Since VkQueryPipelineStatisticFlagBits is extended by two bits for
task/mesh shader invocations, ANV_PIPELINE_STATISTICS_MASK should be
defined conditionally based on GFX_VER.
This commit modifies the mask and updates the vk_pipeline_stat_to_reg
array accordingly.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29523>
Like it describes in the comment section of VK_QUERY_TYPE_OCCLUSION,
only occlusion and timestamps queries needs ANV_COPY_QUERY_FLAG_PARTIAL.
VK_QUERY_TYPE_PRIMITIVES_GENERATED_EXT is captured by MI commands.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29493>
Currently for an "unavailable" query, if VK_QUERY_RESULT_PARTIAL_BIT is
set, anv will return (slot.end - slot.begin). This can cause underflow
because slot.end might still be at the initial value of 0.
This commit fixes the issue by returning 0 in that situation.
Cc: mesa-stable
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/29447>
If we did clear a query buffer in compute mode, the flushing needs to
match the engine used for clearing.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: 6823ffe70e ("anv: try to keep the pipeline in GPGPU mode when buffer transfer ops")
Reviewed-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28285>
It seems like an L3 setting is different between DG2 & MTL, breaking
the L3 coherency with CS.
We can apply the same tile cache flush as we do on TGL for now until
we figure out how to configure L3 properly to avoid this.
Tested with :
$ query_clear_with_blorp_threshold=0 query_copy_with_shader_threshold=0 ./deqp-vk -n dEQP-VK.query_pool.*
to force the shader optimizations.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27597>
When doing query result copies in 3D mode, we're flushing the render
target cache, but the shader writes go through the dataport.
Fixes flakes/fails in piglit with shader query copies forced with Zink :
$ query_copy_with_shader_threshold=0 ./bin/arb_query_buffer_object-coherency -auto -fbo
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: b3b12c2c27 ("anv: enable CmdCopyQueryPoolResults to use shader for copies")
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26797>
Ref: 0a52002a1c ("anv: disable reset query pools using blorp opt on MTL")
Ref: b3b12c2c27 ("anv: enable CmdCopyQueryPoolResults to use shader for copies")
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27352>
When URB state for DS changes, we need to emit URB setup for VS with
256 handles and 0 for rest, commit this using a HDC flush before
setting real values.
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26920>
Launch with :
$ MESA_VK_TRACE=rmv MESA_VK_TRACE_TRIGGER=/tmp/trig ./my_app
In another terminal, trigger a capture :
$ touch /tmp/trig
The application with create a snapshot and print out :
RMV capture saved to '/tmp/my_app_2024.01.19_10.56.33.rmv'
Then just open it with RMV :
./RadeonMemoryVisualizer /tmp/my_app_2024.01.19_10.56.33.rmv
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26843>
Insert a dummy blit prior to MI_ARB_CHECK, MI_SEMAPHORE_WAIT,
MI_FLUSH_DW submitted on the copy engine.
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26209>
On Blitter engine, we don't support PIPE_CONTROL, we have to update
memory locations using the MI_FLUSH_DW command.
v2:
- Handle video queue (Lionel)
Fixes: 056b0cb87f ("anv: add video engine support in various places")
Fixes: 5112b42146 ("anv: Handle end of pipe with MI_FLUSH_DW on transfer queue")
Signed-off-by: Sagar Ghuge <sagar.ghuge@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26121>
Fixes performance regression introduced by prior refactoring of
pipe control code that unnecessarily added CS_FLUSH to query start
and end. Issue was diagnosed by Ben L (thank you!)
Confirmed this restores performance on:
* Borderlands3 +2%
* Payday +3%
* Factorio +3%
* HogwartsLegacy +4%
* Ghostrunner +7%
Fixes: 6dc95685 (convert genX_query pipe controls to use pc helper)
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25983>
In case we run out of space, all the parts of the driver that rely on
this should deal with failure. The helpers will set the batch in error
state so that it cannot be submitted by the application.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25955>
This way we can implemented workarounds depending on the pipeline.
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25671>
While earlier changes to pipe control emission allowed debug dump of
each pipe control, they also changed debug output to almost always print
same reason/function for each pc. These changes fix the output so that
we print the original function name where pc is emitted.
As example:
pc: emit PC=( +depth_flush +rt_flush +pb_stall +depth_stall ) reason: gfx11_batch_emit_pipe_control_write
pc: emit PC=( ) reason: gfx11_batch_emit_pipe_control_write
changes back to:
pc: emit PC=( +depth_flush +rt_flush +pb_stall +depth_stall ) reason: gfx11_emit_apply_pipe_flushes
pc: emit PC=( ) reason: cmd_buffer_emit_depth_stencil
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25282>
We'll use this later to know when to reemit
3DSTATE_STREAMOUT::ForceRendering
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24536>
MOCS = 0 is a invalid MOCS index, so it is necessary get a valid value
and set to MI_MATH instructions.
So here the mocs index is set with mi_builder_set_mocs(), it can be
always set but it is required when mi_build will emit MI_MATH
instructions.
The mocs index will only be stored and used in gfx12.5+ platforms
so no changes were are required in crocus or hasvk.
Signed-off-by: José Roberto de Souza <jose.souza@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22508>
CID 1528164 (#1 of 1): Unintentional integer overflow (OVERFLOW_BEFORE_WIDEN)
overflow_before_widen: Potentially overflowing expression
pool->n_passes * pool->khr_perf_preamble_stride with type
unsigned int (32 bits, unsigned) is evaluated using 32-bit arithmetic,
and then used in a context that expects an expression of type uint64_t (64 bits, unsigned).
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: José Roberto de Souza <jose.souza@intel.com>
Signed-off-by: Illia Polishchuk <illia.a.polishchuk@globallogic.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20893>
Since we expect the number of copies to be > 6, emitting fewer
commands makes more sense.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Rohan Garg <rohan.garg@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23675>
Clears should be flushed only on :
- vkCmdBeginQuery*
- vkCmdWriteTimestamp*
- vkCmdWriteAccelerationStructuresPropertiesKHR
- vkCmdCopyQueryPoolResults
Buffer writes should be flush only on :
- vkCmdCopyQueryPoolResults
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Rohan Garg <rohan.garg@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23675>
If we do the clear operations on a compute only command buffer, the
operations will not use render target writes but compute shader writes
instead.
Probably not an issue right now because this is not a feature we've
enabled.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Rohan Garg <rohan.garg@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23675>
split ANV_PIPE_RENDER_TARGET_BUFFER_WRITES into separate CS_STALL,
RT_FLUSH & TILE_FLUSH flags in order to have finer control over cache
coherency.
Tigerlake CS has it's own cache fetching directly from the memory controller,
so we need to do a tile flush to ensure the query data is visible.
This fixes test_resolve_non_issued_query_data in vkd3d on TGL.
Signed-off-by: Rohan Garg <rohan.garg@intel.com>
Fixes: 3c4c18341a ("anv: narrow flushing of the render target to buffer writes")
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23500>
This optimization causes some MTL tests to run forever. Not
yet sure why. Disabling optimization until we have a fix.
Reviewed-by: Mark Janes <markjanes@swizzler.org>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22373>
The query buffer contains a batch to implement the multi pass
replay/accumulation of results. So we can't clear it with a memset.
An optimization for later would be to move the batches to the very end
of the query buffer so we can clear the query data without touching
the batches.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Fixes: 4dc7256bf9 ("anv: reset query pools using blorp")
Reviewed-by: Felix DeGrood <felix.j.degrood@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22421>
Previously we used PC to set query data to 0 during
CmdResetQueryPool. This was slow when clearing large query pools.
Switching to blorp to clear pools is faster for large query pools.
Red Dead Redemption 2: +1.5% speedup
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22178>
All the flushes should already have happened, we just need CS to wait
for the operations to complete. Just use a MI_SEMAPHORE_WAIT to check
the availability bit is set.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Felix DeGrood <felix.j.degrood@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22178>
