The xe.ko driver finally fixed bug 746, which means we can finally
pass multiple bind operations in a single ioctl. There's a dEQP test
that issues 960 bind operations in a single call, so our gains here
have potential, although most real-world apps are not even remotely
close to this.
Link: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/746
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27926>
Summary:
- ensure headers used outside runtime are included in dependency source
- drop redundant idep_vulkan_common_entrypoints_h
- drop redundant icd side tricks for the order of header gen
Signed-off-by: Yiwei Zhang <zzyiwei@chromium.org>
Reviewed-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Yonggang Luo <luoyonggang@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28066>
The generated "astc_spv.h" is for runtime internal use, so leave it
inside the runtime files to ensure the header is generated before being
used to compile.
Signed-off-by: Yiwei Zhang <zzyiwei@chromium.org>
Reviewed-by: Eric Engestrom <eric@engestrom.ch>
Reviewed-by: Yonggang Luo <luoyonggang@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28066>
Batches must be ignored if batch count is zero, so all batch inspections
have to be gated behind batch count. For memcpy, it's UB if either src
or dst is NULL even when size is zero.
Side note:
- For original commit, this fixes just the memcpy UB
- For current codes, this fixes to not skip ffb batch prepare
Fixes: 493a3b5cda ("venus: refactor batch submission fixup")
Signed-off-by: Yiwei Zhang <zzyiwei@chromium.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28071>
Adds a driver workaround for IHVs actually supporting rate control
reconfiguration but not reporting it in the DX12 driver support flags,
and later having crashes/hangs in the driver when the rate control
reconfiguration happens using the fallback method that includes re-creating
the encoder state and encoder heap objects upon new rate control params
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28075>
Blitter and video engines don't support PIPE_CONTROL and
3DSTATE_BINDING_TABLE_POOL_ALLOC.
I'm not 100% sure if something else should be called instead but this
is doing the same as cmd_buffer_emit_state_base_address() and this
fixes the test that was crashing in
unreachable("Trying to emit unsupported PIPE_CONTROL command.");
Fixes: dEQP-VK.pipeline.monolithic.timestamp.misc_tests.two_cmd_buffers_secondary_transfer_queue_with_availability_bit
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28053>
These 2 compute code paths were checking for
anv_cmd_buffer_is_render_queue() before calling
flush_pipeline_select_gpgpu() causing cmd_buffer->state.current_pipeline
to never to be set to GPGPU, trigerring
assert(cmd_buffer->state.current_pipeline == GPGPU) when running in
the compute engine.
So here just dropping the anv_cmd_buffer_is_render_queue() check.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28053>
Add RMV support for Turnip. The internal RMV layer is added and integrated
into the VkDevice entrypoint dispatch tables. As elsewhere, memory tracing
is put into action when enabled through the MESA_VK_TRACE environment
variable.
Similar to other implementations of RMV support in Mesa, tracing points are
added across Turnip to report on different types of RMV events, calling
into tu_rmv logging functions to emit the relevant RMV token data.
TU_BO_ALLOC_INTERNAL_RESOURCE allocation flag is added. When used, in RMV
output such an allocation will be associated with an internal resource
of the VK_RMV_RESOURCE_TYPE_MISC_INTERNAL type.
Signed-off-by: Zan Dobersek <zdobersek@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27631>
Add the vk_rmv_misc_internal_description struct and list the misc_internal
member of that type in the vk_rmv_resource_create_token union, allowing
logging of different internal resources in RMV dumps.
The vk_rmv_common.h header also has the C-linkage block added in order to
enable its inclusion in C++ files.
Signed-off-by: Zan Dobersek <zdobersek@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27631>
Add up to four reasons per flush to perfetto flushes. PC reasons
will help debuggers understand why flushes were required, and
perhaps provide hints as to how they can be avoided.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27400>
VK_EXT_shader_object is now supported on all GPUs! It's still not
enabled by default because it needs more testing and more fixing (Renoir
still hangs for some reasons and Zink/RADV on Polaris10 still has
flakes).
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27880>
NGG streamout isn't supported on GFX10/GFX10.3, so NGG GS must be
disabled when pre-rasterization stages are compiled separately because
it's not possible to know that when compiling VS/TES only.
Also GFX10/GFX10.3 needs to disable NGG when extreme geometry are used
with tessellation and we can't know the previous stage if the GS is
compiled separately.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27880>
This change adds a new generated header dep to the runtime internal
library dependencies. This ensures the headers are generated before the
below libraries are compiled:
- libvulkan_lite_runtime (already satisfied due to file sources)
- libvulkan_lite_instance
- libvulkan_runtime
- libvulkan_instance
Fixes: fe2ec50844 ("vulkan: allow building venus without libcompiler")
Signed-off-by: Yiwei Zhang <zzyiwei@chromium.org>
Reviewed-by: Yonggang Luo <luoyonggang@gmail.com>
Reviewed-by: Eric Engestrom <eric@engestrom.ch>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28062>
Flip on the caps/extensions, use their presence to turn on bindless just like
descriptor_indexing, use the buffer flag to indicate UAV access, and fix up
the getter to return the kind of data we want.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28028>
This works similarly to the CL compiler, where a 64-bit address is
decomposed into a 32-bit index and offset. But unlike CL, where the
index is into a per-kernel array of bound buffers, for Vulkan it points
into the global device-wide descriptor heap.
For all global deref chains that terminate in a load/store/atomic, create
a parallel deref chain that begins by decomposing the pointer to a vec2,
followed by a load_vulkan_descriptor, and then an SSBO deref chain. Any instance
where the original deref chain was used for something else will remain as
global derefs, so also run lower_explicit_io for global to produce appropriate
pointer math.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28028>
This is done by introduce idep_vulkan_lite_runtime, and only venus
depends on idep_vulkan_lite_runtime.
Modify the meson and source files to allow building venus without
the compiler.
See details Venus build metrics at the MR description.
gfxstream-vulkan forwards the shader to the host, and doesn't
need to convert into NIR in the guest. This results in faster
builds and less parts of Mesa to build. Also venus does the
same thing too, that's what the build is keyed on right now
as an in-tree user.
v7: By Yonggang Luo <luoyonggang@gmail.com>
Add idep_vulkan_common_entrypoints_h into vulkan_lite_runtime_deps because
vk_instance.c depends on idep_vulkan_common_entrypoints_h but vk_common_entrypoints is
not compiled in library `vulkan_lite_instance`.
Rename idep_vulkan_runtime_headers to idep_vulkan_lite_runtime_headers because
both lite/full runtime library depends on this, but lite should not depends on full
vk_meta_private.h added into vulkan_runtime_files
v6: By Yonggang Luo <luoyonggang@gmail.com>
get vulkan_lite_runtime_files and vulkan_runtime_files sorted
v5: By Yiwei Zhang <zzyiwei@chromium.org>
both vk_sampler and vk_ycbcr_conversion can stay in the lite runtime
v4: By Yonggang Luo <luoyonggang@gmail.com>
only build vk_instance.(c|h) twice for reduce compiling time
v3: By Yiwei Zhang <zzyiwei@chromium.org>
less code changes by introduce libvulkan_lite_runtime
v2: By Yonggang Luo <luoyonggang@gmail.com>
allow building Vulkan without libcompiler without compiling flags, the
venus is always built without libcompiler
v1: By Gurchetan Singh <gurchetansingh@google.com>
allow building Vulkan without libcompiler
Signed-off-by: Gurchetan Singh <gurchetansingh@google.com>
Signed-off-by: Yonggang Luo <luoyonggang@gmail.com>
Signed-off-by: Yiwei Zhang <zzyiwei@chromium.org>
Reviewed-by: Yiwei Zhang <zzyiwei@chromium.org>
Reviewed-by: Yonggang Luo <luoyonggang@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26574>
We can gather the args used by all other stages and use that to optimize
the traversal shader.
Totals from 4 (1.06% of 379) affected shaders:
Instrs: 2912 -> 2864 (-1.65%)
CodeSize: 15424 -> 15232 (-1.24%)
Latency: 69342 -> 69074 (-0.39%)
InvThroughput: 11558 -> 11512 (-0.40%)
Copies: 712 -> 676 (-5.06%)
Branches: 152 -> 148 (-2.63%)
PreVGPRs: 324 -> 316 (-2.47%)
Reviewed-by: Friedrich Vock <friedrich.vock@gmx.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27137>
DebugMarkerSetObjectNameEXT is just a less powerful version of
SetDebugUtilsObjectNameEXT. Fixes the objectType cast warning as well.
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27975>
The spec for vkCreateDescriptorPool says:
If VkMutableDescriptorTypeCreateInfoEXT does not exist in the pNext
chain, or VkMutableDescriptorTypeCreateInfoEXT::pMutableDescriptorTypeLists[i]
is out of range, the descriptor pool allocates enough memory to be
able to allocate a VK_DESCRIPTOR_TYPE_MUTABLE_EXT descriptor with any
supported VkDescriptorType as a mutable descriptor.
So check that mutableDescriptorTypeListCount is in range of the binding
we are asking for instead of just 0.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28031>
We had a "Don't read out-of-bounds" sanity check for creating an alpha
when ATEST was needed, but that check happened only after we already
did a bi_extract(), which meant that the bi_extract could get into
trouble and assert() when there weren't enough components. Fixed by
re-arranging the calculation.
Signed-off-by: Eric R. Smith <eric.smith@collabora.com>
Reviewed-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Erik Faye-Lund <erik.faye-lund>@collabora.com>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28045>
This prevents potential app bugs causing GPU hangs and other issues.
Note that the draw ID is undefined in mesh shaders when also
using a task shader.
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27879>
