Up to now we've been lucky that the buffer returned was always exactly
at the address we requested.
Fixes: 144b40db54 ("intel: aubinator: drop the 1Tb GTT mapping")
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Rafael Antognolli <rafael.antognolli@intel.com>
Tarball distribution is done through "make distcheck". We include the
meson targets also into autotools so they won't fail when building
from the tarball.
Fixes: 6a60beba40 ("intel/tools: Add an error state to aub translator")
Cc: Jason Ekstrand <jason.ekstrand@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: Dylan Baker <dylan.c.baker@intel.com>
Signed-off-by: Andres Gomez <agomez@igalia.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Dylan Baker <dylan@pnwbakers.com>
This leaves us with a series of little anv_pipeline_compile_* functions
which each take a compiler object, a mem_ctx, the stage to compile, and
the previous stage for VUE linking purposes. Some of them do
interesting things but most are little more than wrappers around
brw_compile_*.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
This breaks compilation up a bit into "link" and "compile". In the
"link" stage, new anv_pipeline_link_* helpers are called which are
responsible for setting up the binding table and doing anything needed
to properly link with the next stage in the pipeline if one exists.
They are called in reverse order starting with the fragment shader so
you can assume linking in later stages is already done.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
We can set active_stages much more directly and then it's just candy
around setting pipeline->stages[stage].
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Instead of hashing each stage separately (and TES and TCS together), we
hash the entire pipeline. This means we'll get fewer cache hits if
they, for instance, re-use the same VS over and over again but it also
means we can now safely do cross-stage optimizations.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Instead of having each anv_pipeline_compile_* function populate the
shader key, make it part of the anv_pipeline_stage struct and fill it
out up-front.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
During code review, Jason pointed out that:
2b3064c073 "i965, anv: Use INTEL_DEBUG for disk_cache driver flags"
Didn't account for INTEL_SCALER_* environment variables.
To fix this, let the compiler return the disk_cache driver flags.
Another possible fix would be to pull the INTEL_SCALER_* into
INTEL_DEBUG bits, but as we are currently using 41 of 64 bits, I
didn't think it was a good use of 4 more of these bits. (5 since
INTEL_PRECISE_TRIG needs to be accounted for as well.)
Cc: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Shader time hard codes an index of the shader time buffer within the
gen program.
In order to support shader time in the disk shader cache, we'd need to
add the shader time index into the program key. This should work, but
probably is not worth it for this particular debug feature.
Therefore, let's just disable the disk shader cache if the shader time
debug feature is used.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=106382
Fixes: 96fe36f7ac "i965: Enable disk shader cache by default"
Cc: Eero Tamminen <eero.t.tamminen@intel.com>
Cc: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Instead of just looking at the number of color attachments, look at
which ones are actually used by the subpass. This lets us potentially
throw away chunks of the fragment shader. In DXVK, for example, all
subpasses have 8 attachments and most are VK_ATTACHMENT_UNUSED so this
is very helpful in that case.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
The back-end compiler emits the number of color writes specified by
wm_prog_key::nr_color_regions regardless of what nir_store_outputs we
have. Once we've gone through and figured out which render targets
actually exist and are written by the shader, we should restrict the key
to avoid extra RT write messages.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
With the new deref instructions, we have to keep the modes consistent
between the derefs and the variables they reference. Since we remove
outputs by changing them to local variables, we need to run the fixup
pass to fix the modes.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
The NIR nir_lower_io_arrays_to_elements pass attempts to split I/O
variables which are arrays or matrices into a sequence of separate
variables. This can help link-time optimization by allowing us to
remove varyings at a more granular level.
Shader-db results on Kaby Lake:
total instructions in shared programs: 15177645 -> 15168494 (-0.06%)
instructions in affected programs: 79857 -> 70706 (-11.46%)
helped: 392
HURT: 0
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Otherwise, only the first vec4 of a matrix or other complex type will
get marked as flat and we'll interpolate the others. This was caught by
a dEQP test which started failing because it did a SSO vs. non-SSO
comparison. Previously, we did the interpolation wrong consistently in
both versions. However, with one of Tim Arceri's NIR linkingpatches, we
started splitting the matrix input into vectors at link time in the
non-SSO version and it started getting correctly interpolated which
didn't match the broken SSO version. As of this commit, they both get
correctly interpolated.
Fixes: e61cc87c75 "i965/fs: Add a flat_inputs field to prog_data"
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Gen10+ has an additional bit in MI_BATCH_BUFFER_END to signal the end
of the context image.
We select the largest size for the context image regardless of the
generation.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Rafael Antognolli <rafael.antognolli@intel.com>
In both Python 2 and 3, zlib.Compress.compress() takes a byte string,
and returns a byte string as well.
In Python 2, the script was working because:
1. string literalls were byte strings;
2. opening a file in unicode mode, reading from it, then passing the
unicode string to compress() would automatically encode to a byte
string;
On Python 3, the above two points are not valid any more, so:
1. zlib.Compress.compress() refuses the passed unicode string;
2. compressed_data, defined as an empty unicode string literal, can't be
concatenated with the byte string returned by compress();
This commit fixes this by explicitly using byte strings where
appropriate, so that the script works on both Python 2 and 3.
Signed-off-by: Mathieu Bridon <bochecha@daitauha.fr>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
The XML parser wants byte strings, not unicode strings.
In both Python 2 and 3, opening a file without specifying the mode will
open it for reading in text mode ('r').
On Python 2, the read() method of the file object will return byte
strings, while on Python 3 it will return unicode strings.
Explicitly specifying the binary mode ('rb') makes the behaviour
identical in both Python 2 and 3, returning what the XML parser
expects.
Signed-off-by: Mathieu Bridon <bochecha@daitauha.fr>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Reviewed-by: Dylan Baker <dylan@pnwbakers.com>
In Python 2, iterating over a byte-string yields single-byte strings,
and we can pass them to ord() to get the corresponding integer.
In Python 3, iterating over a byte-string directly yields those
integers.
Transforming the byte string into a bytearray gives us a list of the
integers corresponding to each byte in the string, removing the need to
call ord().
This makes the script compatible with both Python 2 and 3.
Signed-off-by: Mathieu Bridon <bochecha@daitauha.fr>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
The hardware doesn't support byte immediates, so similar to setup_imm_df()
for doubles, these helpers work by loading the constant value into a
VGRF.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Gen 11 workarounds table #2056 WABTPPrefetchDisable suggests to
disable prefetching of binding tables for ICLLP A0 and B0
steppings. It fixes multiple gpu hangs in
ext_framebuffer_multisample* tests on ICLLP B0 h/w.
Anuj: Add comments and commit message.
Add gen 11 checks in the code.
Signed-off-by: Anuj Phogat <anuj.phogat@gmail.com>
Reviewed-by: Rafael Antognolli <rafael.antognolli@intel.com>
The pass can create a temporary result for the instruction and then
moves from it to the original destination, however, if the original
instruction was predicated, the mov has to be predicated as well.
Reviewed-by: Jose Maria Casanova Crespo <jmcasanova@igalia.com>
Until now, we had separate passes for lowering gl_PatchVerticesIn to
a statically known constant (for TES inputs when linked against a TCS),
and a uniform in the other cases. Annoyingly, one had to be run before
nir_lower_system_values, and the other afterward. This simplified the
passes, but made life painful for the callers.
This patch combines both into a single pass. If you give it a non-zero
static count, it uses that. If you give it Mesa state slots, it turns
it back into a built-in uniform. Otherwise, it does nothing.
This also moves the i965 uniform lowering out to shared code.
v2: Make token arrays const.
Reviewed-by: Eric Anholt <eric@anholt.net>
These are lowered by brw_nir_lower_vs_inputs(). If they weren't, we
would have already hit the unreachable() in emit_system_values_block().
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
The various base addresses are simply addresses. There may or may not
be a buffer located at those addresses. So, it doesn't make much sense
to request one. Just save the raw address so we can add it later, when
asking about BOs at the final <base + offset> address.
Suggested-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Normally, i965 programs STATE_BASE_ADDRESS every batch, and puts all
state for a given base in a single buffer.
I'm working on a prototype which emits STATE_BASE_ADDRESS only once at
startup, where each base address is a fixed 4GB region of the PPGTT.
State may live in many buffers in that 4GB region, even if there isn't
a buffer located at the actual base address itself.
To handle this, we need to save the STATE_BASE_ADDRESS values across
multiple batches, rather than assuming we'll see the command each time.
Then, each time we see a pointer, we need to ask the driver for the BO
map for that data. (We can't just use the map for the base address, as
state may be in multiple buffers, and there may not even be a buffer
at the base address to map.)
v2: Fix things caught in review by Lionel:
- Drop bogus bind_bo.size check.
- Drop "get the BOs again" code - we just get the BOs as needed
- Add a message about interface descriptor data being unavailable
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
CovID: 1438132
Fixes: a99c9e63a0 "anv: finish the binding_table_pool on
destroyDevice when use_softpin"
Signed-off-by: Eric Engestrom <eric.engestrom@intel.com>
Reviewed-by: Jose Maria Casanova Crespo <jmcasanova@igalia.com>
We might fail on master node drm fd because we won't have the right
permissions.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
Since various options within INTEL_DEBUG could impact code generation,
we need to set the disk cache driver_flags parameter based on the
INTEL_DEBUG flags in use.
An example that will affect the program generated by i965 is the
INTEL_DEBUG=nocompact option.
The DEBUG_DISK_CACHE_MASK value is added to mask the settings of
INTEL_DEBUG that can affect program generation.
v2:
* Use driver_flags (Tim)
* Also update Anvil (Jason)
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
This extra character should not be used by snprintf, but we make it
available to verify that we printed the exact number we wanted, and
didn't overflow.
v2:
* Also update Anvil
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
we need rounding modes on other conversions involving floats and it is easier
to rename f2f16_undef than renaming all the other ones.
v2: rebased on master
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Acked-by: Rob Clark <robdclark@gmail.com>
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Python 2 has a range() function which returns a list, and an xrange()
one which returns an iterator.
Python 3 lost the function returning a list, and renamed the function
returning an iterator as range().
As a result, using range() makes the scripts compatible with both Python
versions 2 and 3.
Signed-off-by: Mathieu Bridon <bochecha@daitauha.fr>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Reviewed-by: Dylan Baker <dylan@pnwbakers.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
In Python 2, dictionaries have 2 sets of methods to iterate over their
keys and values: keys()/values()/items() and iterkeys()/itervalues()/iteritems().
The former return lists while the latter return iterators.
Python 3 dropped the method which return lists, and renamed the methods
returning iterators to keys()/values()/items().
Using those names makes the scripts compatible with both Python 2 and 3.
Signed-off-by: Mathieu Bridon <bochecha@daitauha.fr>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Reviewed-by: Dylan Baker <dylan@pnwbakers.com>
