Decorations (and ExecutionModes) can have not only literals, but also
Ids associated with them. So rename the field to the more general
name "Operand" used by the spec.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
This reverts commit 9e0c744f07, which
regressed dEQP-GLES2.functional.uniform_api.random.3. It turns out
that the newly produced location is meaningless and impossible to
consume by drivers that want to look at gl_uniform_storage, so it's
probably better to leave it unset (0) than a number that looks usable.
Leave a tombstone^Wcomment to discourage the next person from making
the obvious looking fix.
See the next commit for a longer description of the problem.
This breaks tests/spec/glsl-1.10/execution/samplers/uniform-struct
on i965, which was originally fixed by the revert. The next commit
will fix it again.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
We have a macro for this now; no reason to hand-roll it for derefs.
While we're here, move the NIR_DEFINE_CAST for derefs down to where all
the other ones are.
Reviewed-by: Eric Anholt <eric@anholt.net>
When we have a bindless sampler, we need an instruction header. Even in
SIMD8, this pushes the instruction over the sampler message size maximum
of 11 registers. Instead, we have to lower TXD to TXL.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Compiler warns about overflow when assigning UINT64_MAX to something
smaller than a uin64_t:
src/compiler/nir/nir_constant_expressions.c:16909:50: warning: implicit conversion from 'unsigned long long' to 'uint1_t' (aka 'unsigned char') changes value from 18446744073709551615 to 255 [-Wconstant-conversion]
uint1_t dst = (src0 + src1) < src0 ? UINT64_MAX : (src0 + src1);
~~~ ^~~~~~~~~~
Shift UINT64_MAX down to the appropriate maximum value for the type
being assigned to.
Signed-off-by: Kristian H. Kristensen <hoegsberg@google.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
If we want to assert on found == true when the loop exits early, we
need to initialize it to false.
Signed-off-by: Kristian H. Kristensen <hoegsberg@chromium.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
When looking at the dEQP nested_struct_array_dynamic_index_fragment code
after lowering, I was horrified at the amount of adding and multiplying by
0 we were doing. The builder _imm helpers handle that for you so that the
following optimization passes have less work to do. Plus, it's easier to
read.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
We were calcuating the offset for the field within the struct, and just
dropping it on the floor. Fixes a regression in
KHR-GLES3.shaders.struct.local.nested_struct_array_dynamic_index_fragment
and a few of its friends since the scratch lowering commit.
Fixes: e8e159e9df ("nir/deref: Add helpers for getting offsets")
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
The mali utgard pp doesn't support a sign instruction.
In the ARM offline shader compiler, the sign function is implemented
using sub(gt(0.0, a), lt(0.0, a)).
This is a generic optimization, so implement it in the nir level when
lower_fsign is set, alongside the lowering for isign.
Signed-off-by: Erico Nunes <nunes.erico@gmail.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
All of the affected shaders are in Mad Max. I noticed this while
looking at some other things. I tried a couple similar patterns, but
the affect on cycles was general negative. It may be worth revisiting
this later.
v2: Rebase on 1-bit Boolean changes.
All Gen7+ platforms had similar results. (Skylake shown)
total instructions in shared programs: 15282073 -> 15282053 (<.01%)
instructions in affected programs: 1192 -> 1172 (-1.68%)
helped: 14
HURT: 0
helped stats (abs) min: 1 max: 2 x̄: 1.43 x̃: 1
helped stats (rel) min: 1.16% max: 2.17% x̄: 1.65% x̃: 1.39%
95% mean confidence interval for instructions value: -1.73 -1.13
95% mean confidence interval for instructions %-change: -1.91% -1.38%
Instructions are helped.
total cycles in shared programs: 372595954 -> 372594532 (<.01%)
cycles in affected programs: 11477 -> 10055 (-12.39%)
helped: 14
HURT: 0
helped stats (abs) min: 76 max: 122 x̄: 101.57 x̃: 104
helped stats (rel) min: 7.76% max: 15.62% x̄: 12.94% x̃: 14.78%
95% mean confidence interval for cycles value: -111.05 -92.09
95% mean confidence interval for cycles %-change: -14.90% -10.98%
Cycles are helped.
No changes on any Gen6 or earlier platforms.
Reviewed-by: Matt Turner <mattst88@gmail.com>
All of the affected shaders are in Mad Max. The inner part of the
pattern is itself an open-coded sign(a). I tried using that as a
pattern, but the results were not good. A bunch of shaders were helped
for instructions, but overall cycles, spill, and fills were hurt.
v2: Rebase on 1-bit Boolean changes.
v3: Fix order of copysign() parameters in comments and commit message.
Noticed by Matt.
All Gen7+ platforms had similar results. (Skylake shown)
total instructions in shared programs: 15282141 -> 15282073 (<.01%)
instructions in affected programs: 6106 -> 6038 (-1.11%)
helped: 17
HURT: 0
helped stats (abs) min: 4 max: 4 x̄: 4.00 x̃: 4
helped stats (rel) min: 1.02% max: 2.20% x̄: 1.15% x̃: 1.06%
95% mean confidence interval for instructions value: -4.00 -4.00
95% mean confidence interval for instructions %-change: -1.30% -1.00%
Instructions are helped.
total cycles in shared programs: 372597886 -> 372595954 (<.01%)
cycles in affected programs: 32701 -> 30769 (-5.91%)
helped: 17
HURT: 0
helped stats (abs) min: 6 max: 216 x̄: 113.65 x̃: 118
helped stats (rel) min: 0.40% max: 21.86% x̄: 6.20% x̃: 5.83%
95% mean confidence interval for cycles value: -152.84 -74.45
95% mean confidence interval for cycles %-change: -8.89% -3.51%
Cycles are helped.
No changes on any Gen6 or earlier platforms.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Other nir_src_as_* functions just take a nir_src. It's not that much
more memory copying and the constness preserving really isn't worth the
cognitive dissonance.
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
v2: When available, include the opcode name too. (Karol)
v3: Use more to_string helpers. (Karol)
Include the wrong bit_size in those failures.
Include the capability number in spv_check_supported.
Provide vtn_fail_with_* macros to avoid noise in the call sites.
v4: Provide macros only for opcode and decoration, which have enough
usages to justify them. (Jason)
Acked-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Also, use a set to identify repeated values. The previous arrangement
worked when the repetitions were one after another, but in some of the
new cases they are not.
Reviewed-by: Karol Herbst <kherbst@redhat.com>
This takes the stupid simplest and most reliable approach to reducing
redundancy that I could come up with: Just use the struct declaration
as the cach key. This cuts the size of the generated C file to about
half and takes about 50 KiB off the .data section.
size before (release build):
text data bss dec hex filename
5363833 336880 13584 5714297 573179 _install/lib64/libvulkan_intel.so
size after (release build):
text data bss dec hex filename
5229017 285264 13584 5527865 545939 _install/lib64/libvulkan_intel.so
Reviewed-by: Connor Abbott <cwabbott0@gmail.com>
Both Vulkan and OpenGL might be using glsl_types simultaneously or we
can also have multiple concurrent Vulkan instances using glsl_types.
Patch adds a one time init to track number of users and will release
types only when last user calls _glsl_type_singleton_decref().
This change fixes glsl_type memory leaks we have with anv driver.
v2: reuse hash_mutex, cleanup, apply fix also to radv driver and
rename helper functions (Jason)
v3: move init, destroy to happen on GL context init and destroy
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Until now, we were only doing this when linking a SSO
program. However, nothing avoids linking a non SSO program which
doesn't have both a VS and FS. In those cases, we also need to report
the usual linking errors, if happening.
v2: Use a better name for the renamed function (Timothy).
Signed-off-by: Andres Gomez <agomez@igalia.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Acked-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Acked-by: Marek Olšák <marek.olsak@amd.com>
Acked-by: Jason Ekstrand <jason@jlekstrand.net>
Acked-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Acked-by: Matt Turner <mattst88@gmail.com>
v3: rebase
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com> (v2)
Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Seems it was missing the "/ ma + 0.5" and the order was swapped.
Fixes: a1a2a8dfda ('nir: add AMD_gcn_shader extended instructions')
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
When gathering info for unmovable types we need to handle arrays.
While we dont support packing/moving arrays we do support packing
scalar components with these arrays.
Fixes piglit:
tests/spec/arb_enhanced_layouts/execution/component-layout/vs-fs-array-interleave-range.shader_test
Fixes: 5eb17506e1 ("nir: do not pack varying with different types")
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Now that nir_const_value is a scalar, we don't need the switch on bit
size in order to pluck off components properly.
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Now that nir_const_value is a scalar, we don't need the switch on bit
size in order copy components around properly.
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Now that nir_const_value is a scalar, we don't need the switch on bit
size in order to swizzle them properly.
Reviewed-by: Karol Herbst <kherbst@redhat.com>
v2: remove & operator in a couple of memsets
add some memsets
v3: fixup lima
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net> (v2)
we already assert above that there are no more than 3 sources, so it
doesn't make sense to use an array of 4 sources
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
While we're here, fix a typo which caused it to actually return a vec4
with the third and fourth components zero.
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
On Mali hardware (supported by Panfrost and Lima), the fixed-function
transformation from world-space to screen-space coordinates is done in
the vertex shader prior to writing out the gl_Position varying, rather
than in dedicated hardware. This commit adds a shared NIR pass for
implementing coordinate transformation and lowering gl_Position writes
into screen-space gl_Position writes.
v2: Run directly on derefs before io/vars are lowered to cleanup the
code substantially. Thank you to Qiang for this suggestion!
v3: Bikeshed continues.
v4: Add to Makefile.sources (per Jason's comment). Bikeshed comment.
Ian and Qiang's reviews are from v3, but no real functional changes from
v4. Rob's review is from v4.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Suggested-by: Qiang Yu <yuq825@gmail.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Qiang Yu <yuq825@gmail.com>
Reviewed-by: Rob Clark <robdclark@gmail.com>
This commit adds new nir_load/store_scratch opcodes which read and write
a virtual scratch space. It's up to the back-end to figure out what to
do with it and where to put the actual scratch data.
v2: Drop const_index comments (by anholt)
Reviewed-by: Eric Anholt <eric@anholt.net>
The constant_index slots are named right there in the intrinsic
definition, and the comment is just a chance to get out of sync. Noticed
while reviewing the lower_to_scratch changes that copy-and-pasted wrong
comments, and load_ubo and load_per_vertex_output had incorrect comments
currently.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
gl_nir_lower_samplers_as_deref splits structure uniform variables,
creating new variables for individual fields. As part of that, it
calculates a new location. It then never set this on the new variables.
Thanks to Michael Fiano for finding this bug. Fixes crashes on i965
with Piglit's new tests/spec/glsl-1.10/execution/samplers/uniform-struct
test, which was reduced from the failing case in Michael's app.
Fixes: f003859f97 nir: Make gl_nir_lower_samplers use gl_nir_lower_samplers_as_deref
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
v2: handle atomics as well
make use of nir_rewrite_image_intrinsic
v3: remove call to nir_remove_dead_derefs
v4: (Timothy Arceri) dont actually call lowering yet
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net> (v3)
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
fixes retrieving the sampler type for bindless images stored inside structs.
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
v2: add support for AMD
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net> (v1)
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Fixes a couple of Coverity warnings CID 1444626.
Fixes: e30804c602 ("nir/radv: remove restrictions on opt_if_loop_last_continue()")
Reviewed-by: Tapani Pälli <tapani.palli@intel.com>
In commit 3b3653c4cf we decided not to use bare types; hence do not use
bare type when comparing with interface type to find out if the xfb
variable is an array block.
This fixes dEQP-VK.transform_feedback.* tests.
Fixes: 3b3653c4cf ("nir/spirv: don't use bare types, remove assert in
split vars for testing")
CC: Dave Airlie <airlied@redhat.com>
CC: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
also set some constants for SSBOs.
With that it can compile the shader from:
dEQP-GLES31.functional.ssbo.layout.random.all_per_block_buffers.18
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Otherwise nir_lower_non_uniform_access crashes when it tries
to get the access of a load_ubo.
Fixes: 8ed583fe52 "spirv: Handle the NonUniformEXT decoration"
Fixes: e50ab2c0f2 "nir: Add access flags to deref and SSBO atomics"
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
CTS: GL45-CTS.compute_shader.resources-max
Fixes: 4e1e8f684b "glsl: remember which SSBOs are not read-only and pass it to gallium"
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
From the OpenGL 4.60.5 spec, section 4.4.1 Input Layout Qualifiers,
Page 67, (Location aliasing):
" Further, when location aliasing, the aliases sharing the location
must have the same underlying numerical type and bit
width (floating-point or integer, 32-bit versus 64-bit, etc.) and
the same auxiliary storage and interpolation qualification."
Additionally, we have improved the linker error descriptions.
Specifically, when taking structs into account we were producing a
linker error because we assumed that all components in each location
were used and that would cause component aliasing. This is not
accurate of the actual problem. Now, the failure specifies that the
underlying numerical type incompatibility is the cause for the
failure.
Fixes the following piglit test:
tests/spec/arb_enhanced_layouts/linker/component-layout/vs-to-fs-width-mismatch-double-float.shader_test
v2:
- Do not assert if we see invalid numerical types. These come
straight from shader code, so we should produce linker errors if
shaders attempt to do location aliasing on variables that are not
numerical such as records.
- While we are at it, improve error reporting for the case of
numerical type mismatch to include the shader stage.
v3:
- Allow location aliasing of images and samplers. If we get these
it means bindless support is active and they should be handled
as 64-bit integers (Ilia)
- Make sure we produce link errors for any non-numerical type
for which we attempt location aliasing, not just structs.
v4:
- Rebased with minor fixes (Andres).
- Added fixing tag to the commit log (Andres).
v5:
- Remove the helper function and check individually for the
underlying numerical type and bit width (Timothy).
- Implicitly, assume that any non-treated type which is checked for
its underlying numerical type is either integer or
float and has a defined bit width (Timothy).
- Implicitly, assume that structs are the only non-treated
non-numerical type (Timothy).
- Improve the linker error descriptions and commit log (Andres).
Fixes: 13652e7516 ("glsl/linker: Fix type checks for location aliasing")
Cc: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: Timothy Arceri <tarceri@itsqueeze.com>
Cc: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Andres Gomez <agomez@igalia.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
We have a pass to lower global registers to locals and many drivers
dutifully call it. However, no one ever creates a global register ever
so it's all dead code. It's time we bury it.
Acked-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
All we ever do is initialize it to zero, clone it, print it, and
validate it. No one ever sets or uses it.
Acked-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
As defined in SPV_NV_compute_shader_derivatives. These control how the
invocations are arranged in a CS when doing derivative and related
operations (which are also enabled by the extension).
Since we expect valid SPIR-V, we don't need to do more work at SPIR-V
level to enable the derivative and related operations to be called.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
When using NV_compute_shader_derivatives to set a derivative group,
a compute shader supports texture with implicit LOD calculation, so
don't set an explicit LOD.
Note if the extension is used but the derivative group is not
specified, it will default to LOD=0 as before.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
In compute shaders if no derivative group is defined, the derivatives
will always be zero. Specified in NV_compute_shader_derivatives.
To make the check more convenient, add a "info" local variable to the
generated code so we can refer to it in the Python rules. (Jason)
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
NV_compute_shader_derivatives allow selecting between two possible
arrangements (quads and linear) when calculating derivatives and
certain subgroup operations in case of Vulkan. So parse and propagate
those up to shader_info.h.
v2: Do not fail when ARB_compute_variable_group_size is being used,
since we are still clarifying what is the right thing to do here.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
When I implemented opt_if_loop_last_continue() I had restricted
this pass from moving other if-statements inside the branch opposite
the continue. At the time it was causing a bunch of spilling in
shader-db for i965.
However Samuel Pitoiset noticed that making this pass more aggressive
significantly improved the performance of Doom on RADV. Below are
the statistics he gathered.
28717 shaders in 14931 tests
Totals:
SGPRS: 1267317 -> 1267549 (0.02 %)
VGPRS: 896876 -> 895920 (-0.11 %)
Spilled SGPRs: 24701 -> 26367 (6.74 %)
Code Size: 48379452 -> 48507880 (0.27 %) bytes
Max Waves: 241159 -> 241190 (0.01 %)
Totals from affected shaders:
SGPRS: 23584 -> 23816 (0.98 %)
VGPRS: 25908 -> 24952 (-3.69 %)
Spilled SGPRs: 503 -> 2169 (331.21 %)
Code Size: 2471392 -> 2599820 (5.20 %) bytes
Max Waves: 586 -> 617 (5.29 %)
The codesize increases is related to Wolfenstein II it seems largely
due to an increase in phis rather than the existing jumps.
This gives +10% FPS with Doom on my Vega56.
Rhys Perry also benchmarked Doom on his VEGA64:
Before: 72.53 FPS
After: 80.77 FPS
v2: disable pass on non-AMD drivers
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com> (v1)
Acked-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Consider the following search expression and NIR sequence:
('iadd', ('imul', a, b), b)
ssa_2 = imul ssa_0, ssa_1
ssa_3 = iadd ssa_2, ssa_0
The current algorithm is greedy and, the moment the imul finds a match,
it commits those variable names and returns success. In the above
example, it maps a -> ssa_0 and b -> ssa_1. When we then try to match
the iadd, it sees that ssa_0 is not b and fails to match. The iadd
match will attempt to flip itself and try again (which won't work) but
it cannot ask the imul to try a flipped match.
This commit instead counts the number of commutative ops in each
expression and assigns an index to each. It then does a loop and loops
over the full combinatorial matrix of commutative operations. In order
to keep things sane, we limit it to at most 4 commutative operations (16
combinations). There is only one optimization in opt_algebraic that
goes over this limit and it's the bitfieldReverse detection for some UE4
demo.
Shader-db results on Kaby Lake:
total instructions in shared programs: 15310125 -> 15302469 (-0.05%)
instructions in affected programs: 1797123 -> 1789467 (-0.43%)
helped: 6751
HURT: 2264
total cycles in shared programs: 357346617 -> 357202526 (-0.04%)
cycles in affected programs: 15931005 -> 15786914 (-0.90%)
helped: 6024
HURT: 3436
total loops in shared programs: 4360 -> 4360 (0.00%)
loops in affected programs: 0 -> 0
helped: 0
HURT: 0
total spills in shared programs: 23675 -> 23666 (-0.04%)
spills in affected programs: 235 -> 226 (-3.83%)
helped: 5
HURT: 1
total fills in shared programs: 32040 -> 32032 (-0.02%)
fills in affected programs: 190 -> 182 (-4.21%)
helped: 6
HURT: 2
LOST: 18
GAINED: 5
Reviewed-by: Thomas Helland <thomashelland90@gmail.com>
The new OR pattern has been seen in the wild and can end up being
generated by GLSLang. Not sure about the other two new patterns but we
may as well throw them in for completeness. While we're here, we can
drop the '@bool' specifier from the one pattern because specifying True
already implies 1-bit which basically implies boolean.
Shader-db results on Kaby Lake:
total instructions in shared programs: 15321227 -> 15321129 (<.01%)
instructions in affected programs: 3594 -> 3496 (-2.73%)
helped: 6
HURT: 0
total cycles in shared programs: 357481321 -> 357479725 (<.01%)
cycles in affected programs: 44109 -> 42513 (-3.62%)
helped: 6
HURT: 0
VkPipeline-DB results on Kaby Lake:
total instructions in shared programs: 3770504 -> 3769734 (-0.02%)
instructions in affected programs: 19058 -> 18288 (-4.04%)
helped: 163
HURT: 0
total cycles in shared programs: 1417583701 -> 1417569727 (<.01%)
cycles in affected programs: 750958 -> 736984 (-1.86%)
helped: 158
HURT: 1
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Now that we have one-bit booleans, we don't need to rely on looking at
parent instructions in order to figure out if a value is a Boolean most
of the time. We can drop these specifiers and now the optimizations
will apply more generally.
Shader-DB results on Kaby Lake:
total instructions in shared programs: 15321168 -> 15321227 (<.01%)
instructions in affected programs: 8836 -> 8895 (0.67%)
helped: 1
HURT: 31
total cycles in shared programs: 357481781 -> 357481321 (<.01%)
cycles in affected programs: 146524 -> 146064 (-0.31%)
helped: 22
HURT: 10
total spills in shared programs: 23675 -> 23673 (<.01%)
spills in affected programs: 11 -> 9 (-18.18%)
helped: 1
HURT: 0
total fills in shared programs: 32040 -> 32036 (-0.01%)
fills in affected programs: 27 -> 23 (-14.81%)
helped: 1
HURT: 0
No change in VkPipeline-DB
Looking at the instructions hurt, a bunch of them seem to be a case
where doing exactly the right thing in NIR ends up doing the wrong-ish
thing in the back-end because flags are dumb. In particular, there's a
case where we have a MUL followed by a CMP followed by a SEL and when we
turn that SEL into an OR, it uses the GRF result of the CMP rather than
the flag result so the CMP can't be merged with the MUL. Those shaders
appear to schedule better according to the cycle estimates so I guess
it's a win? Also it helps spilling in one Car Chase compute shader.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
If a def is used as an condition before its definition, we should also
consider this a case to repair. When repairing, make sure we rewrite
any if conditions too.
Found in while inspecting a SPIR-V conversion from a 'continue block'
that contains a conditional branch. We pull the continue block up to
the beggining of the loop, and the condition in the branch ends up
defined afterwards.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Fixes: 364212f1ed "nir: Add a pass to repair SSA form"
The current algorithm only supports packing 32-bit types.
If a shader uses both 16-bit and 32-bit varyings, we shouldn't
compact them together.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Section 7.4.1 (Shader Interface Matching) of the OpenGL 4.30 spec says:
"Variables or block members declared as structures are considered
to match in type if and only if structure members match in name,
type, qualification, and declaration order."
Fixes:
* layout-location-struct.shader_test
v2: rebased against master and small fixes
Signed-off-by: Vadym Shovkoplias <vadym.shovkoplias@globallogic.com>
Reviewed-by: Anuj Phogat <anuj.phogat@gmail.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108250
While a partial set of viewport system values exist, these are scalar
values, which is a poor fit for viewport transformations on vector ISAs
like Midgard (where the vec3 values for scale and offset each need to be
coherent in a vec4 uniform slot to take advantage of vectorized
transform math). This patch adds vec3 scale/offset fields corresponding
to the 3D Gallium viewport / glViewport+depth
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Eric Anholt <eric@anholt.net>
If we increase the vector size in the future it would be good
to not have to fix these up, this should change nothing at present.
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
This prevents getting mixed-up results if a multi-threaded app has two
validation errors in different threads.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
This pass attempts to dectect code sequences like
if (x < y) {
z = y - x;
...
}
and replace them with sequences like
t = x - y;
if (t < 0) {
z = -t;
...
}
On architectures where the subtract can generate the flags used by the
if-statement, this saves an instruction. It's also possible that moving
an instruction out of the if-statement will allow
nir_opt_peephole_select to convert the whole thing to a bcsel.
Currently only floating point compares and adds are supported. Adding
support for integer will be a challenge due to integer overflow. There
are a couple possible solutions, but they may not apply to all
architectures.
v2: Fix a typo in the commit message and a couple typos in comments.
Fix possible NULL pointer deref from result of push_block(). Add
missing (-A + B) case. Suggested by Caio.
v3: Fix is_not_const_zero to work correctly with types other than
nir_type_float32. Suggested by Ken.
v4: Add some comments explaining how this works. Suggested by Ken.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
v2: Move bug fix in get_neg_instr from the next patch to this patch
(where it was intended to be in the first place). Noticed by Caio.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
No shader-db changes on any Intel platform.
v2: Use a loop to generate patterns. Suggested by Jason.
v3: Fix a copy-and-paste bug in the extract_[ui] of ishl loop that would
replace an extract_i8 with and extract_u8. This broke ~180 tests. This
bug was introduced in v2.
Reviewed-by: Matt Turner <mattst88@gmail.com> [v1]
Reviewed-by: Dylan Baker <dylan@pnwbakers.com> [v2]
Acked-by: Jason Ekstrand <jason@jlekstrand.net> [v2]
No shader-db changes on any Intel platform.
v2: Use a loop to generate patterns. Suggested by Jason.
v3: Fix a copy-and-paste bug in the extract_[ui] of ishl loop that would
replace an extract_i8 with and extract_u8. This broke ~180 tests. This
bug was introduced in v2.
Reviewed-by: Matt Turner <mattst88@gmail.com> [v1]
Reviewed-by: Dylan Baker <dylan@pnwbakers.com> [v2]
Acked-by: Jason Ekstrand <jason@jlekstrand.net> [v2]
No shader-db changes on any Intel platform.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Dylan Baker <dylan@pnwbakers.com>
Acked-by: Jason Ekstrand <jason@jlekstrand.net>
llvm/spir-v spits out some struct a { struct b {} }, but it
doesn't deref, it casts (struct a) to (struct b), reconstruct
struct derefs instead of casts for these.
v2: use ssa_def_rewrite uses, rework the type restrictions (Jason)
v3: squish more stuff into one function, drop unused temp (Jason)
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
It was only propagated when UBO/SSBO access are lowered to offsets.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: <Jason Ekstrand jason@jlekstrand.net>
This will allow us to make use of the selection control support in
spirv and the GL support provided by EXT_control_flow_attributes.
Note this only supports if-statements as we dont support switches
in NIR.
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108841
This will allow us to make use of the loop control support in
spirv and the GL support provided by EXT_control_flow_attributes.
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108841
We will need them for a new ACCESS_NON_UNIFORM flag that's about to be
added in the next commit.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
On Intel, we have both bindless and bindful and we'd like to use them at
the same time if we can so we need to be able to distinguish at the NIR
level between the two. This also fixes nir_lower_tex to properly handle
bindless in its tex_texture_size and get_texture_lod helpers.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
v2 (Topi):
- Make bit-size handling order be 16-bit, 32-bit, 64-bit
- Clamp lower exponent range at -28 instead of -30.
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
With vkpipelinedb Samuel discovered a regression since we stopped
stripping types at the spir-v level.
This adds a check to the var splitting for the case where it
asserts the type hasn't changed, when it has just created a bare
type, and it's different than the original type which has an explicit
stride.
This also removes a pointless assert that also triggers.
Fixes: 3b3653c4cf (nir/spirv: don't use bare types, remove assert in split vars for testing)
Acked-by: Jason Ekstrand <jason@jlekstrand.net>
Also handle GLSL_TYPE_INTERFACE the same way we do GLSL_TYPE_STRUCT in
various places. Motivated by ARB_gl_spirv work, that will take
advantage of the interface types when handling NIR coming from SPIR-V.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Also updates gl_spirv to pick the right one. At the moment nothing
uses it, but upcoming functionality part of ARB_gl_spirv will use it,
and we also later can be more assertful when handling certain features
for each of the execution environments.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Acked-by: Karol Herbst <kherbst@redhat.com>
This lowering isn't needed for RADV because AMDGCN has two
instructions. It will be disabled for RADV in an upcoming series.
While we are at it, factorize a little bit.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Only the exponent needs to be 32-bit signed integer.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Fix this build error with GCC 4.4.7.
CC nir/nir_opt_copy_prop_vars.lo
nir/nir_opt_copy_prop_vars.c: In function ‘load_element_from_ssa_entry_value’:
nir/nir_opt_copy_prop_vars.c:454: error: unknown field ‘ssa’ specified in initializer
nir/nir_opt_copy_prop_vars.c:455: error: unknown field ‘def’ specified in initializer
nir/nir_opt_copy_prop_vars.c:456: error: unknown field ‘component’ specified in initializer
nir/nir_opt_copy_prop_vars.c:456: error: extra brace group at end of initializer
nir/nir_opt_copy_prop_vars.c:456: error: (near initialization for ‘(anonymous).<anonymous>’)
nir/nir_opt_copy_prop_vars.c:456: warning: excess elements in union initializer
nir/nir_opt_copy_prop_vars.c:456: warning: (near initialization for ‘(anonymous).<anonymous>’)
Fixes: 96c32d7776 ("nir/copy_prop_vars: handle load/store of vector elements")
Signed-off-by: Vinson Lee <vlee@freedesktop.org>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=109810
Reviewed-by: Andres Gomez <agomez@igalia.com>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
'invariant' qualifier is propagated on variables which are used
to calculate other invariant variables, however when we are matching
variable's declarations we should take into account only explicitly
declared invariance because invariance propagation is an implementation
specific detail.
Thus new flag is added to ir_variable_data which indicates 'invariant'
qualifier being explicitly set in the shader.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=100316
Fixes: 89b60492 ('glsl: Add a pass to propagate the "invariant" and
"precise" qualifiers')
Signed-off-by: Danylo Piliaiev <danylo.piliaiev@globallogic.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Rather than skipping code that looked like this:
loop {
...
if (cond) {
do_work_1();
continue;
} else {
break;
}
do_work_2();
}
Previously we would turn this into:
loop {
...
if (cond) {
do_work_1();
continue;
} else {
do_work_2();
break;
}
}
This was clearly wrong. This change checks for this case and makes
sure we now leave it for nir_opt_dead_cf() to clean up.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
In some cases, we can end up with varying structs that aren't split to
their member variables. nir_compact_varyings attempted to record these
as unmovable, so it would leave them be. Unfortunately, it didn't do
it right for non-vector/scalar types. It set the mask to:
((1 << (elements * dmul)) - 1) << var->data.location_frac
where elements is the number of vector elements. For structures and
other non-vector/scalars, elements is 0...so the whole mask became 0.
This caused nir_compact_varyings to assign other varyings on top of
the structure varying's location (as it appeared to take up no space).
To combat this, we just set elements to 4 for non-vector/scalar types,
so that the entire slot gets marked as unmovable.
Fixes KHR-GL45.tessellation_shader.tessellation_control_to_tessellation_evaluation.gl_in on iris.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Users of this function expect alu to be a supported comparision
if the induction variable is not NULL. Since we attempt to
override the return values if the first limit is not a const, we
must make sure we are dealing with a valid comparision before
overriding the alu instruction.
Fixes an unreachable in inverse_comparison() with the game
Assasins Creed Odyssey.
Fixes: 3235a942c1 ("nir: find induction/limit vars in iand instructions")
Acked-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=110216
Values inside the offsets parameter of textureGatherOffsets are required to be
constants in the range of [GL_MIN_PROGRAM_TEXTURE_GATHER_OFFSET,
GL_MAX_PROGRAM_TEXTURE_GATHER_OFFSET].
As this range is never outside [-32, 31] for all existing drivers inside mesa,
we can simply store the offsets as a int8_t[4][2] array inside nir_tex_instr.
Right now only Nvidia hardware supports this in hardware, so we can turn this
on inside Nouveau for the NIR path as it is already enabled with the TGSI one.
v2: use memcpy instead of for loops
add missing bits to nir_instr_set
don't show offsets if they are all 0
v3: default offsets aren't all 0
v4: rename offsets -> tg4_offsets
rename nir_tex_instr_has_explicit_offsets -> nir_tex_instr_has_explicit_tg4_offsets
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Not sure how ptr_stride should be taken into account if at all here
v2: reorder check to avoid src walking (Jason)
v3: remove is_cast_cast checks, keep going afterwards (Jason)
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
For OpenCL we never want to strip the info from the types, and it makes
type comparisons easier in later stages. We might later need a nir pass to
strip this for GLSL, but so far the only regression is the assert and Jason
said removing that is fine.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Fixes dEQP-VK.binding_model.buffer_device_address.* and
dEQP-VK.ssbo.phys.layout* Vulkan CTS tests.
v2: set val->type->stride in the section below (Jason)
v3: restore val->type->type to original place (Jason)
Fixes: d0ba326f23 ("nir/spirv: support physical pointers")
CC: Karol Herbst <kherbst@redhat.com>
CC: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
This reverts commit 1aa5738e66.
This patch incorrectly asumed that for SSOs no inner interface
matching check was needed.
From the ARB_separate_shader_objects spec v.25:
" With separable program objects, interfaces between shader stages
may involve the outputs from one program object and the inputs
from a second program object. For such interfaces, it is not
possible to detect mismatches at link time, because the programs
are linked separately. When each such program is linked, all
inputs or outputs interfacing with another program stage are
treated as active. The linker will generate an executable that
assumes the presence of a compatible program on the other side of
the interface. If a mismatch between programs occurs, no GL error
will be generated, but some or all of the inputs on the interface
will be undefined."
This completes the fix from commit:
3be05dd267 ("glsl/linker: don't fail non static used inputs without matching outputs")
Fixes: 1aa5738e66 ("glsl: relax input->output validation for SSO programs")
Cc: Tapani Pälli <tapani.palli@intel.com>
Cc: Timothy Arceri <tarceri@itsqueeze.com>
Cc: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: Samuel Iglesias Gonsálvez <siglesias@igalia.com>
Cc: Ian Romanick <ian.d.romanick@intel.com>
Signed-off-by: Andres Gomez <agomez@igalia.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Current implementation uses a complicated calculation which relies in
an implicit conversion to check the integral part of 2 division
results.
However, the calculation actually checks that the xfb_offset is
smaller or a multiplier of the xfb_stride. For example, while this is
expected to fail, it actually succeeds:
"
...
layout(xfb_buffer = 2, xfb_stride = 12) out block3 {
layout(xfb_offset = 0) vec3 c;
layout(xfb_offset = 12) vec3 d; // ERROR, requires stride of 24
};
...
"
Fixes: 2fab85aaea ("glsl: add xfb_stride link time validation")
Cc: Timothy Arceri <tarceri@itsqueeze.com>
Signed-off-by: Andres Gomez <agomez@igalia.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
If there is no Static Use of an input variable, the linker shouldn't
fail whenever there is no defined matching output variable in the
previous stage.
From page 47 (page 51 of the PDF) of the GLSL 4.60 v.5 spec:
" Only the input variables that are statically read need to be
written by the previous stage; it is allowed to have superfluous
declarations of input variables."
Now, we complete this exception whenever the input variable has an
explicit location. Previously, 18004c338f ("glsl: fail when a
shader's input var has not an equivalent out var in previous") took
care of the cases in which the input variable didn't have an explicit
location.
v2: do the location based interface matching check regardless on
whether it is a separable program or not (Ilia).
Fixes: 1aa5738e66 ("glsl: relax input->output validation for SSO programs")
Cc: Timothy Arceri <tarceri@itsqueeze.com>
Cc: Iago Toral Quiroga <itoral@igalia.com>
Cc: Samuel Iglesias Gonsálvez <siglesias@igalia.com>
Cc: Tapani Pälli <tapani.palli@intel.com>
Cc: Ian Romanick <ian.d.romanick@intel.com>
Cc: Ilia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: Andres Gomez <agomez@igalia.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Outputs are always validated when having explicit locations and we
were trusting its outcome to catch similar problems with the inputs
since, in case of having undefined outputs for existing inputs, we
would be already reporting a linker error.
However, consider this case:
" Shader stage n:
---------------
...
layout(location = 0) out float a;
...
Shader stage n+1:
-----------------
...
layout(location = 0) in float b;
layout(location = 0) in float c;
...
"
Currently, this won't report a linker error even though location
aliasing is happening for the inputs.
Therefore, we also need to validate the inputs independently from the
outcome of the outputs validation.
Cc: Timothy Arceri <tarceri@itsqueeze.com>
Cc: Iago Toral Quiroga <itoral@igalia.com>
Cc: Ilia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: Andres Gomez <agomez@igalia.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
From page 62 (page 68 of the PDF) of the GLSL 4.50 v.7 spec:
" A dvec3 or dvec4 can only be declared without specifying a
component."
Therefore, using the "component" qualifier with a dvec3 or dvec4
should result in a compiling error.
v2: enhance the error message (Timothy).
Fixes: 94438578d2 ("glsl: validate and store component layout qualifier in GLSL IR")
Cc: Timothy Arceri <tarceri@itsqueeze.com>
Cc: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Andres Gomez <agomez@igalia.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
This reverts commit db57db5317. When
building IR, nothing is really immutable and, since C has no concept of
constness propagating beyond the first pointer, we have to be vary
careful with how we use it. To just throw const into a function like
this is a lie.
Instead, we should just drop the unneeded const in spirv_to_nir which
this commit does along with the revert.
the idea here is to generate an entry point stub function wrapping around the
actual kernel function and turn all parameters into shader inputs with byte
addressing instead of vec4.
This gives us several advantages:
1. calling kernel functions doesn't differ from calling any other function
2. CL inputs match uniforms in most ways and we can just take advantage of most
of nir_lower_io
v2: move code into a seperate function
v3: verify the entry point got a name
fix minor typo
v4: make vtn_emit_kernel_entry_point_wrapper take the old entry point as an arg
Signed-off-by: Karol Herbst <kherbst@redhat.com>
local memory is too small to require 64 bit pointers, so cast the array index
to a 32 bit value to save up on 64 bit operations.
Signed-off-by: Karol Herbst <kherbst@redhat.com>
We need this for OpenCL kernels because we have to apply C rules for alignment
and padding inside structs and for this we also have to know if a struct is
packed or not.
v2: fix for kernel params
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
This pass was originally written for lowering TCS output reads and
writes but it is also applicable just about anything including UBOs,
SSBOs, and shared variables.
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
This one's a tiny bit better than what we had in spirv_to_nir because it
emits a binary tree rather than a linear walk. It also doesn't leave
around unneeded bcsel instructions for a constant index and returns an
undef for constant OOB access.
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
When varyings was added we moved to use to dynamycally allocated
pointers, instead of allocating just one block for everything. That
breaks some assumptions of some vulkan drivers (like anv), that make
serialization and copying easier. And at the same time, varyings are
not needed for vulkan.
So this commit moves them out. Although it seems a little an overkill,
fixing the anv side would require a similar, or more, changes, so in
the end it is about to decide where do we want to put our effort.
v2: (from Jason review)
* Don't use a temp variable on the _create methods, just return
result of rzalloc_size
* Wrap some lines too long.
Fixes: cf0b2ad486 ("nir/xfb: adding varyings on nir_xfb_info and gather_info")
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
We didn't have any of these before because all NIR consumers always
called lower_ubo_references. Soon, we want to pass the derefs straight
through to NIR so we need to handle these intrinsics directly.
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
We want to be able to use variables and derefs for UBO/SSBO access in
NIR. In order to do this, the rest of NIR needs to know the type layout
information.
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
All of these are backed by some sort of memory so if you have multiple
threads writing to different components of the same vector at the same
time, the load-vec-store pattern that GLSL IR emits won't work. This
shouldn't affect any drivers today as they all call GLSL IR lowering
which lowers access to these variables to index+offset intrinsics before
we get to this point. However, NIR will start handling the derefs
itself and won't want the lowering.
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
It's just a 32-bit index and offset. We're going to want to use it in
GL as well so stop talking about Vulkan.
Reviewed-by: Kristian H. Kristensen <hoegsberg@chromium.org>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
If we get to two deref_var paths with different variables, we usually
know they don't alias. However, if both of the paths are marked
coherent, we don't have to worry about it.
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
We also need to modify the current size/align helpers to not blow up
when they encounter an explicitly laid out type. Previously we
considered using the size/align helpers mutually exclusive with standard
layouts but now we just assert that they match.
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Reviewed-by: Kristian H. Kristensen <hoegsberg@chromium.org>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
With UBOs and SSBOs we have boolean types but they're actually 32-bit
values. Make the validator a little less strict so that we can do a
32-bit load/store on boolean types. We're about to add a lowering pass
called gl_nir_lower_buffers which will lower boolean load/store
operations to 32-bit and insert i2b and b2i instructions to convert
to/from 1-bit booleans. We want that to be legal.
Reviewed-by: Kristian H. Kristensen <hoegsberg@chromium.org>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
If we want to be able to use copy_deref instructions on explicitly laid
out types, we have to be a little more flexible about what types we
allow. Instead, of requiring the types to exactly match, only require
the bare types to match.
Reviewed-by: Kristian H. Kristensen <hoegsberg@chromium.org>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Shader-db results on Kaby Lake:
total instructions in shared programs: 15225213 -> 15222365 (-0.02%)
instructions in affected programs: 43524 -> 40676 (-6.54%)
helped: 203
HURT: 0
Lots of shaders in Shadow Warrior had this pattern along with Deus Ex,
Civ, Shadow of Mordor, and several others.
Reviewed-by: Kristian H. Kristensen <hoegsberg@chromium.org>
These are ir3 specific versions of SSBO intrinsics that add an
extra source to hold the element offset (dword), which is what the
backend instructions need.
The original byte-offset source provided by NIR is not replaced
because on a4xx and a5xx the backend still needs it.
Reviewed-by: Rob Clark <robdclark@gmail.com>
v2: (all from Jason)
Reuse existing function for the end of the block combinations.
Check the SSA values are coming from the right place in tests.
Document the case when the store to array_deref is reused.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Tessellation control shader outputs act as if they have memory backing
them and you can have multiple writes to different components of the
same vector in-flight at the same time. When this happens, the load vec
store pattern that gets used by ir_triop_vector_insert doesn't yield the
correct results. Instead, just emit a sequence of conditional
assignments.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Cc: mesa-stable@lists.freedesktop.org
The previous code was completely broken when it came to constructing the
undef values. I'm not sure how it ever worked. For the case of a copy
that reads an undefined value, we can just delete the copy because the
destination is a valid undefined value. This saves us the effort of
trying to construct a value for an arbitrary copy_deref intrinsic.
Fixes: e8a8937a04 "nir: add partial loop unrolling support"
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Oftentimes various nir shaders after lowering will be the same, or
almost the same. For example, this can happen when the same shader is
linked with different shaders to form different pipelines and
cross-stage optimizations don't kick in to change it. We want to avoid
running the backend twice on these shaders. We were already doing this
with radeonsi, but we were storing a few extra pieces of information
that made this much less effective compared to TGSI. The worse offender
by far was the program name, which caused most of the cache misses. This
pass strips out these pieces of information, controlled by the NIR_STRIP
debug env variable.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Rather than getting this from the alu instruction this allows us
some flexibility. In the following pass we instead pass the
inverse op.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
This helps make find_trip_count() a little easier to follow but
will also be used by a following patch.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
This will be used to help find the trip count of loops that look
like the following:
while (a < x && i < 8) {
...
i++;
}
Where the NIR will end up looking something like this:
vec1 32 ssa_1 = load_const (0x00000004 /* 0.000000 */)
loop {
...
vec1 1 ssa_12 = ilt ssa_225, ssa_11
vec1 1 ssa_17 = ilt ssa_226, ssa_1
vec1 1 ssa_18 = iand ssa_12, ssa_17
vec1 1 ssa_19 = inot ssa_18
if ssa_19 {
...
break
} else {
...
}
}
So in order to find the trip count we need to find the inverse of
ilt.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Here we create a helper is_supported_terminator_condition()
and use that rather than embedding all the trip count code
inside a switch.
The new helper will also be used in a following patch.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
This adds support to loop analysis for loops where the induction
variable is compared to the result of min(variable, constant).
For example:
for (int i = 0; i < imin(x, 4); i++)
...
We add a new bool to the loop terminator struct in order to
differentiate terminators with this exit condition.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
This adds partial loop unrolling support and makes use of a
guessed trip count based on array access.
The code is written so that we could use partial unrolling
more generally, but for now it's only use when we have guessed
the trip count.
We use partial unrolling for this guessed trip count because its
possible any out of bounds array access doesn't otherwise affect
the shader e.g the stores/loads to/from the array are unused. So
we insert a copy of the loop in the innermost continue branch of
the unrolled loop. Later on its possible for nir_opt_dead_cf()
to then remove the loop in some cases.
A Renderdoc capture from the Rise of the Tomb Raider benchmark,
reports the following change in an affected compute shader:
GPU duration: 350 -> 325 microseconds
shader-db results radeonsi VEGA (NIR backend):
SGPRS: 1008 -> 816 (-19.05 %)
VGPRS: 684 -> 432 (-36.84 %)
Spilled SGPRs: 539 -> 0 (-100.00 %)
Spilled VGPRs: 0 -> 0 (0.00 %)
Private memory VGPRs: 0 -> 0 (0.00 %)
Scratch size: 0 -> 0 (0.00 %) dwords per thread
Code Size: 39708 -> 45812 (15.37 %) bytes
LDS: 0 -> 0 (0.00 %) blocks
Max Waves: 105 -> 144 (37.14 %)
Wait states: 0 -> 0 (0.00 %)
shader-db results i965 SKL:
total instructions in shared programs: 13098265 -> 13103359 (0.04%)
instructions in affected programs: 5126 -> 10220 (99.38%)
helped: 0
HURT: 21
total cycles in shared programs: 332039949 -> 331985622 (-0.02%)
cycles in affected programs: 289252 -> 234925 (-18.78%)
helped: 12
HURT: 9
vkpipeline-db results VEGA:
Totals from affected shaders:
SGPRS: 184 -> 184 (0.00 %)
VGPRS: 448 -> 448 (0.00 %)
Spilled SGPRs: 0 -> 0 (0.00 %)
Spilled VGPRs: 0 -> 0 (0.00 %)
Private memory VGPRs: 0 -> 0 (0.00 %)
Scratch size: 0 -> 0 (0.00 %) dwords per thread
Code Size: 26076 -> 24428 (-6.32 %) bytes
LDS: 6 -> 6 (0.00 %) blocks
Max Waves: 5 -> 5 (0.00 %)
Wait states: 0 -> 0 (0.00 %)
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
In order to stop continuously partially unrolling the same loop
we add the bool partially_unrolled to nir_loop, we add it here
rather than in nir_loop_info because nir_loop_info is only set
via loop analysis and is intended to be cleared before each
analysis. Also nir_loop_info is never cloned.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
This detects an induction variable used as an array index to guess
the trip count of the loop. This enables us to do a partial
unroll of the loop, which can eventually result in the loop being
eliminated.
v2: check if the induction var is used to index more than a single
array and if so get the size of the smallest array.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
'dxc' hlsl-to-spirv compiler appears to emit 2 (Unknown) in the depth field,
when the image is not sampled and the value is not needed.
Previously, shaders failed with:
SPIR-V parsing FAILED:
In file ../src/compiler/spirv/spirv_to_nir.c:1412
!is_shadow
632 bytes into the SPIR-V binary
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
The nir_state_slot struct had some padding that was never initialized.
Serializing the individual parts of the struct is more robust and avoids
the overhead of zeroing it at creation, so just do that.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
This broke piles of image load store tests (179 failures on CI,
mesa_master build #15546, previous build right before this landed
was green). I'd rather not leave the tree on fire over the weekend,
so let's revert for now, and we can figure out what happened next week.
No shader-db changes on any Intel platform.
v2: Use a loop to generate patterns. Suggested by Jason.
Reviewed-by: Matt Turner <mattst88@gmail.com> [v1]
Reviewed-by: Dylan Baker <dylan@pnwbakers.com>
Acked-by: Jason Ekstrand <jason@jlekstrand.net>
No shader-db changes on any Intel platform.
v2: Use a loop to generate patterns. Suggested by Jason.
Reviewed-by: Matt Turner <mattst88@gmail.com> [v1]
Reviewed-by: Dylan Baker <dylan@pnwbakers.com>
Acked-by: Jason Ekstrand <jason@jlekstrand.net>
No shader-db changes on any Intel platform.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Dylan Baker <dylan@pnwbakers.com>
Acked-by: Jason Ekstrand <jason@jlekstrand.net>
From the ARB_enhanced_layouts specification:
"For the property TRANSFORM_FEEDBACK_BUFFER_INDEX, a single integer
identifying the index of the active transform feedback buffer
associated with an active variable is written to <params>. For
variables corresponding to the special names "gl_NextBuffer",
"gl_SkipComponents1", "gl_SkipComponents2", "gl_SkipComponents3",
and "gl_SkipComponents4", -1 is written to <params>."
We were storing the xfb_buffer value, instead of the value
corresponding to GL_TRANSFORM_FEEDBACK_BUFFER_INDEX.
Note that the implementation assumes that varyings would be sorted by
offset and buffer.
Signed-off-by: Antia Puentes <apuentes@igalia.com>
Signed-off-by: Alejandro Piñeiro <apinheiro@igalia.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Instead of a custom ARB_gl_spirv xfb gather info pass.
In fact, this is not only about reusing code, but the current custom
code was not handling properly how many varyings are enumerated from
some complex types. So this change is also about fixing some corner
cases.
v2: Use util_bitcount, simplify current stage check (Kenneth)
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
On OpenGL, a array of a simple type adds just one varying. So
gl_transform_feedback_varying_info struct defined at mtypes.h includes
the parameters Type (base_type) and Size (number of elements).
This commit checks this when the recursive add_var_xfb_outputs call
handles arrays, to ensure that just one is addded.
We also need to take into account AoA here
v2: use glsl_type_is_leaf from nir_types (Timothy Arceri)
v3: simplified aoa check, without the need ot using glsl_type_is_leaf,
using glsl_types_is_struct (Timothy Arceri)
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Right now we are only re-sorting outputs. But it is better to sort too
varyings, as linker expect them to be sorted out (as it was done on
GLSL). For varyings, and to make easier to compute buffer_index, we
sort also by buffer. We could do the same for outputs, but we lack a
reason for that, so we left it as it is (just offset).
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
In order to be used for OpenGL (right now for ARB_gl_spirv).
This commit adds two new structures:
* nir_xfb_varying_info: that identifies each individual varying. For
each one, we need to know the type, buffer and xfb_offset
* nir_xfb_buffer_info: as now for each buffer, in addition to the
stride, we need to know how many varyings are assigned to it.
For this patch, the only case where num_outputs != num_varyings is
with the case of doubles, that for dvec3/4 could require more than one
output. There are more cases though (like aoa), that will be handled
on following patches.
v2: updated after new nir general XFB support introduced for "anv: Add
support for VK_EXT_transform_feedback"
v3: compute num_varyings beforehand for allocating, instead of relying
on num_outputs as approximate value (Timothy Arceri)
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Where component_offset here is the offset when accessing components of
a packed variable. Or in other words, location_frac on
nir.h. Different places of mesa use different names for it.
Technically nir_xfb_info consumer can get the same from the
component_mask, it seems somewhat forced to make it to compute it,
instead of providing it.
v2: rename local location_frac for comp_offset, more similar to the
intended use (Timothy Arceri)
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Unlike most of the cases in which we do this by hand, the new helper
properly handles non-32-bit pointers.
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
There's no guarantee when build_deref_follower is called that the two
derefs have the same bit size destination. Insert a cast on the array
index in case we have differing bit sizes. While we're here, insert
some asserts in build_deref_array and build_deref_ptr_as_array. The
validator will catch violations here but they're easier to debug if we
catch them while building.
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Because we already know the immediate right-hand parameter, we can
potentially save the optimizer a bit of work.
Reviewed-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Fixes a leak:
==7576== 320 (48 direct, 272 indirect) bytes in 1 blocks are definitely lost in loss record 26 of 26
==7576== at 0x4C2EE3B: malloc (vg_replace_malloc.c:309)
==7576== by 0x53EF0E4: ralloc_size (ralloc.c:119)
==7576== by 0x53EF0C2: ralloc_context (ralloc.c:113)
==7576== by 0x5471F64: nir_split_per_member_structs (nir_split_per_member_structs.c:176)
==7576== by 0x51288CF: anv_shader_compile_to_nir (anv_pipeline.c:216)
Signed-off-by: Tapani Pälli <tapani.palli@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
glsl_to_nir() is still missing support for converting certain
functions to NIR, so for those we use the GLSL IR optimisations
to remove the functions.
Reviewed-by: Eric Anholt <eric@anholt.net>
Instead of trusting the caller to already have created a softfp64
function shader and added all its functions to our shader, we simply
take the softfp64 shader as an argument and do the function inlining
ouselves. This means that there's no more nasty functions lying around
that the caller needs to worry about cleaning up.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
This pulls the guts of function inlining into a builder helper so that
it can be used elsewhere. The rest of the infrastructure is still
needed for most inlining cases to ensure that everything gets inlined
and only ever once. However, there are use-cases where you just want to
inline one little thing. This new helper also has a neat trick where it
can seamlessly inline a function from one nir_shader into another.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
This doesn't really change anything as the functions will all get
inlined anyway. However it does let us do a bit of the work earlier and
in a common place.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
The lowering we do for 64-bit instructions can cause a single NIR ALU
instruction to blow up into hundreds or thousands of instructions
potentially with control flow. If loop unrolling isn't aware of this,
it can unroll a loop 20 times which contains a nir_op_fsqrt which we
then lower to a full software implementation based on integer math.
Those 20 invocations suddenly get a lot more expensive than NIR loop
unrolling currently expects. By giving it an approximate estimate
function, we can prevent loop unrolling from going to town when it
shouldn't.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
We already have one internally for int64 but we don't have a similar one
for doubles so we'll have to make one.
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
This is set to True only for numeric conversion opcodes.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Not complete, mostly just adding things as I encounter them in CTS. But
not getting far enough yet to hit most of the OpenCL.std instructions.
Anyway, this is better than nothing and covers the most common builtins.
v2: add hadd proof from Jason
move some of the lowering into opt_algebraic and create new nir opcodes
simplify nextafter lowering
fix normalize lowering for inf
rework upsample to use nir_pack_bits
add missing files to build systems
v3: split lines of iadd/sub_sat expressions
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
v2: use formula with fewer operations
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
v2: add assert in else clause
make local group intrinsics 32 bit wide
v3: always use 32 bit constant for local_size
v4: add comment by Jason
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
we define it inside 'include/c99_math.h' so it is safe to use.
Signed-off-by: Karol Herbst <kherbst@redhat.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Note that locations can be set in different units, and the multiplier
argument caters to supporting these different units. For example,
st_glsl_to_nir uses dwords (4 bytes) so the multiplier should be 4,
while tgsi_to_nir uses bytes, so the multiplier should be 16.
Signed-Off-By: Timur Kristóf <timur.kristof@gmail.com>
Tested-by: Andre Heider <a.heider@gmail.com>
Tested-by: Rob Clark <robdclark@gmail.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
The nir_lower_uniforms_to_ubo function is useful outside of
mesa/state_tracker, and in fact is needed to produce NIR for
drivers that have the PIPE_CAP_PACKED_UNIFORMS capability.
Signed-Off-By: Timur Kristóf <timur.kristof@gmail.com>
Tested-by: Andre Heider <a.heider@gmail.com>
Tested-by: Rob Clark <robdclark@gmail.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
This patch adds a shader_info field that tells the driver to use window
space coordinates for a given vertex shader. It also enables this feature
in radeonsi (the only NIR-capable driver that supported it in TGSI),
and makes tgsi_to_nir aware of it.
Signed-Off-By: Timur Kristóf <timur.kristof@gmail.com>
Tested-by: Andre Heider <a.heider@gmail.com>
Tested-by: Rob Clark <robdclark@gmail.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
This lets us emit the VPM_WRITEs directly from
nir_intrinsic_store_output() (useful once NIR scheduling is in place so
that we can reduce register pressure), and lets future NIR scheduling
schedule the math to generate them. Even in the meantime, it looks like
this lets NIR DCE some more code and make better decisions.
total instructions in shared programs: 6429246 -> 6412976 (-0.25%)
total threads in shared programs: 153924 -> 153934 (<.01%)
total loops in shared programs: 486 -> 483 (-0.62%)
total uniforms in shared programs: 2385436 -> 2388195 (0.12%)
Acked-by: Ian Romanick <ian.d.romanick@intel.com> (nir)
We were printing only when the channel was exactly the start channel, so
scalarized loads/stores would be missing the name on the rest.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
We need more space than just a 32-bit scalar and we have to burn all
that space anyway so we may as well expose it to the driver. This also
fixes a subtle bug when UBOs and SSBOs have different pointer types.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
With the new deref changes, the old pointer_offset version may not be
the right one to call. Just call the generic one and let it sort it
out.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
We can't pull it from the variable type because it might be an array of
blocks and not just the one block. While we're here, throw in some
error checking.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: mesa-stable@lists.freedesktop.org
When we have a larger sampler index, we get into the "high sampler"
scenario and need an instruction header. Even in SIMD8, this pushes the
instruction over the sampler message size maximum of 11 registers.
Instead, we have to lower TXD to TXL.
Fixes: cb98e0755f "intel/fs: Support min_lod parameters on texture..."
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
No idea how this fell through the cracks besides the fact that the
sampler bound at 0 almost always works and the CTS isn't amazing. In
any case, this appears to have been broken for almost forever.
Reviewed-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: mesa-stable@lists.freedesktop.org
Use new nir opcode nir_[i/u]mul_2x32_64 and extract lower and higher 32
bits as needed instead of emitting mul and mul_high.
v2: Surround the switch case with curly braces (Jason Ekstrand)
Signed-off-by: Sagar Ghuge <sagar.ghuge@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Optimize a situation where we only need lower 32 bits from 64 bit
result.
Signed-off-by: Sagar Ghuge <sagar.ghuge@intel.com>
Suggested-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Optimize mulExtended to use 32x32->64 multiplication.
Drivers which are not based on NIR, they can set the
MUL64_TO_MUL_AND_MUL_HIGH lowering flag in order to have same old
behavior.
v2: Add missing condition check (Jason Ekstrand)
Signed-off-by: Sagar Ghuge <sagar.ghuge@intel.com>
Suggested-by: Matt Turner <Matt Turner <mattst88@gmail.com>
Suggested-by: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
On Gen 8 and 9, "mul" instruction supports 64 bit destination type. We
can reduce our 64x64 int multiplication from 4 instructions to 3.
Also instead of emitting two mul instructions, we can emit single mul
instuction and extract low/high 32 bits from 64 bit result for
[i/u]mulExtended
v2: 1) Allow lower_mul_high64 to use new opcode (Jason Ekstrand)
2) Add lower_mul_2x32_64 flag (Matt Turner)
3) Remove associative property as bit size is different (Connor
Abbott)
v3: Fix indentation and variable naming convention (Jason Ekstrand)
Signed-off-by: Sagar Ghuge <sagar.ghuge@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
This is purely for conformance, since it's not actually possible to do
XFB on TCS output varyings. However we do have to make sure we record
the names correctly, and this removes an extra level of array-ness from
the names in question.
Fixes KHR-GL45.tessellation_shader.single.xfb_captures_data_from_correct_stage
v2: Add comment to the new program_resource_visitor::process function.
(Ilia Mirkin)
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=108457
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: 19.0 <mesa-stable@lists.freedesktop.org>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Avoids regression on:
KHR-GLES*.core.tessellation_shader.single.xfb_captures_data_from_correct_stage
that is uncovered by the following patch.
"glsl: fix recording of variables for XFB in TCS shaders"
v2: Rebased over glsl: fix recording of variables for XFB in TCS shaders
v3: Move this patch before "glsl: fix recording of variables for XFB in TCS
shaders" to avoid temporal regressions. (Illia Mirkin)
Cc: 19.0 <mesa-stable@lists.freedesktop.org>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
EXT_texture_query_lod provides the same functionality for GLES like
the ARB extension with the same name for GL.
v2: Set ES 3.0 as minimum GLES version as required by the extension
Signed-off-by: Gert Wollny <gert.wollny@collabora.com>
Reviewed-by: Eric Anholt <eric@anholt.net>
This will allow the options to be visible under nir_shader->options,
which will allow the gallium state_tracker to use the driver preferred
settings during glsl_to_nir.
Suggested-by: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
I noticed this while looking at a shader that was affected by Tim's
"more loop unrolling" series.
In review, Tim Arceri asked:
> Why the hurt on Gen6+ is this something that should be in the late
> optimisations pass?
As far as I can tell, it's just because our scheduler is terrible. In
all the fragment shaders that I looked at (some hurt shaders were from
other stages), only one of the SIMD8 or SIMD16 version would be hurt.
In many of those case, the other SIMD width is improved (e.g.,
shaders/closed/steam/brutal-legend/3990.shader_test).
Often it looks like the scheduler decides to differently schedule a SEND
the occurs somewhere early in the shader. Once that happens, everything
is different.
I looked at one vertex shader that was hurt (from Goat Simulator). In
that case, both the floor and fract are used. The optimization
eliminates the add, and it should allow better scheduling. In the area
of the FRC and RNDD instructions, the scheduler does the right thing.
However, later in the shader a MAD and and ADD get scheduled
differently, and that makes it slightly worse.
In light of this, I tried adding some "is_used_once" mark-up, and that
did not fix all the cycles regressions. It also did a lot more harm
than good on SKL (helped 82 vs. hurt 241).
All Gen6+ platforms had similar results. (Skylake shown)
total instructions in shared programs: 15437001 -> 15435259 (-0.01%)
instructions in affected programs: 213651 -> 211909 (-0.82%)
helped: 988
HURT: 0
helped stats (abs) min: 1 max: 27 x̄: 1.76 x̃: 1
helped stats (rel) min: 0.15% max: 11.54% x̄: 1.14% x̃: 0.59%
95% mean confidence interval for instructions value: -1.89 -1.63
95% mean confidence interval for instructions %-change: -1.23% -1.05%
Instructions are helped.
total cycles in shared programs: 383007378 -> 382997063 (<.01%)
cycles in affected programs: 1650825 -> 1640510 (-0.62%)
helped: 679
HURT: 302
helped stats (abs) min: 1 max: 348 x̄: 23.39 x̃: 14
helped stats (rel) min: 0.04% max: 28.77% x̄: 1.61% x̃: 0.98%
HURT stats (abs) min: 1 max: 250 x̄: 18.43 x̃: 7
HURT stats (rel) min: 0.04% max: 25.86% x̄: 1.41% x̃: 0.53%
95% mean confidence interval for cycles value: -13.05 -7.98
95% mean confidence interval for cycles %-change: -0.86% -0.50%
Cycles are helped.
Iron Lake and GM45 had similar results. (GM45 shown)
total instructions in shared programs: 5043616 -> 5043010 (-0.01%)
instructions in affected programs: 119691 -> 119085 (-0.51%)
helped: 432
HURT: 0
helped stats (abs) min: 1 max: 27 x̄: 1.40 x̃: 1
helped stats (rel) min: 0.10% max: 8.11% x̄: 0.66% x̃: 0.39%
95% mean confidence interval for instructions value: -1.58 -1.23
95% mean confidence interval for instructions %-change: -0.72% -0.59%
Instructions are helped.
total cycles in shared programs: 128139812 -> 128135762 (<.01%)
cycles in affected programs: 3829724 -> 3825674 (-0.11%)
helped: 602
HURT: 0
helped stats (abs) min: 2 max: 486 x̄: 6.73 x̃: 6
helped stats (rel) min: 0.02% max: 4.85% x̄: 0.19% x̃: 0.10%
95% mean confidence interval for cycles value: -8.40 -5.05
95% mean confidence interval for cycles %-change: -0.22% -0.16%
Cycles are helped.
Reviewed-by: Elie Tournier <tournier.elie@gmail.com>
I have not investigated the result of doing this during code
generation. That should be possible, but it would be a bit more
effort.
All Gen6+ platforms had nearly identical results. (Skylake shown)
total cycles in shared programs: 370961508 -> 370961367 (<.01%)
cycles in affected programs: 5174 -> 5033 (-2.73%)
helped: 2
HURT: 0
Iron Lake and GM45 had similar results. (Iron Lake shown)
total instructions in shared programs: 8206587 -> 8206589 (<.01%)
instructions in affected programs: 1325 -> 1327 (0.15%)
helped: 0
HURT: 2
total cycles in shared programs: 187657422 -> 187657428 (<.01%)
cycles in affected programs: 11566 -> 11572 (0.05%)
helped: 0
HURT: 2
This change has almost no effect right now. However, removing this
patch (but leaving the patch "intel/fs: Generate if instructions with
inverted conditions") after adding a patch that removes !(a < b) -> (a
>= b) optimizations (like
https://patchwork.freedesktop.org/patch/264787/) has the following
results on Skylake:
Skylake
total instructions in shared programs: 15071804 -> 15071806 (<.01%)
instructions in affected programs: 640 -> 642 (0.31%)
helped: 0
HURT: 2
total cycles in shared programs: 369914348 -> 369916569 (<.01%)
cycles in affected programs: 27900 -> 30121 (7.96%)
helped: 4
HURT: 15
helped stats (abs) min: 2 max: 112 x̄: 30.00 x̃: 3
helped stats (rel) min: 0.28% max: 12.28% x̄: 3.34% x̃: 0.40%
HURT stats (abs) min: 2 max: 758 x̄: 156.07 x̃: 81
HURT stats (rel) min: 0.20% max: 74.30% x̄: 16.29% x̃: 16.91%
95% mean confidence interval for cycles value: 12.68 221.11
95% mean confidence interval for cycles %-change: 3.09% 21.23%
Cycles are HURT.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Differently than the direct case, the indirect array derefs of vector
are handled like regular derefs, with the exception that we ignore any
vector entry that has SSA values when performing a load. Such SSA
values don't help loading of the indirect unless we emit an if-ladder.
Copy_derefs are supported for indirects.
Also enable two tests that now pass.
v2: Remove unnecessary temporaries. Be clearer when identifying the
case where copy_entry doesn't help when we are dealing with an
indirect array_deref (of a vector). (Jason)
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
When looking up an entry to use, always prefer an equal match, as it
more likely to contain reusable SSA or derefs to propagate.
This will be necessary when adding entries with array derefs of
vectors, because we don't want the vector if the equal entry (an array
deref of that vector) is present.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Both on an actual array and on a vector, and an extra test on a vector
mixing direct and indirect access. The vector tests are disabled and
will be enabled by a later commit.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
When direct array deref is used on a vector type (for loads and
stores), copy_prop_vars is now smart to propagate values it knows
about.
Given a 'vec4 v', storing to v[3] will update the copy entry for v and
it is equivalent to a write to v.w. Loading from v[1] will try first
to see if there's a known value for v.y -- and drop the load in that
case.
The copy entries still always refer to the entire vectors, so the
operations happen on the parent deref (the 'vector') and the values
are fixed accordingly.
It might be the case now that certain entries have not only different
SSA defs in each element but also those come from different components
than they are set to, because stores to individual elements always
come from a SSA definition with a single component.
Tests related to these cases are now enabled.
v2: Instead of asserting on invalid indices, "load" an undef and
remove the store. (Jason)
v3: Merge code path for the cases of is_array_deref_of_vector into the
regular code path. Add a base_index parameter to
value_set_from_value. (code changes by Jason)
v4: Removed the get_entry_for_deref helper, now being used only once.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Also replace uses of 0xf with the appropriate full mask created from
the number of components.
Note that an increase of MAX might make us change how the data is
stored later on, but for now at least we make sure the pass is not
hardcoded.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
The name reflected this function role back when the pass also did dead
write elimination. So rename it to what it does now, which is setting
a value using another value; and narrow the argument list.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
When emitting a branch in a block, it does not make sense to continue
processing further instructions, as they will not be reachable.
This fixes a nasty case with a loop with a branch that both then-part
and else-part exits the loop:
%1 = OpLabel
OpLoopMerge %2 %3 None
OpBranchConditional %false %2 %2
%3 = OpLabel
OpBranch %1
%2 = OpLabel
[...]
We know that block %1 will branch always to block %2, which is the merge
block for the loop. And thus a break is emitted. If we keep continuing
processing further instructions, we will be processing the branch
conditional and thus emitting the proper NIR conditional, which leads to
instructions after the break.
This fixes dEQP-VK.graphicsfuzz.continue-and-merge.
CC: Jason Ekstrand <jason@jlekstrand.net>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Some types of params such as some builtins are always padded. We
need to keep track of this so we can restore the list correctly.
Here we also remove a couple of cache entries that are not actually
required as they get rebuilt by the _mesa_add_parameter() calls.
This patch fixes a bunch of arb_texture_multisample and
arb_sample_shading piglit tests for the radeonsi NIR backend.
Fixes: edded12376 ("mesa: rework ParameterList to allow packing")
Reviewed-by: Marek Olšák <marek.olsak@amd.com>