Daniel Schürmann [Tue, 25 Apr 2023 13:56:57 +0000 (15:56 +0200)]
radv/rt: refactor compute_rt_stack_size() to use radv_ray_tracing_stage information
instead of pStages.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22100>
Daniel Schürmann [Thu, 23 Mar 2023 14:18:29 +0000 (15:18 +0100)]
radv/rt: use precompiled stages to create RT shader
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22100>
Daniel Schürmann [Thu, 23 Mar 2023 01:23:55 +0000 (02:23 +0100)]
radv/rt: retain parsed NIR shaders in radv_ray_tracing_lib_pipeline
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22100>
Daniel Schürmann [Tue, 25 Apr 2023 12:38:15 +0000 (14:38 +0200)]
radv/rt: introduce struct radv_ray_tracing_stage
The purpose of this struct is to bundle per-stage information
for ray-tracing pipelines.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22100>
Daniel Schürmann [Wed, 8 Mar 2023 03:25:05 +0000 (04:25 +0100)]
radv/rt: expose radv_parse_rt_stage()
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22100>
Daniel Schürmann [Fri, 31 Mar 2023 14:05:22 +0000 (16:05 +0200)]
radv/pipeline_cache: add NIR caching capabilities
This patch adds functions to radv_pipeline_cache in order to cache
serialized NIR shaders as opaque cache objects.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22100>
Daniel Schürmann [Wed, 26 Apr 2023 13:51:20 +0000 (15:51 +0200)]
vulkan/pipeline_cache: expose vk_raw_data_cache_object
together with vk_raw_data_cache_object_ops and vk_raw_data_cache_object_create().
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22100>
Karol Herbst [Wed, 26 Apr 2023 20:06:44 +0000 (22:06 +0200)]
nvc0: do not randomly emit fences.
We track fences in a global list and have a per context "current" fence
which we randomly attach things to. If we take such a fence and emit it
without also creating a new fence for future tasks we can get out of sync
leading to random failures.
Some of our queries could trigger such cases and even though this issues
appears to be triggered by the MT rework, I'm convinced that this was only
made more visible by those fixes and we had this bug lurking for quite a
while.
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/7429
Fixes:
df0a4d02f26 ("nvc0: make state handling race free")
Signed-off-by: Karol Herbst <git@karolherbst.de>
Acked-by: M Henning <drawoc@darkrefraction.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22722>
Corentin Noël [Wed, 26 Apr 2023 13:51:15 +0000 (15:51 +0200)]
ci: Uprev crosvm and virglrenderer
Update crosvm, virglrenderer and bindgen-cli to their latest version on time.
Signed-off-by: Corentin Noël <corentin.noel@collabora.com>
Reviewed-by: Yiwei Zhang <zzyiwei@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22712>
Lionel Landwerlin [Tue, 2 May 2023 09:06:59 +0000 (12:06 +0300)]
nir/lower_non_uniform_access: add get_ssbo_size handling
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22793>
Karol Herbst [Sun, 30 Apr 2023 23:22:56 +0000 (01:22 +0200)]
rusticl/nir: finish blob after serializing
Signed-off-by: Karol Herbst <git@karolherbst.de>
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22776>
Karol Herbst [Sun, 30 Apr 2023 23:22:14 +0000 (01:22 +0200)]
clc: free kernel args in clc_free_kernels_info
Signed-off-by: Karol Herbst <git@karolherbst.de>
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22776>
Daniel Schürmann [Thu, 27 Apr 2023 13:24:55 +0000 (15:24 +0200)]
radv: add padding to radv_shader_binary_legacy
This fixes an alignment mismatch in radv_shader_serialize()
Fixes:
577d76f60f788c3a8d43b4b388bb5a04e4e64994 ('radv: add radv_shader_serialize() and radv_shader_deserialize() functions')
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22735>
Daniel Schürmann [Thu, 27 Apr 2023 13:20:06 +0000 (15:20 +0200)]
vulkan/pipeline_cache: use vk_pipeline_cache_insert_object() to replace raw data objects
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22735>
Daniel Schürmann [Thu, 27 Apr 2023 13:13:51 +0000 (15:13 +0200)]
vulkan/pipeline_cache: replace raw data objects on cache insertion of real objects
It might happen that a raw data object (from pipeline cache creation)
was never looked up, and thus never deserialized, before it gets
inserted again into the cache. In this case, the deserialized object
got replaced by the raw data object.
Instead, replace the raw data object with the real object in the cache.
Fixes:
8b13ee75ba9f27ceac6b6180ca05d321caa13612 ('vulkan: Fall back to raw data objects when deserializing if ops == NULL')
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22735>
Christian Gmeiner [Tue, 25 Apr 2023 18:36:14 +0000 (20:36 +0200)]
etnaviv: Add util_blitter_save_so_targets(..) call
We do not support stream outputs yet so be better at faking it.
Fixes the following assertion when running deqp-gles3:
u_blitter.c:635: blitter_check_saved_vertex_states: Assertion `!ctx->has_stream_out || ctx->base.saved_num_so_targets != ~0u' failed
Signed-off-by: Christian Gmeiner <christian.gmeiner@gmail.com>
Reviewed-by: Lucas Stach <l.stach@pengutronix.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22754>
Matt Coster [Tue, 2 May 2023 10:37:59 +0000 (11:37 +0100)]
pvr: Correctly validate PBE accum format
Fixes: dEQP-VK.pipeline.monolithic.blend.format.e5b9g9r9_ufloat_pack32
.states
.color_sas_1mda_add_alpha_1msa_sas_rsub
-color_1mda_cc_min_alpha_cc_cc_min
-color_1mcc_1mca_rsub_alpha_1mca_1mda_min
-color_sc_1mda_sub_alpha_sa_cc_min
Signed-off-by: Matt Coster <matt.coster@imgtec.com>
Reported-by: James Glanville <james.glanville@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22795>
Rhys Perry [Mon, 1 May 2023 16:38:11 +0000 (17:38 +0100)]
radv: fix bc optimization with POS_W_FLOAT_ENA(1)
0286CC_PERSP_CENTER_ENA is also set if:
- No barycentrics are used
- POS_W_FLOAT is enabled
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Qiang Yu <yuq825@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Fixes:
a4b60295a79 ("aco,ac/llvm,radv,radeonsi: handle ps bc optimization in nir for radv")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/8928
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22782>
Matt Coster [Fri, 28 Apr 2023 14:00:21 +0000 (15:00 +0100)]
pvr: Unmap mapped memory on free
From the Vulkan spec (§11.2.13. Freeing Device Memory):
If a memory object is mapped at the time it is freed, it is implicitly
unmapped.
Signed-off-by: Matt Coster <matt.coster@imgtec.com>
Reviewed-by: Karmjit Mahil <Karmjit.Mahil@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22762>
Karmjit Mahil [Fri, 21 Apr 2023 15:13:24 +0000 (16:13 +0100)]
pvr: Fix unaligned VDMCTRL_PDS_STATE1 data address
For indirect draw commands the data segment's address was being
calculated with an unaligned code size which could potentially
send an unaligned address to the hw causing problems.
Reported-by: James Glanville <james.glanville@imgtec.com>
Signed-off-by: Karmjit Mahil <Karmjit.Mahil@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22746>
James Glanville [Tue, 25 Apr 2023 20:20:02 +0000 (21:20 +0100)]
pvr: Fix image to buffer copies
The code to increment the destination buffer address was wrong. Instead of
incrementing an address on every iteration, the buffer slice size was added
as a static offset to all blits.
Seen in dEQP-VK.draw.renderpass.depth_clamp.d16_unorm, though issues remain.
Signed-off-by: James Glanville <james.glanville@imgtec.com>
Signed-off-by: Karmjit Mahil <Karmjit.Mahil@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22747>
James Glanville [Fri, 28 Apr 2023 08:21:50 +0000 (09:21 +0100)]
pvr: Fix vtxin special var allocation count
When pvr_graphics_pipeline_alloc_vertex_special_vars() was
allocating vtxin regs for special vars, it wasn't returning back
the updated amount of allocated regs so when the PDS was filling
them in, it would try to write out of bounds.
Signed-off-by: James Glanville <james.glanville@imgtec.com>
Signed-off-by: Karmjit Mahil <Karmjit.Mahil@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22750>
James Glanville [Tue, 25 Apr 2023 21:41:51 +0000 (22:41 +0100)]
pvr: Improve support for image clears
Depth/stencil surfaces are not PBE renderable, so a compatible format must
be used instead. The code to calculate this compatible format was not called
when configuring the PBE, and it was missing formats.
Also the code to calculate PBE swizzles was throwing an error in unhandled
cases, rather than using the pre-calculated defaults which was the correct
behaviour.
Fixes blits in dEQP-VK.draw.renderpass.depth_clamp.d32_sfloat
Signed-off-by: James Glanville <james.glanville@imgtec.com>
Signed-off-by: Karmjit Mahil <Karmjit.Mahil@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22748>
Erik Faye-Lund [Sun, 30 Apr 2023 10:15:31 +0000 (12:15 +0200)]
nir: fix constant-folding of 64-bit fpow
We need to do full pow if 64-bit, and we can do fpow() otherwise. Not
the other way around.
Fixes:
9076c4e289d ("nir: update opcode definitions for different bit sizes")
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22774>
Samuel Pitoiset [Fri, 28 Apr 2023 16:13:19 +0000 (18:13 +0200)]
radv: fix dynamic depth clamp enable support
The Vulkan spec says:
"If the depth clamping state is changed dynamically, and the pipeline
was not created with VK_DYNAMIC_STATE_DEPTH_CLIP_ENABLE_EXT enabled,
then depth clipping is enabled when depth clamping is disabled and
vice versa"
Fixes:
e48c0fbd8f7 ("radv: add support for dynamic depth clamp enable")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22777>
Jesse Natalie [Mon, 1 May 2023 20:08:12 +0000 (13:08 -0700)]
microsoft/compiler: Unroll loops in opt passes
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22786>
Jesse Natalie [Mon, 1 May 2023 20:07:01 +0000 (13:07 -0700)]
spirv2dxil: Mark SSBO reads for bindless as CAN_REORDER
This makes it so that they can be CSE'd, which helps prevent redundant
reads of the same data.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22786>
Yiwei Zhang [Mon, 1 May 2023 16:58:11 +0000 (16:58 +0000)]
radv: respect VK_QUERY_RESULT_WAIT_BIT in GetQueryPoolResults
The flag was ignored for VK_QUERY_TYPE_TRANSFORM_FEEDBACK_STREAM_EXT and
VK_QUERY_TYPE_PRIMITIVES_GENERATED_EXT.
Cc: mesa-stable
Signed-off-by: Yiwei Zhang <zzyiwei@chromium.org>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22781>
Rob Clark [Mon, 1 May 2023 14:34:13 +0000 (07:34 -0700)]
Revert "ci: disable all a306/a530/a630 jobs"
This reverts commit
af214c233b8612e9b063b268219a655f29d9aad6.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22780>
Michel Dänzer [Fri, 21 Apr 2023 07:56:34 +0000 (09:56 +0200)]
ci: Enable rusticl in the fedora-release job
v2:
* Drop superfluous -D rust_std=2021 (Eric Engestrom)
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22718>
Michel Dänzer [Tue, 14 Mar 2023 08:50:34 +0000 (09:50 +0100)]
ci: Upgrade fedora-release job to Fedora 38
Need to add -Wno-error=dangling-reference -Wno-error=overloaded-virtual
for C++ for now.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22718>
Michel Dänzer [Thu, 27 Apr 2023 07:23:42 +0000 (09:23 +0200)]
ci: Drop -Wno-error=array-bounds from fedora-release job
No warnings left.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22718>
Michel Dänzer [Wed, 26 Apr 2023 09:05:47 +0000 (11:05 +0200)]
clover/llvm: Use std::nullopt already with LLVM 16
llvm::None is already deprecated and defined as std::nullopt in LLVM 16.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22718>
Michel Dänzer [Wed, 26 Apr 2023 07:30:05 +0000 (09:30 +0200)]
clover/llvm: Use llvm::DataLayout::getABITypeAlign with LLVM >= 16
llvm::DataLayout::getABITypeAlignment is deprecated:
../src/gallium/frontends/clover/llvm/codegen/common.cpp: In function ‘std::vector<clover::binary::argument> {anonymous}::make_kernel_args(const llvm::Module&, const std::string&, const clang::CompilerInstance&)’:
../src/gallium/frontends/clover/llvm/codegen/common.cpp:211:62: warning: ‘uint64_t llvm::DataLayout::getABITypeAlignment(llvm::Type*) const’ is deprecated: use getABITypeAlign instead [-Wdeprecated-declarations]
211 | const unsigned target_align = dl.getABITypeAlignment(arg_type);
| ~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~
In file included from /usr/include/llvm/IR/Module.h:24,
from ../src/gallium/frontends/clover/llvm/codegen.hpp:35,
from ../src/gallium/frontends/clover/llvm/codegen/common.cpp:36:
/usr/include/llvm/IR/DataLayout.h:527:12: note: declared here
527 | uint64_t getABITypeAlignment(Type *Ty) const;
| ^~~~~~~~~~~~~~~~~~~
../src/gallium/frontends/clover/llvm/codegen/common.cpp:232:53: warning: ‘uint64_t llvm::DataLayout::getABITypeAlignment(llvm::Type*) const’ is deprecated: use getABITypeAlign instead [-Wdeprecated-declarations]
232 | dl.getABITypeAlignment(size_type),
| ~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~
/usr/include/llvm/IR/DataLayout.h:527:12: note: declared here
527 | uint64_t getABITypeAlignment(Type *Ty) const;
| ^~~~~~~~~~~~~~~~~~~
../src/gallium/frontends/clover/llvm/codegen/common.cpp:240:53: warning: ‘uint64_t llvm::DataLayout::getABITypeAlignment(llvm::Type*) const’ is deprecated: use getABITypeAlign instead [-Wdeprecated-declarations]
240 | dl.getABITypeAlignment(size_type),
| ~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~
/usr/include/llvm/IR/DataLayout.h:527:12: note: declared here
527 | uint64_t getABITypeAlignment(Type *Ty) const;
| ^~~~~~~~~~~~~~~~~~~
../src/gallium/frontends/clover/llvm/codegen/common.cpp:262:92: warning: ‘uint64_t llvm::DataLayout::getABITypeAlignment(llvm::Type*) const’ is deprecated: use getABITypeAlign instead [-Wdeprecated-declarations]
262 | (pointee_type->isVoidTy()) ? 8 : dl.getABITypeAlignment(pointee_type),
| ~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~~~
/usr/include/llvm/IR/DataLayout.h:527:12: note: declared here
527 | uint64_t getABITypeAlignment(Type *Ty) const;
| ^~~~~~~~~~~~~~~~~~~
../src/gallium/frontends/clover/llvm/codegen/common.cpp:304:47: warning: ‘uint64_t llvm::DataLayout::getABITypeAlignment(llvm::Type*) const’ is deprecated: use getABITypeAlign instead [-Wdeprecated-declarations]
304 | dl.getABITypeAlignment(size_type),
| ~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~
/usr/include/llvm/IR/DataLayout.h:527:12: note: declared here
527 | uint64_t getABITypeAlignment(Type *Ty) const;
| ^~~~~~~~~~~~~~~~~~~
../src/gallium/frontends/clover/llvm/codegen/common.cpp:310:47: warning: ‘uint64_t llvm::DataLayout::getABITypeAlignment(llvm::Type*) const’ is deprecated: use getABITypeAlign instead [-Wdeprecated-declarations]
310 | dl.getABITypeAlignment(size_type),
| ~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~
/usr/include/llvm/IR/DataLayout.h:527:12: note: declared here
527 | uint64_t getABITypeAlignment(Type *Ty) const;
| ^~~~~~~~~~~~~~~~~~~
v2:
* Use compat helper function (Karol Herbst)
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22718>
Michel Dänzer [Tue, 25 Apr 2023 16:43:06 +0000 (18:43 +0200)]
svga: Make declaration of emit_input_declaration match definition
Pointed out by GCC 13:
../src/gallium/drivers/svga/svga_tgsi_vgpu10.c:3786:1: warning: conflicting types for ‘emit_input_declaration’ due to enum/integer mismatch; have ‘void(struct svga_shader_emitter_v10 *, VGPU10_OPCODE_TYPE, VGPU10_OPERAND_TYPE, VGPU10_OPERAND_INDEX_DIMENSION, unsigned int, unsigned int, VGPU10_SYSTEM_NAME, VGPU10_OPERAND_NUM_COMPONENTS, VGPU10_OPERAND_4_COMPONENT_SELECTION_MODE, unsigned int, VGPU10_INTERPOLATION_MODE, boolean, SVGA3dDXSignatureSemanticName)’ {aka ‘void(struct svga_shader_emitter_v10 *, VGPU10_OPCODE_TYPE, VGPU10_OPERAND_TYPE, VGPU10_OPERAND_INDEX_DIMENSION, unsigned int, unsigned int, VGPU10_SYSTEM_NAME, VGPU10_OPERAND_NUM_COMPONENTS, VGPU10_OPERAND_4_COMPONENT_SELECTION_MODE, unsigned int, VGPU10_INTERPOLATION_MODE, unsigned char, unsigned int)’} [-Wenum-int-mismatch]
3786 | emit_input_declaration(struct svga_shader_emitter_v10 *emit,
| ^~~~~~~~~~~~~~~~~~~~~~
../src/gallium/drivers/svga/svga_tgsi_vgpu10.c:516:1: note: previous declaration of ‘emit_input_declaration’ with type ‘void(struct svga_shader_emitter_v10 *, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, boolean, SVGA3dDXSignatureSemanticName)’ {aka ‘void(struct svga_shader_emitter_v10 *, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned int, unsigned char, unsigned int)’}
516 | emit_input_declaration(struct svga_shader_emitter_v10 *emit,
| ^~~~~~~~~~~~~~~~~~~~~~
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22718>
Michel Dänzer [Tue, 25 Apr 2023 16:14:16 +0000 (18:14 +0200)]
svga: Make vmw_svga_winsys_buffer_map definition match declaration
Pointed out by GCC 13:
../src/gallium/winsys/svga/drm/vmw_buffer.c:355:1: warning: conflicting types for ‘vmw_svga_winsys_buffer_map’ due to enum/integer mismatch; have ‘void *(struct svga_winsys_screen *, struct svga_winsys_buffer *, enum pipe_map_flags)’ [-Wenum-int-mismatch]
355 | vmw_svga_winsys_buffer_map(struct svga_winsys_screen *sws,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from ../src/gallium/winsys/svga/drm/vmw_buffer.c:52:
../src/gallium/winsys/svga/drm/vmw_buffer.h:82:1: note: previous declaration of ‘vmw_svga_winsys_buffer_map’ with type ‘void *(struct svga_winsys_screen *, struct svga_winsys_buffer *, unsigned int)’
82 | vmw_svga_winsys_buffer_map(struct svga_winsys_screen *sws,
| ^~~~~~~~~~~~~~~~~~~~~~~~~~
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22718>
Michel Dänzer [Fri, 21 Apr 2023 10:11:05 +0000 (12:11 +0200)]
vulkan: Fix GetPhysicalDeviceSparseImageFormatProperties definitions
To match the declarations (and the corresponding definition in Vulkan
headers).
Pointed out by GCC 13, e.g.:
../src/intel/vulkan_hasvk/anv_formats.c:1589:6: error: conflicting types for 'anv_GetPhysicalDeviceSparseImageFormatProperties' due to enum/integer mismatch; have 'void(struct VkPhysicalDevice_T *, VkFormat, VkImageType, uint32_t, VkImageUsageFlags, VkImageTiling, uint32_t *, VkSparseImageFormatProperties *)' {aka 'void(struct VkPhysicalDevice_T *, VkFormat, VkImageType, unsigned int, unsigned int, VkImageTiling, unsigned int *, VkSparseImageFormatProperties *)'} [-Werror=enum-int-mismatch]
1589 | void anv_GetPhysicalDeviceSparseImageFormatProperties(
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from ../src/intel/vulkan_hasvk/anv_private.h:113,
from ../src/intel/vulkan_hasvk/anv_formats.c:24:
src/intel/vulkan_hasvk/anv_entrypoints.h:120:30: note: previous declaration of 'anv_GetPhysicalDeviceSparseImageFormatProperties' with type 'void(struct VkPhysicalDevice_T *, VkFormat, VkImageType, VkSampleCountFlagBits, VkImageUsageFlags, VkImageTiling, uint32_t *, VkSparseImageFormatProperties *)' {aka 'void(struct VkPhysicalDevice_T *, VkFormat, VkImageType, VkSampleCountFlagBits, unsigned int, VkImageTiling, unsigned int *, VkSparseImageFormatProperties *)'}
120 | VKAPI_ATTR void VKAPI_CALL anv_GetPhysicalDeviceSparseImageFormatProperties(VkPhysicalDevice physicalDevice, VkFormat format, VkImageType type, VkSampleCountFlagBits samples, VkImageUsageFlags usage, VkImageTiling tiling, uint32_t* pPropertyCount, VkSparseImageFormatProperties* pProperties);
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22718>
Samuel Pitoiset [Fri, 28 Apr 2023 14:30:00 +0000 (16:30 +0200)]
radv: enable RADV_THREAD_TRACE_CACHE_COUNTERS by default
It should work but if not enabled by default, I think most people
forget about it.
If you have any issues with it, you can disable by using
RADV_THREAD_TRACE_CACHE_COUNTERS=false and please report!
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22763>
Gert Wollny [Mon, 1 May 2023 11:03:00 +0000 (13:03 +0200)]
r600/sfn: assign window_space_position in shader state
This fixes a few tests out of the nin-tests test suite.
Fixes:
79ca456b4837 ("r600/sfn: rewrite NIR backend")
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22778>
Gert Wollny [Mon, 1 May 2023 11:01:12 +0000 (13:01 +0200)]
r600+sfn: Assign ps_conservative_z and switch to NIR defines
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22778>
Juan A. Suarez Romero [Sun, 30 Apr 2023 14:07:34 +0000 (16:07 +0200)]
v3d: apply 1D texture miplevel alignment in arrays
1D texture miplevels are aligned to 64b, but this should include also
texture arrays.
Fixes
`spec@glsl-1.30@execution@texelfetchoffset@vs-texelfetch-usampler1darray`
and several other piglit tests.
CC: mesa-stable
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22775>
Bas Nieuwenhuizen [Sun, 12 Mar 2023 00:55:26 +0000 (01:55 +0100)]
radv: Add asserts in radeon_emit{,_array}.
Also add an unsafe helper for some winsys stuff that can't really
use the reservation mechanism (e.g. chaining between cmdbuffers).
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20152>
Bas Nieuwenhuizen [Sun, 4 Dec 2022 23:54:14 +0000 (00:54 +0100)]
radv: Add stricter space checks.
The check for max_dw means that none of checks triggered reliably
when we had an issue. Use a stricter reserved dw measure to increase
the probability of catching issues.
Adds a radeon_check_space to some places after cs_create as they
previously relied on the min. cs size, but that would still trigger
the checks.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20152>
Bas Nieuwenhuizen [Mon, 24 Apr 2023 00:49:48 +0000 (02:49 +0200)]
radv: Reserve space in the ACE pre/postambles.
Since we check reservations now.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20152>
Bas Nieuwenhuizen [Mon, 24 Apr 2023 00:32:17 +0000 (02:32 +0200)]
radv: Reserve space for indirect descriptor set address writes.
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20152>
Pavel Ondračka [Wed, 26 Apr 2023 11:38:41 +0000 (13:38 +0200)]
r300: remove simple duplicate ARL instructions
Removes duplicate ARL reads from the same source when the original ADDR
register is still live. This is the remaining low-hanging fruit from #7723
Should account for most of the potential improvements and is also
trivial as no source or destination rewrite is needed.
RV530:
total instructions in shared programs: 132447 -> 131488 (-0.72%)
instructions in affected programs: 33396 -> 32437 (-2.87%)
helped: 331
HURT: 0
total temps in shared programs: 17035 -> 17015 (-0.12%)
temps in affected programs: 361 -> 341 (-5.54%)
helped: 30
HURT: 10
RV370:
total instructions in shared programs: 83555 -> 82659 (-1.07%)
instructions in affected programs: 28310 -> 27414 (-3.16%)
helped: 312
HURT: 0
total temps in shared programs: 12418 -> 12426 (0.06%)
temps in affected programs: 302 -> 310 (2.65%)
helped: 21
HURT: 29
Signed-off-by: Pavel Ondračka <pavel.ondracka@gmail.com>
Reviewed-by: Filip Gawin <filip@gawin.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22752>
Erik Faye-Lund [Wed, 15 Feb 2023 13:47:53 +0000 (14:47 +0100)]
mesa/main: make ffvertex output nir
There's little point in going from fixed-function to ARB progs just to
convert it to NIR in the end. So let's emit NIR code directly here
instead.
This all made sense back when we had DRI drivers that didn't use NIR at
all in the tree, but these days we unconditionally call prog_to_nir.
Since we're no longer generating something that resembles ARM asm
shaders, we also no longer pass is_arb_asm as true to NewProgram. But
we still require legacy math rules, so we set use_legacy_math_rules in
the shader_info instead. This should do the same thing, but
communicates exactly what we actually need rather than having a half-
truth about the source of the shader.
Acked-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22520>
Erik Faye-Lund [Tue, 18 Apr 2023 10:23:15 +0000 (12:23 +0200)]
mesa/main: allow passing nir-shaders to st_program_string_notify
This will enable us to emit NIR directly for fixed-function vertex
shaders.
Acked-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22520>
Erik Faye-Lund [Tue, 14 Feb 2023 11:39:53 +0000 (12:39 +0100)]
mesa/main: drop disasm-code from ffvertex_prog.c
We're about to rewrite this code to emit NIR directly, so let's drop
this needless logic.
Acked-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22520>
Erik Faye-Lund [Tue, 14 Feb 2023 10:13:20 +0000 (11:13 +0100)]
mesa/main: clean up white-space in ffvertex_prog.c
We're about to change this file, so let's clean up the whitespace a bit
first.
Acked-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22520>
David Heidelberg [Wed, 26 Apr 2023 08:54:42 +0000 (10:54 +0200)]
ci/skqp: update to the Android CTS 12.1_r5 version
Reviewed-by: Eric Engestrom <eric@igalia.com>
Signed-off-by: David Heidelberg <david.heidelberg@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22710>
David Heidelberg [Wed, 26 Apr 2023 08:51:20 +0000 (10:51 +0200)]
ci/skqp: replace license with SPDX and extract the used branch
Reviewed-by: Eric Engestrom <eric@igalia.com>
Signed-off-by: David Heidelberg <david.heidelberg@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22710>
Jesse Natalie [Thu, 27 Apr 2023 17:37:08 +0000 (10:37 -0700)]
meson: Don't use masm with VS backend
Fixes:
77826e83 ("util: Add a copy of BLAKE3 hash library.")
Reviewed-by: Tatsuyuki Ishi <ishitatsuyuki@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22740>
antonino [Fri, 28 Apr 2023 09:36:15 +0000 (11:36 +0200)]
Revert "zink: add `single_sample` to fs key"
This reverts commit
420f2c0878f0c38128854f2adbbeb1391e752cb8.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22753>
antonino [Fri, 28 Apr 2023 09:36:08 +0000 (11:36 +0200)]
Revert "zink: add to multisample field to `zink_gfx_pipeline_state`"
This reverts commit
14d58926099fb735312705f0853785dcd1888c2e.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22753>
antonino [Fri, 28 Apr 2023 09:36:00 +0000 (11:36 +0200)]
Revert "zink: don't render with multisampling when it is disabled"
This reverts commit
a004825266fdcb43afd5e9fdf946ad9641f1e296.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22753>
antonino [Fri, 28 Apr 2023 09:35:52 +0000 (11:35 +0200)]
Revert "zink/ci: remove xt_framebuffer_multisample-interpolation fail"
This reverts commit
177c92fe7ca3f171ab4fe41491935895134eff3f.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22753>
antonino [Fri, 28 Apr 2023 09:35:27 +0000 (11:35 +0200)]
Revert "zink: set when pipeline dirty flag when multisample changes"
This reverts commit
5969541123dbfe1ac339284911a83af712fdcc25.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22753>
Mike Blumenkrantz [Fri, 28 Apr 2023 19:35:00 +0000 (15:35 -0400)]
zink: add extendedDynamicState3DepthClipNegativeOneToOne to profile
Fixes:
3017d01c9de ("zink: check for extendedDynamicState3DepthClipNegativeOneToOne for ds3 support")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22765>
Mike Blumenkrantz [Fri, 28 Apr 2023 14:19:04 +0000 (10:19 -0400)]
zink: update amdpro fails
how is this driver still so broken
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22761>
Mike Blumenkrantz [Fri, 28 Apr 2023 20:34:44 +0000 (16:34 -0400)]
llvmpipe: fix native vector width init
this otherwise causes infinite loops in subgroup tests
and kills ci
Fixes:
4a056807bc3 ("gallivm: break out native vector width calc for reuse")
Reviewed-by: Dave Airlie <airlied@redhat.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22767>
Dave Airlie [Fri, 26 Aug 2022 06:56:41 +0000 (16:56 +1000)]
gallivm: reorder some texture/image members.
This just aligns texture/image a bit more, shouldn't have much
affect, but might make things easier going forward.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18265>
Dave Airlie [Fri, 26 Aug 2022 06:47:26 +0000 (16:47 +1000)]
gallium: consolidate jit image types between draw/llvmpipe
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18265>
Dave Airlie [Fri, 26 Aug 2022 06:43:18 +0000 (16:43 +1000)]
gallivm: consolidate llvmpipe/draw sampler types.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18265>
Dave Airlie [Fri, 26 Aug 2022 06:36:37 +0000 (16:36 +1000)]
gallivm: consolidate draw/lp texture type.
This just makes the type creation, struct and fields the same.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18265>
Dave Airlie [Fri, 26 Aug 2022 06:31:43 +0000 (16:31 +1000)]
lp_jit: use pipe max for the lp_jit texture levels.
Align this with draw, so we the structs can be shared.
Reviewed-by: Roland Scheidegger <sroland@vmware.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/18265>
Mike Blumenkrantz [Sat, 29 Apr 2023 01:09:31 +0000 (21:09 -0400)]
ci: disable all a306/a530/a630 jobs
these have been dead and timing out all day
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22768>
David Heidelberg [Fri, 28 Apr 2023 20:35:21 +0000 (22:35 +0200)]
ci/dzn: add flaking test
Signed-off-by: David Heidelberg <david.heidelberg@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22766>
Ruijing Dong [Thu, 20 Apr 2023 15:22:31 +0000 (11:22 -0400)]
radeonsi/vcn: correct cropping for hevc case
reason:
corect cropping calculation error.
If no cropping from the external, then it will
need to calculate cropping size internally, the
padding size on left and top should be zero.
Cc: mesa-stable
Fixes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/7171
Reviewed-by: Thong Thai <thong.thai@amd.com>
Signed-off-by: Ruijing Dong <ruijing.dong@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22758>
Samuel Pitoiset [Fri, 28 Apr 2023 12:49:49 +0000 (14:49 +0200)]
ac/nir: fix 8-bit/10-bit PS exports clamping
This broke many tests on GFX6 (Pitcairn).
Fixes:
c1821544562 ("ac/nir: add ac_nir_lower_ps")
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22756>
Samuel Pitoiset [Wed, 26 Apr 2023 15:02:38 +0000 (17:02 +0200)]
ac,radv,radeonsi: rename thread_trace to sqtt everywhere
SQTT stands for SQ Thread Trace but it's shorter.
Note that environment variables aren't renamed because this might
break external applications.
This renames:
- ac_thread_trace_data to ac_sqtt (this is the main struct)
- ac_thread_trace_info to ac_sqtt_data_info
- ac_thread_trace_se to ac_sqtt_data_se
- ac_thread_trace to ac_sqtt_trace (this contains trace only)
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22732>
Samuel Pitoiset [Wed, 26 Apr 2023 13:41:41 +0000 (15:41 +0200)]
ac/rgp: remove ac_thread_trace_data from ac_thread_trace
We only need the RGP objects.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22732>
Samuel Pitoiset [Wed, 26 Apr 2023 12:28:19 +0000 (14:28 +0200)]
radv: do not abort when the SQTT buffer resize failed
This seems to much. While we are at it, update the error msg.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22732>
Samuel Pitoiset [Wed, 26 Apr 2023 12:26:07 +0000 (14:26 +0200)]
ac/sqtt: add ac_sqtt_get_trace() helper
It can be shared between RADV and RadeonSI. The only difference is
that RadeonSI can't auto-resize the SQTT BO.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22732>
Samuel Pitoiset [Wed, 26 Apr 2023 12:08:44 +0000 (14:08 +0200)]
ac/sqtt: add ac_sqtt_se_is_disabled() helper
It can be shared between RADV and RadeonSI.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22732>
Matt Coster [Tue, 25 Apr 2023 15:31:22 +0000 (16:31 +0100)]
pvr: Fixup format features
Fixes: dEQP-VK.api.info.format_features.*
Signed-off-by: Matt Coster <matt.coster@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22749>
Matt Coster [Fri, 28 Apr 2023 09:11:07 +0000 (10:11 +0100)]
pvr: Remove false assumption from pvr_write_draw_indirect_vdm_stream()
Partially reverts:
bd513059433a6bbda8ce0f95b85dcc76d48f959c
pvr: Minor cleanup around pvr_emit_vdm_index_list()
Signed-off-by: Matt Coster <matt.coster@imgtec.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22751>
Eric Engestrom [Thu, 27 Apr 2023 18:40:07 +0000 (19:40 +0100)]
v3d: fix various minor issues in gen_pack_header.py
Signed-off-by: Eric Engestrom <eric@igalia.com>
Acked-by: Juan A. Suarez <jasuarez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22742>
José Roberto de Souza [Thu, 20 Apr 2023 18:52:20 +0000 (11:52 -0700)]
iris: Allow shared scanout buffer to be placed in smem as well
i915 and Xe kmd allows scanout to display of prime buffers placed
in smem.
Allowing shared and scanout bos to be placed in smem and lmem allows
the dma buf to work in some cases that only lmem is not enough.
Fixes:
c10ff1970461 ("iris: Place scanout buffers only into lmem for discrete GPUs")
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/8867
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/8766
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Tested-by: Tapani Pälli <tapani.palli@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22665>
Gert Wollny [Mon, 17 Apr 2023 10:06:45 +0000 (12:06 +0200)]
r600/sfn: Tie in address load splitting
Add R600_NIR_DEBUG flag "noaddrsplit" to disable the behaviour and use the
old code path.
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Sun, 16 Apr 2023 13:31:32 +0000 (15:31 +0200)]
r600/sfn: prepare for emitting AR loads
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Sun, 16 Apr 2023 07:52:06 +0000 (09:52 +0200)]
r600/sfn: factor out index loading for non-alu instructions
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Tue, 7 Mar 2023 13:30:06 +0000 (14:30 +0100)]
r600/sfn: Can't use an indirect array access as source to AR load
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Mon, 6 Mar 2023 12:02:32 +0000 (13:02 +0100)]
r600/sfn: print failing block when scheduling fails
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Fri, 10 Feb 2023 15:40:04 +0000 (16:40 +0100)]
r600/sfn: Add more tests and update to use address splits
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Mon, 6 Mar 2023 12:01:23 +0000 (13:01 +0100)]
r600/sfn: scheduled instructions are always ready
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Tue, 7 Mar 2023 16:53:08 +0000 (17:53 +0100)]
r600/sfn: Fix copy-prop with array access
We will have to check whether there is access to an array between the
instructions involved with the copy prop, so for now do not allow it.
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Sun, 19 Feb 2023 18:05:02 +0000 (19:05 +0100)]
r600/sfn: Override Array access handling in backend assembler
Since we do thi sin the scheduler, there is no need to do this in the
backend again.
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Sun, 19 Feb 2023 17:29:07 +0000 (18:29 +0100)]
r600/sfn: Add handling for R600 indirect access alias handling
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Sun, 19 Feb 2023 16:06:13 +0000 (17:06 +0100)]
r600/sfn: Add chip family to shader class
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Tue, 14 Feb 2023 16:35:33 +0000 (17:35 +0100)]
r600/sfn: Start a new ALU CF on index use, not on index emission
With that we can use the two IDX registers in parallel any might
save some CF instructions.
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Tue, 14 Feb 2023 16:34:04 +0000 (17:34 +0100)]
r600/sfn: set CF force flag always when starting a new block
There is no reason not to do this, because we only start a new
block if a new CF block must be started.
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Tue, 14 Feb 2023 15:46:33 +0000 (16:46 +0100)]
r600/sfn: Add test for multiple index load
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Fri, 10 Feb 2023 15:57:43 +0000 (16:57 +0100)]
r600/sfn: Don't copy-propagate indirect access into LDS instr
Propagating array elements has the problem that we would have to
check whether the last load is not overwritten by an indirect store.
Indirect kcache buffer loads require starting a new CF, and we would
have to make sure that we don't split the LDS fetch/read group with
that, so don't do this.
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Fri, 10 Feb 2023 15:40:04 +0000 (16:40 +0100)]
r600/sfn: Add more tests and update to use address splits
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Fri, 10 Feb 2023 15:38:04 +0000 (16:38 +0100)]
r600/sfn: take address loads into account when scheduling
Also change a bit the instruction priority handling
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Fri, 10 Feb 2023 15:36:24 +0000 (16:36 +0100)]
r600/sfn: Add function to check whether a group loads a index register
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Fri, 10 Feb 2023 15:22:38 +0000 (16:22 +0100)]
r600/sfn: Add pass to split addess and index register loads
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Fri, 10 Feb 2023 15:18:57 +0000 (16:18 +0100)]
r600/sfn: Add interface to count AR uses in ALU op
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>
Gert Wollny [Fri, 10 Feb 2023 15:17:49 +0000 (16:17 +0100)]
r600/sfn: Add a RW get function of IF predicate access
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21347>