That is: the five least significant bits provide the values of
'bits' and 'offset' which is the case for all hardware currently
supported by NIR and using the bfm/bfe instructions.
This patch also changes the lowering of bitfield_insert/extract
using shifts to not use bfm and removes the flag 'lower_bfm'.
Tested-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Connor Abbott <cwabbott0@gmail.com>
These optimizations are based on the fact that
'and(a,b) <= umin(a,b)'.
For AMD, this series moves the optimization from LLVM to NIR,
so currently no vkpipeline-db changes here.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
We don't expect the output of a TXS instruction to be wider than a
vec3. Add an assert() to make sure this never happens.
Suggested-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Most places in NIR, we treat matrices like arrays. The one annoying
exception to this has been nir_constant where a matrix is a first-class
thing. This commit changes that so a matrix nir_constant is the same as
an array nir_constant. This makes matrix nir_constants a tiny bit more
expensive but shrinks all others by 96B.
Reviewed-by: Karol Herbst <kherbst@redhat.com>
The spec explicitly says that volatile writes can't be removed and
volatile reads do not guarantee that the same value will still be around
after the read, as if there were a barrier after each read/write. Just
ignore them.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
We were completely ignoring these before, except for putting them on
variables. While we're here, don't set access qualifiers when converting
to bindless since glsl_to_nir will already have set a more accurate
qualifier that includes any qualifiers on struct members that are
dereferenced.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
In the next commit, we'll properly handle access qualifiers on struct
members by propagating them to load/store instructions, but these
instructions had no way to specify the qualifier.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
This effectively does the opposite of nir_lower_alus_to_scalar, trying
to combine per-component ALU operations with the same sources but
different swizzles into one larger ALU operation. It uses a similar
model as CSE, where we do a depth-first approach and keep around a hash
set of instructions to be combined, but there are a few major
differences:
1. For now, we only support entirely per-component ALU operations.
2. Since it's not always guaranteed that we'll be able to combine
equivalent instructions, we keep a stack of equivalent instructions
around, trying to combine new instructions with instructions on the
stack.
The pass isn't comprehensive by far; it can't handle operations where
some of the sources are per-component and others aren't, and it can't
handle phi nodes. But it should handle the more common cases, and it
should be reasonably efficient.
[Alyssa: Rebase on latest master, updating with respect to typeless
moves]
Acked-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Acked-by: Jason Ekstrand <jason@jlekstrand.net>
The V3D driver has an open-coded solution for this, and we need the
same thing for Panfrost, so let's add a generic way to lower TXS(LOD)
into max(TXS(0) >> LOD, 1).
Changes in v2:
* Use == 0 instead of !
* Rework the minification logic as suggested by Jason
* Assign cursor pos at the beginning of the function
* Patch the LOD just after retrieving the old value
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
get_texture_size() will create a txs instruction with ->sampler_dim set
to the original tex->sampler_dim. The condition to call lower_rect()
only checks the value of ->sampler_dim and whether lower_rect is
requested or not. This leads to an infinite loop when calling
nir_lower_tex() with the same options until it returns false.
In order to avoid that, let's move the tex->sampler_dim patching before
get_texture_size() is called. This way the txs instruction will have
->sampler_dim set to GLSL_SAMPLER_DIM_2D and nir_lower_tex() won't try
to lower it on the subsequent passes.
Changes in v2:
* Add Jason R-b
* Add a comment explaining why we patch ->sampler_dim at the beginning
of the lower_rect() func
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
The code considers that projector lowering was done even if it's not
really the case. Change the project_src() prototype to return a bool
encoding whether projector lowering happened or not and update the
progress var accordingly in nir_lower_tex_block().
---
Changes in v2:
* Add Jason R-b
* Drop the part suggesting that nir_lower_rect() could be called in
a do-while(progress) loop.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
This fixes a rebase fail in ea51275e07, and prevents it from happening
again. There's no reason to do this manually.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
The rules added in patch 3addd7c are inverted:
It should be:
(al * bh) << 16 + c
instead of:
(ah * bl) << 16 + c
Fixes a number of regressions under
dEQP-GLES31.functional.draw_indirect.compute_interop.large.*
on Freedreno.
Reviewed-by: Rob Clark <robdclark@gmail.com>
Fixes: cd73b6174b "nir/lower_to_source_mods: Stop turning add, sat, and neg into mov"
Signed-off-by: Eric Engestrom <eric.engestrom@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
For umul_low (al * bl), zero is returned if the low 16-bits word of either
source is zero.
for imadsh_mix16 (ah * bl << 16 + c), c is returned if either 'ah' or 'bl'
is zero.
A couple of nir_search_helpers are added:
is_upper_half_zero() returns true if the highest word of all components of
an integer NIR alu src are zero.
is_lower_half_zero() returns true if the lowest word of all components of
an integer nir alu src are zero.
Reviewed-by: Eric Anholt <eric@anholt.net>
'umul_low' is the low 32-bits of unsigned integer multiply. It maps
directly to ir3's MULL_U.
'imadsh_mix16' is multiply add with shift and mix, an ir3 specific
instruction that maps directly to ir3's IMADSH_M16.
Both are necessary for the lowering of integer multiplication on
Freedreno, which will be introduced later in this series.
Reviewed-by: Eric Anholt <eric@anholt.net>
We originally had a single lower_fmod option. In commit 2ab2d2e5, Sam
split 32 and 64-bit lowering into separate flags, with the rationale
that some drivers might want different options there. This left 16-bit
unhandled, so Iago added a lower_fmod16 option in commit ca31df6f.
Now that lower_fmod64 is gone (in favor of nir_lower_doubles and
nir_lower_dmod), we re-combine lower_fmod16 and lower_fmod32 into a
single lower_fmod flag again. I'm not aware of any hardware which
need lowering for one bitsize and not the other.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
nir_lower_doubles offers a wide variety of fp64 lowering, including
lowering fmod@64. The version there also better handles imprecisions
due to lowered frcp@64. Let's consolidate on one version.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Instead, we add a new helper which stomps one nir_shader and replaces it
with another. The new helper effectively just changes which pointer
gets used for the base nir_shader. It should be 99% as good at testing
cloning but without requiring that everything handle having the shader
swapped out from under it constantly.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108957
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Rob Clark <robdclark@chromium.org>
This pattern was noticed in glmark's jellyfish scene.
v2: Add inexact qualifier due to NaN behaviour.
Minimal shader-db changes (slightly helped).
Signed-off-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Reviewed-by: Elie Tournier <tournier.elie@gmail.com>
v2: Fix comparing addresses from formats that have more than one
component by using nir_ball_iequal(). (Jason)
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Fixes: c1275052 "nir: add type information to load uniform/input and store output intrinsics"
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Erico Nunes <nunes.erico@gmail.com>
Tested-by: Erico Nunes <nunes.erico@gmail.com>
Tested-by: Andreas Baierl <ichgeh@imkreisrum.de>
Now that the type gathering function look at instructions that might
have other types, return invalid type instead of crashing. That
invalid will be properly ignored later.
Fixes: c12750527b "nir: add type information to load uniform/input and store output intrinsics"
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Removes the bool_to_float logic from the int_to_float pass, so that both
can be used separately. By having separate passes we have better validation
and it makes it possible to use with the lower_ftrunc option (int lowering
generates ftrunc, but lower_ftrunc generates bools, ftrunc lowering should
probably be reworked). For now we always expect lower_bool to come after
lower_int.
Also fixes f2i32 to become ftrunc and adds u2f/f2u cases.
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
It is treated like the vecN instructions which also have no type.
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Add a "lower_bitshift" option, which disables optimizations introducing
bitshifts and lowers ishl by constant to a multiply, so that we don't have
to deal with bitshifts in int_to_float lowering.
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Consts and undefs can be used as different types (common with "0" constant)
so don't copy types from consts/undefs, only to them. It doesn't entirely
solve the problem that the type given to the const could be wrong , but
now the only realistic case is with "0" which is the same when casted to
float, so it doesn't matter for lower_int_to_float.
The other change is to get type information for load input/uniform and
store output, and use that to get correct results.
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
This type information will be used by gather_ssa_types to get usable results
Signed-off-by: Jonathan Marek <jonathan@marek.ca>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Before this change, we were searching for each instruction twice, once
when checking if it exists and once when figuring out where to insert
it. By using the new function, we can do everything we need to do in one
operation.
Compilation time numbers for my shader-db database:
Difference at 95.0% confidence
-4.04706 +/- 0.669508
-0.922142% +/- 0.151948%
(Student's t, pooled s = 0.95824)
Reviewed-by: Eric Anholt <eric@anholt.net>
Acked-by: Jason Ekstrand <jason@jlekstrand.net>
On some architectures, Boolean values used to control conditional
branches or condtional selection must be propagated into a flag. This
generally means that a stored Boolean value must be compared with zero.
Rather than force the generation of extra compares with zero, re-emit
the original comparison instruction. This can save register pressure by
not needing to store the Boolean value.
There are several possible ares for future improvement to this pass:
1. Be more conservative. If both sources to the comparison instruction
are non-constants, it may be better for register pressure to emit the
extra compare. The current shader-db results on Intel GPUs (next
commit) lead me to believe that this is not currently a problem.
2. Be less conservative. Currently the pass requires that all users of
the comparison match the pattern. The idea is that after the pass is
complete, no instruction will use the resulting Boolean value. The only
uses will be of the flag value. It may be beneficial to relax this
requirement in some cases.
3. Be less conservative. Also try to rematerialize comparisons used for
discard_if intrinsics. After changing the way the Intel compiler
generates cod e for discard_if (see MR!935), I tried implementing this
already. The changes were pretty small. Instructions were helped in 19
shaders, but, overall, cycles were hurt. A commit "nir: Rematerialize
comparisons for nir_intrinsic_discard_if too" is on my fd.o cgit.
4. Copy the preceeding ALU instruction. If the comparison is a
comparison with zero, and it is the only user of a particular ALU
instruction (e.g., (a+b) != 0.0), it may be a further improvment to also
copy the preceeding ALU instruction. On Intel GPUs, this may enable
cmod propagation to make additional progress.
v2: Use much simpler method to get the prev_block for an if-statement.
Suggested by Tim.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Found with Jasons new metadata rework (https://gitlab.freedesktop.org/mesa/mesa/merge_requests/950).
Fixes: af355aaa07 "nir: add nir_opt_move_load_ubo() optimization pass"
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Because the core principle of the vars_to_ssa pass is that it globally
(within a function) looks at all of the uses of a never-indirected path
and does a full into-SSA on that path, it can't handle a path which has
any chance of having aliasing. If a function_temp variable has a cast
or anything else which may cause aliasing, we have to assume that all
paths to that variable may alias and ignore the entire variable.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
We're about to change the meaning of get_deref_node returning NULL so we
need a non-NULL value to mean properly undefined.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
This lets passes easily detect derefs which have uses that fall outside
the standard load/store/copy pattern so they can bail appropriately.
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
When we inlined cf_node_has_side_effects into node_is_dead, all the
conditions flipped and we forgot to flip one. Fortunately, it doesn't
matter right now because no one uses this pass on shaders with more than
one function.
Fixes: b50465d197 "nir/dead_cf: Inline cf_node_has_side_effects"
Reviewed-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
This mode is used by PhysicalStorageBufferEXT storage class.
Fixes: 8bdf5a008b "nir: Allow derefs to be used as phi sources"
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Silence two unused var warnings. And init elem_size, elem_align to
zero to silence "maybe uninitialized" warnings.
Reviewed-by: Kristian H. Kristensen <hoegsberg@google.com>
It is possible and valid for a pointer to be selected based on a
conditional before used, and depending on the mode, those cases will
result in a phi with derefs as sources.
To achieve this, we don't rematerialize derefs that are used by phis.
As a consequence, when converting from SSA to regs, we may have phis
that come from different blocks and are used by phis. We now convert
those to regs too.
Validation was added to ensure only derefs of certain modes can be
used as phi sources. No extra validation is needed for the presence
of cast, any instruction that uses derefs will validate the
deref-chain is complete (ending in a cast or a var).
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
