aco does not implement fpow, need nir to lower it
first. llvm will do by itself in the same way, so
we always lower fpow in nir now.
Remove the llvm fpow implementation that has special
handling for the muliplication. It's not used any
more and does not match GLSL spec as fpow(0,0)=NaN
but here we get 0.
There's some pixel changes for gl-radeonsi-stoney:
ror-default 2 (no tolerance), 0 (1% tol.)
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22573>
ACO only support nir_fsin/cos_amd.
There's some pixel changes for gl-radeonsi-stoney trace.
Different pixels:
furmark 61 (no tolerance), 0 (1% tol.)
gimark 93867 (no tolerance), 888 (1% tol.)
tessmark 39 (no tolerance), 0 (1% tol.)
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22573>
aco does not implement these idiv ops.
nir_lower_idiv is for idiv ops <= 32bit and ported from
llvm amdgpu, so llvm do the same.
nir_lower_divmod64 is for 64bit idiv ops.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22573>
Use case: radeonsi will generate internal tgsi shader
with 64bit udiv instruction, and we want all 64bit udiv
to be lowered in nir by lower_int64_options.
For GLSL shaders, this is done in glsl to nir, so we do
the same for tgsi here.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22573>
It's the output of ACO compiler. To share the si_shader_binary
struct with ELF type:
* add a type field to indicate RAW or ELF
* rename elf_buffer/size to code_buffer/size
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22573>
Use ACCESS_* flags in call sites instead of GLC/DLC/SLC.
ACCESS_* flags are extended to describe other aspects of memory instructions
like load/store/atomic/smem.
Then add a function that converts the access flags to GLC, DLC, SLC.
The new functions are also usable by ACO.
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22770>
Refactor framebuffer to renderpass to mirror previous INTEL_MEASURE
changes.
We dump hashes/pointers for shaders and framebuffer/renderpass.
Reduce from 64bit to 32bit pointers. We don't benefit from the
extra precision and reduced output size is convenient.
Reviewed-by: Mark Janes <markjanes@swizzler.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22723>
This is a huge win because gallivm duplicated the translations in a zillion
places.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22914>
This fixes vaon12 driver file name to be consistent with libva
expectation - vaon12_drv_video.dll - without lib prefix.
Signed-off-by: Dmitry Rogozhkin <dmitry.v.rogozhkin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22995>
If either dest or src is an invalid or null pointer, the behavior is
undefined, even if count is zero.
Cc: mesa-stable
Signed-off-by: Yiwei Zhang <zzyiwei@chromium.org>
Reviewed-by: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22979>
Add support for using BLORP's ambiguate pass to initialize MCS instead
of mapping and memsetting it on the CPU. Note that this won't be used if
the first operation on the MSAA layer is a fast clear.
Since we're no longer mapping, this removes a blocker towards getting
MCS_CCS enabled in small-BAR mode.
This functionality is difficult to test because of the way iris is set
up. It always tries to compress writes. So, a test would only read the
ambiguated MCS element if it tries to read from undefined samples.
To test this, I locally disabled fast clears and rendering with MCS (via
iris_resource_render_aux_usage). I continued to allow sampling with MCS
in iris_resource_texture_aux_usage. So, writes go directly to the main
surface and reads go through the ambiguated MCS surface.
When I then ran the test group, dEQP-GLES3.functional.multisample.*, all
48/64 supported tests passed on my Ice Lake. If I slightly changed
BLORP's ambiguate pass, I observed several tests failing.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22545>
BOs can be written from several contexts, so writing to this member is
racy. We only care about this for the purposes of exporting BOs after a
submission (and if the app is racing writers/submissions at that point
all bets are off), so just keeping track of the last written value is
sufficient.
Switch to atomic operations to eliminate the race, and drop the assert
in the batch cleanup path that no longer holds when the BO might have
been written to from another context.
Fixes: asahi/mesa#20
Signed-off-by: Asahi Lina <lina@asahilina.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22971>
We track buffers written by batches, but this gets messy when we end up
with an empty batch that is never submitted, since then it might have
taken over writer state from a prior already submitted batch (for its
framebuffers).
Instead of trying to track two tiers of resource writers, let's just
defer initializing batch state until we know we have a draw (or compute
launch, or clear). This means that if a batch is marked as a writer for
a buffer, we know it will not be an empty batch.
This should be a small performance win for empty batches (no need to
emit initial VDM state or run the writer code), but more impontantly it
eliminates the empty batch writer state revert corner case.
Signed-off-by: Asahi Lina <lina@asahilina.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22971>
This seems to flake some dEQPs due to some kind of race/UB (which
doesn't even always cause the dEQPs to fail due to leeway in the image
comparison, since the problem is usually just a few pixels, but it's
there).
I spent a bunch of time trying other flags/things, and almost everything
changed the bad pixel pattern randomly but nothing fixed it. Let's
revisit this one later, since it looks like a pretty deep rabbit hole.
Signed-off-by: Asahi Lina <lina@asahilina.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22971>
Framebuffer fetch is coherent, so there is no need for barriers here.
This avoids pointless flushing if an app calls glBlendBarrier().
Signed-off-by: Asahi Lina <lina@asahilina.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22971>
Apparently we were still missing some fence stuff, and it started
crashing Firefox in apitrace? I'm not sure why we never noticed this
before, but it's trivial enough. Cargo culted from Panfrost.
Signed-off-by: Asahi Lina <lina@asahilina.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22971>
