
Alyssa Rosenzweig b18181d924 agx: Check for spilling in release builds 
Don't smash stack -- explain to the user what happened.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:55 +00:00
Alyssa Rosenzweig 7b92c63105 agx: Fix fragment side effects scheduling 
We can't move discards across side effects, or the side effect might not happen.

Fixes KHR-GLES31.core.shader_image_load_store.basic-allFormats-load-fs
regression. Sigh.

CI is up next.

Fixes: 119e5b9719 ("agx: Schedule for register pressure")
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:55 +00:00
Christian Gmeiner e928f45735 agx: Re-index nir defs to reduce memory usage 
nir_index_ssa_defs(..) will re-index the function impl and will
update ssa_alloc. In almost all cases this will result in a lower
ctx->alloc number which reduces memory usage in compiler passes
that are using ctx-alloc to allocate memory.

Signed-off-by: Christian Gmeiner <cgmeiner@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:54 +00:00
Alyssa Rosenzweig b6b01aa1f2 agx: Legalize image MS index 
Fix 2D MSAA Array tests in arb_shader_image_load_store-max-size

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:54 +00:00
Alyssa Rosenzweig 019a52fff0 asahi: Clamp 8-bit integer RTs 
Fixes gl-3.0-render-integer.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:54 +00:00
Alyssa Rosenzweig 8d9d9d0207 nir/print: handle adjacency 
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Antonino Maniscalco <antonino.maniscalco@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:54 +00:00
Alyssa Rosenzweig d0a4a8cda0 nir: Add intrinsics for lowering bindless textures/samplers 
Needed for merged stages to work properly.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Antonino Maniscalco <antonino.maniscalco@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:54 +00:00
Alyssa Rosenzweig 33e80918de nir: Add intrinsics for lowering GS 
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Antonino Maniscalco <antonino.maniscalco@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:54 +00:00
Alyssa Rosenzweig cc3f20ca6c nir: Also gather decomposed primitive count 
Simple extension.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Antonino Maniscalco <antonino.maniscalco@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:54 +00:00
Alyssa Rosenzweig b65636ca40 nir/lower_gs_intrinsics: Count decomposed primitives too 
We need both: decomposed primitives for transform feedback and regular
primitives for the sizing the index buffer.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Antonino Maniscalco <antonino.maniscalco@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:54 +00:00
Alyssa Rosenzweig 0a35aa3a2b nir/lower_gs_intrinsics: Append EndPrimitive 
This is simpler for generic GS lowering.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Antonino Maniscalco <antonino.maniscalco@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:54 +00:00
Alyssa Rosenzweig f157a3de4e nir/lower_gs_intrinsics: Include primitive counts 
Generic GS lowering needs this, we already calculate it.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Antonino Maniscalco <antonino.maniscalco@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:54 +00:00
Alyssa Rosenzweig a147801f9b compiler: Make u_decomposed_prims_for_vertices available to CL 
For indirect geometry shader setup.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Antonino Maniscalco <antonino.maniscalco@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:54 +00:00
Alyssa Rosenzweig 64f7b70763 compiler: Inline mesa_vertices_per_prim 
Makes it more easily consumable from the gpu.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Antonino Maniscalco <antonino.maniscalco@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:54 +00:00
Alyssa Rosenzweig 7cfe2ecb33 compiler: Make shader_enums.h CL-safe 
macros.h is not safe for CL for a bunch of reasons but shader_enums.h barely
uses its functionality. Stub out the minimum for CL.

Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Antonino Maniscalco <antonino.maniscalco@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26056>
 2023-11-07 00:05:54 +00:00
Karol Herbst 1519ff7ebd rusticl/memory: fix new clippy::needless-borrow warning 
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Antonio Gomes <antoniospg100@gmail.com>
Reviewed-by: @LingMan <18294-LingMan@users.noreply.gitlab.freedesktop.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26051>
 2023-11-06 23:47:18 +00:00
Karol Herbst 98df65a875 rusticl: only support the matching device for gl_sharing 
Cross vendor is bogus because of modifier screw ups. We could allow it on
all devices from the same vendor, but for that we have to check if the
supported modifiers match.

Also verify the device in questions actually supports gl_sharing.

Fixes: 57dfc013a6 ("rusticl: Add functions to create CL ctxs from GL, and also to query them")
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Antonio Gomes <antoniospg100@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26051>
 2023-11-06 23:47:18 +00:00
Georg Lehmann 6cd78281f6 aco: deduplicate Format definition 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25943>
 2023-11-06 23:16:38 +00:00
Georg Lehmann 6e0bf33a89 aco: deduplicate instr_class definition 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25943>
 2023-11-06 23:16:38 +00:00
Georg Lehmann bdd81c6be7 aco: namespace aco_opcode 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25943>
 2023-11-06 23:16:38 +00:00
Georg Lehmann 1b9a3b7466 aco: stop using cstdint 
We use stdint.h everywhere else.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25943>
 2023-11-06 23:16:38 +00:00
Georg Lehmann 04956d54ce aco: force uniform result for LDS load with uniform address if it can be non uniform 
Because a LDS load is 2 separate loads on gfx10+ with wave64, a different wave
can write LDS in between and cause a non uniform result. Use v_readfirst_lane
instead of p_as_uniform because it cannot be copy propagated.

Fixes a OpenCL CTS test with zink+rusticl.

Totals from 136 (0.17% of 78196) affected shaders:
MaxWaves: 3236 -> 3244 (+0.25%)
Instrs: 130069 -> 131221 (+0.89%)
CodeSize: 698048 -> 703436 (+0.77%)
VGPRs: 5464 -> 5440 (-0.44%)
SpillSGPRs: 94 -> 96 (+2.13%)
Latency: 5361017 -> 5363781 (+0.05%); split: -0.00%, +0.05%
InvThroughput: 883010 -> 884100 (+0.12%)
SClause: 3822 -> 3821 (-0.03%); split: -0.05%, +0.03%
Copies: 14220 -> 14314 (+0.66%); split: -0.01%, +0.68%
Branches: 4549 -> 4551 (+0.04%)
PreSGPRs: 4934 -> 4940 (+0.12%)
PreVGPRs: 4666 -> 4655 (-0.24%)

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25973>
 2023-11-06 22:43:33 +00:00
Eric Engestrom a4597777fe ci: restore sanity (aka. Revert "ci: don't run sanity in Marge pipelines") 
This reverts commit fac60c140b.

Turns out there are pipelines that do not create any other jobs, and
Marge requires a pipeline to pass, which means a pipeline needs to
exist, which means a job needs to always exist.

There is no reason `sanity` would be the one, but it's there so let's
just use it instead of making another one.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26080>
 2023-11-06 21:49:44 +00:00
Georg Lehmann ab87831ae8 aco, radv: vectorize f2f16 if rounding mode is rtz 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25952>
 2023-11-06 21:05:34 +00:00
Eric Engestrom b781bd478c zink+radv/ci: ensure renderer is "zink on radv" 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26065>
 2023-11-06 18:54:37 +00:00
Eric Engestrom cd600868b4 zink+radv/ci: simplify deqp config 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26065>
 2023-11-06 18:54:37 +00:00
Andrew Gazizov d1009481c8 venus: Add use_guest_vram capset to enable guest-based blob alloc 
For hypervisors that do not support host memory injection into the
guest address space, it's necessary to have guest-based blob alloc.
Therefore, use a new 'use_guest_vram' virgl capset to decide on
performing guest blob allocations from dedicated heap (Host visible
memory).

Signed-off-by: Andrew D. Gazizov <andrew.gazizov@opensynergy.com>
Reviewed-by: Yiwei Zhang <zzyiwei@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25889>
 2023-11-06 18:33:15 +00:00
Mary Guillemard f71f5cf856 venus: skip bind sparse info when checking for feedback query 
Fix an assertion when using vkQueueBindSparse.

Fixes: 7fbf608f2d ("venus: append query feedback at submission time")
Signed-off-by: Mary Guillemard <mary.guillemard@collabora.com>
Reviewed-by: Juston Li <justonli@google.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26027>
 2023-11-06 18:15:03 +00:00
Vitaliy Triang3l Kuzmin bae7538a02 r600/sfn: Remove unused sampler reference in emit_tex_lod 
Signed-off-by: Vitaliy Triang3l Kuzmin <triang3l@yandex.ru>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26068>
 2023-11-06 16:47:29 +00:00
Vitaliy Triang3l Kuzmin 4f86353f4f r600/sfn: Change sampler_index to texture_index in buffer txs 
Signed-off-by: Vitaliy Triang3l Kuzmin <triang3l@yandex.ru>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26068>
 2023-11-06 16:47:29 +00:00
Connor Abbott 2e83aed8b3 vk/graphics_state: Add vk_pipeline_flags_feedback_loops helper 
This will be useful for combining dynamic and static feedback loop
state.

Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25436>
 2023-11-06 14:33:51 +00:00
Connor Abbott a02d1cfa9e vk/graphics_state: Support VK_EXT_attachment_feedback_loop_dynamic_state 
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25436>
 2023-11-06 14:33:51 +00:00
Connor Abbott 55f3f952aa vk/graphics_state, tu: Rewrite renderpass flags handling 
Before this, the render pass code or the driver combined the pipeline
create flags and the implicit flags from the render pass, but the
pipeline create flags will need to be sanitized when they are dynamic
state, so we need to do it in vk_graphics_state where we know that
information.

We also weren't combining pipeline flags correctly when linking, which
on turnip was being hidden by the lack of sanitizing for driver-provided
flags. We can't combine them correctly if they're part of the render
pass state, so they need to be pulled out into the overall pipeline
state.

For drivers using emulated renderpasses or tracking feedback loop
information themselves, this won't make a difference, but we have to
adapt turnip to not pass pipeline flags. This also means that we can
drop all handling of feedback_loop_input_only in turnip and just set it
in the runtime.

Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25436>
 2023-11-06 14:33:51 +00:00
Connor Abbott 2b62d90158 vk/graphics_state: Support VK_KHR_maintenance5 
Switch to using VkPipelineCreateFlags2KHR, and use the new common helper
to get the right flags.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25436>
 2023-11-06 14:33:51 +00:00
Connor Abbott e6f5d7222c vk,lvp,tu,radv,anv: Add common vk_*_pipeline_create_flags() helper 
And replace the various homegrown or copy-pasted helpers in drivers.

Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25436>
 2023-11-06 14:33:51 +00:00
Erik Faye-Lund cac194ff38 panfrost: look at correct blendable format version 
We're currently looking at a mixture of v7 only and v6 and v7 versions
of the blendable formats. Let's use the one we have stored, so we always
use the most recent definition.

Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25968>
 2023-11-06 14:30:34 +01:00
Erik Faye-Lund f277124544 panfrost: store blendable_formats in panfrost_device 
This way, we don't need to look at the generation to find the right
version. It's also less code to update when we're adding new hardware
generations.

Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25968>
 2023-11-06 14:30:31 +01:00