../src/intel/compiler/brw_fs_nir.cpp:3534:46: warning: comparison of integer expressions of different signedness: ‘unsigned int’ and ‘int’ [-Wsign-compare]
assert(nir_intrinsic_write_mask(instr) ==
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~
(1 << instr->num_components) - 1);
~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
This was caused by 6339aba775 which added these completely valid
checks. However clang likes to complain about signedness mismatches.
Fixes: 6339aba775 "intel/compiler: Lower SSBO and shared..."
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
We have a bunch of code to do this in the back-end compiler but it's
fairly specific to typed surface messages and the way we emit them.
This breaks it out into NIR were it's easier to do things a bit more
generally. It also means we can easily share the code between the vec4
and FS back-ends if we wish.
Reviewed-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com>
As of this commit, all uses of const sources either go through a
nir_src_as_<type> helper which handles bit sizes correctly or else are
accompanied by a nir_src_bit_size() == 32 assertion to assert that we
have the size we think we have.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Everywhere we handle SSBO intrinsics, we have exactly the same pattern
for computing the index so we may as well make a helper for it. We also
add a get_nir_src_imm to vec4 and use it for SSBO offsets.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
This isn't true for Vulkan so we have to whack it to "main" in anv which
is silly. Instead of walking the list of functions and asserting that
everything is named "main" and hoping there's only one function named
"main", just use the nir_shader_get_entrypoint() helper which has better
assertions anyway.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Several of the Atom GPUs have additional restrictions on alignment when
moving < 64-bit source to a 64-bit destination. All of the nir_op_*2*64
code generation paths respected this, but nir_op_b2[fi] did not.
Previous to commit a68dd47b91 it was not possible to generate such an
instruction from the GLSL path. It may have been possible from SPIR-V,
but it's not clear. The aforementioned patch converts a 64-bit
nir_op_fsign into a sequence of operations including a nir_op_b2f with a
64-bit result. This "just works" everywhere except these Atom parts.
This problem was not detected during normal CI testing because the Atom
parts are not included in developer builds.
v2 (idr): Make the patch compile, and make some cosmetic changes. Add a
commit message.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108319
Fixes: a68dd47b91 "nir/algebraic: Simplify fsat of fsign"
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
No shader-db or CI changes on any Intel platform.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Thomas Helland <thomashelland90@gmail.com>
and _mesa_bitcount_64 with util_bitcount_64. This fixes a build problem
in nir for platforms that don't have popcount or popcountll, such as
32bit msvc.
v2: - Fix additional uses of _mesa_bitcount added after this was
originally written
Acked-by: Eric Engestrom <eric.engestrom@intel.com> (v1)
Acked-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Unused since 09f1de97a7 "anv,i965: Lower away image derefs in
the driver".
Cc: Jason Ekstrand <jason.ekstrand@intel.com>
Signed-off-by: Eric Engestrom <eric@engestrom.ch>
Acked-by: Jason Ekstrand <jason@jlekstrand.net>
This is the second patch needed to fix the following piglit tests:
tests/spec/arb_gl_spirv/linker/uniform/multisampler.shader_test
tests/spec/arb_gl_spirv/linker/uniform/multisampler-array.shader_test
Although in this case it doesn't affect so many borrowed tests, as
there aren't too many tests using multisamplers on Intel.
It is worth to note that this patch is also needed when those tests
are run on GLSL mode (using the --glsl option). Although most Intel
drivers would not be able to run/execute tests using multisamplers, as
GL_MAX_IMAGE_SAMPLES is zero, technically those tests are expected to
link correctly, so linking tests should pass.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Previously, the back-end compiler turn image access into magic uniform
reads and there was a complex contract between back-end compiler and
driver about setting up and filling out those params. As of this
commit, both drivers now lower image_deref_load_param_intel intrinsics
to load_uniform intrinsics controlled by the driver and lower the other
image_deref_* intrinsics to image_* intrinsics which take an actual
binding table index. There are still "magic" uniforms but they are now
added and controlled entirely by the driver and that contract no longer
spans components.
This also has the side-effect of making most image use compile-time
binding table indices. Previously, all image access pulled the binding
table index from a uniform. Part of the reason for this was that the
magic uniforms made it difficult to decouple binding table indices from
the uniforms and, since they are indexed completely differently
(especially in Vulkan), it was hard to pull them apart. Now that the
driver is handling both, it's trivial to decouple the two and provide
actual binding table indices.
Shader-db results on Kaby Lake:
total instructions in shared programs: 15166872 -> 15164293 (-0.02%)
instructions in affected programs: 115834 -> 113255 (-2.23%)
helped: 191
HURT: 0
total cycles in shared programs: 571311495 -> 571196465 (-0.02%)
cycles in affected programs: 4757115 -> 4642085 (-2.42%)
helped: 73
HURT: 67
total spills in shared programs: 10951 -> 10926 (-0.23%)
spills in affected programs: 742 -> 717 (-3.37%)
helped: 7
HURT: 0
total fills in shared programs: 22226 -> 22201 (-0.11%)
fills in affected programs: 1146 -> 1121 (-2.18%)
helped: 7
HURT: 0
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
This commit moves our storage image format conversion codegen into NIR
instead of doing it in the back-end. This has the advantage of letting
us run it through NIR's optimizer which is pretty effective at shrinking
things down. In the common case of rgba8, the number of instructions
emitted after NIR is done with it is half of what it was with the
lowering happening in the back-end. On the downside, the back-end's
lowering is able to directly use predicates and the NIR lowering has to
use IFs.
Shader-db results on Kaby Lake:
total instructions in shared programs: 15166910 -> 15166872 (<.01%)
instructions in affected programs: 5895 -> 5857 (-0.64%)
helped: 15
HURT: 0
Clearly, we don't have that much image_load_store happening in the
shaders in shader-db....
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
This greatly simplifies the next patch.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Adds suppport for INTEL_fragment_shader_ordering. We achieve
the fragment ordering by using the same instruction as for
beginInvocationInterlockARB() which is by issuing a memory
fence via sendc.
Signed-off-by: Kevin Rogovin <kevin.rogovin@intel.com>
Reviewed-by: Plamena Manolova <plamena.manolova@intel.com>
v2: Split changes to the message type field to another patch. Suggested
by Caio.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@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>
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>
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>
Until now we have assumed that we could skip emitting these barriers
in the general case based on empirical testing and a few assumptions
detailed in a comment in the driver code, however, recent CTS tests
have showed that we actually need them to produce correct behavior.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
In 6f5abf3146 this code was fixed to calculate the maximum size of
an attribute in a seperate pass and then allocate the registers to
that size. However this wasn’t taking into account ranges that overlap
but don’t have the same starting location. For example:
layout(location = 0, component = 0) out float a[4];
layout(location = 2, component = 1) out float b[4];
Previously, if ‘a’ was processed first then it would allocate a
register of size 4 for location 0 and it wouldn’t allocate another
register for location 2 because it would already be covered by the
range of 0. Then if something tries to write to b[2] it would try to
write past the end of the register allocated for ‘a’ and it would hit
an assert.
This patch changes it to scan for any overlapping ranges that start
within each range to calculate the maximum extent and allocate that
instead.
Fixed Piglit’s arb_enhanced_layouts/execution/component-layout/
vs-fs-array-interleave-range.shader_test
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Fixes: 6f5abf3146 "i965: Fix output register sizes when multiple variables
share a slot."
This reworks INTERPOLATE_AT_PER_SLOT_OFFSET to work more like an ALU
operation and less like a send. This is less code over-all and, as a
side-effect, it now properly handles execution groups and lowering so
SIMD32 support just falls out.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Current discard handling requires dedicating the second flag register to
discard. However, control-flow in SIMD32 requires both flag registers
so it's incompatible with the current discard handling. Just don't
support SIMD32+discard for now.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Matt Turner <mattst88@gmail.com>
The hardware's control flow logic is 16-wide so we're out of luck
here. We could, in theory, support SIMD32 if we know the control-flow
is uniform but we don't have that information at this point.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Since we had to rewrite the deref walking loop anyway, I took the
opportunity to make it a bit clearer and more efficient. In particular,
in the AoA case, we will now emit one minmax instead of one per array
level.
Acked-by: Rob Clark <robdclark@gmail.com>
Acked-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Acked-by: Dave Airlie <airlied@redhat.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
As the previous use of shuffle_32bit_load_result_to_64bit_data
had a source/destination overlap for 64-bit. Now a temporary destination
is used for 64-bit cases to use shuffle_from_32bit_read that doesn't
handle src/dst overlaps.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Previously, the shuffle function had a source/destination overlap that
needs to be avoided to use shuffle_from_32bit_read. As we can use for
the shuffle destination the destination of removed MOVs.
This change also avoids the internal MOVs done by the previous shuffle
to deal with possible overlaps.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
shuffle_from_32bit_read manages 32-bit reads to 32-bit destination
in the same way that the previous loop so now we just call the new
function for all bitsizes, simplifying also the 64-bit load_input.
v2: Add comment about future 16-bit support (Jason Ekstrand)
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
This implementation avoids two unneeded MOVs for each 64-bit
component. One was done in the old shuffle, to avoid cases of
src/dst overlap but this is not the case. And the removed MOV
was already being being done in the shuffle.
Copy propagation wasn't able to remove them because shuffle
destination values are defined with partial writes because they
have stride == 2.
v2: Reword commit log summary (Jason Ekstrand)
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
do_untyped_vector_read is used at load_ssbo and load_shared.
The previous MOVs are removed because shuffle_from_32bit_read
can handle storing the shuffle results in the expected destination
just using the proper offset.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Using shuffle_from_32bit_read instead of 16-bit shuffle functions
avoids the need of retype. At the same time new function are
ready for 8-bit type SSBO reads.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
These new shuffle functions deal with the shuffle/unshuffle operations
needed for read/write operations using 32-bit components when the
read/written components have a different bit-size (8, 16, 64-bits).
Shuffle from 32-bit to 32-bit becomes a simple MOV.
shuffle_src_to_dst takes care of doing a shuffle when source type is
smaller than destination type and an unshuffle when source type is
bigger than destination. So this new read/write functions just need
to call shuffle_src_to_dst assuming that writes use a 32-bit
destination and reads use a 32-bit source.
As shuffle_for_32bit_write/from_32bit_read components take components
in unit of source/destination types and shuffle_src_to_dst takes units
of the smallest type component, we adjust components and first_component
parameters.
To enable this new functions it is needed than there is no
source/destination overlap in the case of shuffle_from_32bit_read.
That never happens on shuffle_for_32bit_write as it allocates a new
destination register as it was at shuffle_64bit_data_for_32bit_write.
v2: Reword commit log and add comments to explain why first_component
and components parameters are adjusted. (Jason Ekstrand)
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
This new function takes care of shuffle/unshuffle components of a
particular bit-size in components with a different bit-size.
If source type size is smaller than destination type size the operation
needed is a component shuffle. The opposite case would be an unshuffle.
Component units are measured in terms of the smaller type between
source and destination. As we are un/shuffling the smaller components
from/into a bigger one.
The operation allows to skip first_component number of components from
the source.
Shuffle MOVs are retyped using integer types avoiding problems with
denorms and float types if source and destination bitsize is different.
This allows to simplify uses of shuffle functions that are dealing with
these retypes individually.
Now there is a new restriction so source and destination can not overlap
anymore when calling this shuffle function. Following patches that migrate
to use this new function will take care individually of avoiding source
and destination overlaps.
v2: (Jason Ekstrand)
- Rewrite overlap asserts.
- Manage type_sz(src.type) == type_sz(dst.type) case using MOVs
from source to dest. This works for 64-bit to 64-bits
operation that on Gen7 as it doesn't support Q registers.
- Explain that components units are based in the smallest type.
v3: - Fix unshuffle overlap assert (Jason Ekstrand)
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Adds suppport for ARB_fragment_shader_interlock. We achieve
the interlock and fragment ordering by issuing a memory fence
via sendc.
Signed-off-by: Plamena Manolova <plamena.manolova@intel.com>
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
The only reason it was it's own opcode was so that we could detect it
and adjust the source register based on the payload setup. Now that
we're using the ATTR file for FS inputs, there's no point in having a
magic opcode for this.
v2 (Jason Ekstrand):
- Break the bit which removes the CINTERP opcode into its own patch
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Matt Turner <mattst88@gmail.com>
