Extracts some per-impl code to nir_lower_vec3_to_vec4 and then
converts to use the nir_shader_instructions_pass helper.
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11683>
The new code splits the work into a few passes instead of trying to do
everything with a single pass. This helps to apply the new clarified
rules for structured control flow in the SPIR-V specification, in
particular the "exit construct" rules.
First find an appropriate ordering for the blocks, based on the
approach taken by Tint (WebGPU compiler). Then, with those blocks
in order, identify the SPIR-V constructs start and end positions.
Finally, walk the blocks again to emit NIR for each of them, "opening"
and "closing" the necessary NIR constructs as we reach the start and
end positions of the SPIR-V constructs.
There are a couple of interesting choices when mapping the constructs
to NIR:
- NIR doesn't have something like a switch, so like the previous code,
we lower the switch construct to a series of conditionals for each
case.
- And, unlike the previous code, when there's a need to perform a
break from a construct that NIR doesn't directly support (e.g. inside
a case construct, conditionally breaking early from the switch), we
now use a combination of a NIR loop and an NIR if. Extra code is
added to ensure that loop_break and loop_continues are propagated
to the right loop.
This should fix various issues with valid SPIR-V that previously
resulted in "Invalid back or cross-edge in the CFG" errors.
Thanks to Alan Baker and David Neto for their explanations of
ordering the blocks, in the Tint code and in presentations to
the SPIR-V WG.
Thanks to Jack Clark for providing a lot of valuable tests used to
validate this MR.
Closes: #5973, #6369
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17922>
If we know the next stage, we can tell whether an output is a sysval,
such as POS.
For example, POS is not a sysval output if the next stage is not FS.
Reviewed-by: Qiang Yu <yuq825@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21861>
We need to keep variables in the IR because a few places use them,
like nir_build_program_resource_list. This will allow us to lower IO
in the linker.
Reviewed-by: Qiang Yu <yuq825@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21861>
Since nir_recompute_io_bases is going to be used instead of
nir_assign_io_var_locations, we need to update num_inputs, num_outputs.
Reviewed-by: Qiang Yu <yuq825@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21861>
- VAR31 was ignored.
- Only a half of the 16-bit slot was passed through, though I'm not sure
if nir_lower_io handles vec8. The slots are only for GLES and I don't
think a passthrough TCS is possible with GLES.
Fixes: a8e84f50bc - nir: Add helper to create passthrough TCS shader
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21861>
They use same instruction. Just because when the time
nir_load_smem_buffer_amd was introduced, radeonsi didn't support
pass buffer descriptor to nir_load_ubo directly.
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Qiang Yu <yuq825@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22523>
With independent sets, we're not able to compute immediate values for
the index at which to read anv_push_constants::dynamic_offsets to get
the offset of a dynamic buffer. This is because the pipeline layout
may not have all the descriptor set layouts when we compile the
shader.
To solve that issue, we insert a layer of indirection.
This reworks the dynamic buffer offset storage with a 2D array in
anv_cmd_pipeline_state :
dynamic_offsets[MAX_SETS][MAX_DYN_BUFFERS]
When the pipeline or the dynamic buffer offsets are updated, we
flatten that array into the
anv_push_constants::dynamic_offsets[MAX_DYN_BUFFERS] array.
For shaders compiled with independent sets, the bottom 6 bits of
element X in anv_push_constants::desc_sets[] is used to specify the
base offsets into the anv_push_constants::dynamic_offsets[] for the
set X.
The computation in the shader is now something like :
base_dyn_buffer_set_idx = anv_push_constants::desc_sets[set_idx] & 0x3f
dyn_buffer_offset = anv_push_constants::dynamic_offsets[base_dyn_buffer_set_idx + dynamic_buffer_idx]
It was suggested by Faith to use a different push constant buffer with
dynamic_offsets prepared for each stage when using independent sets
instead, but it feels easier to understand this way. And there is some
room for optimization if you are set X and that you know all the sets in
the range [0, X], then you can still avoid the indirection. Separate
push constant allocations per stage do have a CPU cost.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15637>
Add more system values for XFB. This should be good enough for lowering GL3.1 +
transform_feedback2 + transform_feedback3. More will probably be needed for
geom/tess but that will be easier to work with when I'm actually bringing up
geom/tess. At any rate, we're splitting out XFB from the rasterization pipeline
and since XFB happens only in the last shader pre-rasterization stage, VS+XFB is
an orthogonal problem from e.g. VS+GS+XFB. Yeah, the combinatorics suck.
These will be used by Asahi, and hopefully eventually Panfrost.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Acked-by: Jesse Natalie <jenatali@microsoft.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22123>
Loading output require per-sample blending, so enable per-sample execution of
the shader as a whole so the right sample values are blended. Affects:
dEQP-GLES31.functional.multisample.default_framebuffer.sample_mask_sum_of_inverses
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22385>
Only insert a load_output if we're going to use it, don't rely on it getting
DCE'd since that will mess up the shader info. This does require a bit of logic
to figure out whether we do need it.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22385>
Floating point ALU assume no NaNs unless
FLOAT_CONTROLS_SIGNED_ZERO_INF_NAN_PRESERVE_FPn or (for some opcodes)
exact=true.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Fixes: bf9c1699cd ("nir: add nir_fisnan helper function")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22206>
We can mostly unify the instr-use and if-use handling, which is a lot more
concise.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22343>
Like nir_instr_rewrite_ssa but without the asserted extra argument. Works on ifs
too, now that we have a unified use list.
We do need to assert that the source has actually been inserted and has valid
use/def chains. Previously, asserting on the parent instruction accomplished
that indirectly. For the more general helper, we instead directly assert that
there exists a non-null parent, whatever it is.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22343>
A source used by an if is necessarily the condition of that if.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22343>
We don't use the tag anywhere, so don't bother with it.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Suggested-by: Faith Ekstrand <faith@gfxstrand.net>
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22343>
We can now determine whether a nir_src is for an if without a sideband, so
simplify the function signature.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Suggested-by: Faith Ekstrand <faith@gfxstrand.net>
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22343>
Every nir_ssa_def is part of a chain of uses, implemented with doubly linked
lists. That means each requires 2 * 64-bit = 16 bytes per def, which is
memory intensive. Together they require 32 bytes per def. Not cool.
To cut that memory use in half, we can combine the two linked lists into a
single use list that contains both regular instruction uses and if-uses. To do
this, we augment the nir_src with a boolean "is_if", and reimplement the
abstract if-uses operations on top of that list. That boolean should fit into
the padding already in nir_src so should not actually affect memory use, and in
the future we sneak it into the bottom bit of a pointer.
However, this creates a new inefficiency: now iterating over regular uses
separate from if-uses is (nominally) more expensive. It turns out virtually
every caller of nir_foreach_if_use(_safe) also calls nir_foreach_use(_safe)
immediately before, so we rewrite most of the callers to instead call a new
single `nir_foreach_use_including_if(_safe)` which predicates the logic based on
`src->is_if`. This should mitigate the performance difference.
There's a bit of churn, but this is largely a mechanical set of changes.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reviewed-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22343>
NIR's docs for sampler_index say
The following operations do not require a sampler and, as such, this
field should be ignored:
- nir_texop_txf
- nir_texop_txf_ms
- nir_texop_txs
- nir_texop_query_levels
- nir_texop_texture_samples
- nir_texop_samples_identical
Contrary to this documentation, we were still printing the sampler_index anyway,
even though the value is formally undefined. This was helpful for
PIPE_CAP_TEXTURE_BUFFER_SAMPLER drivers that (despite the NIR docs) respected the
sampler_index anyway. There are no longer any such drivers, so we should stop
printing sampler_index for txf to avoid confusion (and noise).
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22223>
The one test that remains would have an automatically generated name
that would conflict with another test. This test is also a little
special (per the comment in the test), so it's probably best to leave it
separate anyway.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3445>
If loop iterator is incremented with something other than regular
addition, it would be more error prone to calculate the number of
iterations theoretically. What we can do instead, is try to emulate the
loop, and determine the number of iterations empirically.
These operations are covered:
- imul
- fmul
- ishl
- ishr
- ushr
Also add unit tests for loop unrollment.
Improves performance of Aztec Ruins (sixonix
gfxbench5.aztec_ruins_vk_high) by -1.28042% +/- 0.498555% (N=5) on Intel
Arc A770.
v2 (idr): Rebase on 3 years. :( Use nir_phi_instr_add_src in the test
cases.
v3 (idr): Use try_eval_const_alu in to evaluate loop termination
condition in get_iteration_empirical. Also restructure the loop
slightly. This fixed off by one iteration errors in "inverted" loop
tests (e.g., nir_loop_analyze_test.ushr_ieq_known_count_invert_31).
v4 (idr): Use try_eval_const_alu in to evaluate induction variable
update in get_iteration_empirical. This fixes non-commutative update
operations (e.g., shifts) when the induction varible is not the first
source. This fixes the unit test
nir_loop_analyze_test.ishl_rev_ieq_infinite_loop_unknown_count.
v5 (idr): Fix _type parameter for fadd and fadd_rev loop unroll
tests. Hopefully that fixes the failure on s390x. Temporarily disable
fmul. This works-around the revealed problem in
glsl-fs-loop-unroll-mul-fp64, and there were no shader-db or fossil-db
changes.
v6 (idr): Plumb max_unroll_iterations into get_iteration_empirical. I
was going to do this, but I forgot. Suggested by Tim.
v7 (idr): Disable fadd tests on s390x. They fail because S390 is weird.
Almost all of the shaders affected (OpenGL or Vulkan) are from gfxbench
or geekbench. A couple shaders in Deus Ex (OpenGL), Dirt Rally (OpenGL),
Octopath Traveler (Vulkan), and Rise of the Tomb Raider (Vulkan) are
helped.
The lost / gained shaders in OpenGL are an Aztec Ruins shader that goes
from SIMD16 to SIMD8. The spills / fills affected are in a single Aztec
Ruins (Vulkan) compute shader.
shader-db results:
Skylake, Ice Lake, and Tiger Lake had similar results. (Tiger Lake shown)
total loops in shared programs: 5514 -> 5470 (-0.80%)
loops in affected programs: 62 -> 18 (-70.97%)
helped: 37 / HURT: 0
LOST: 2
GAINED: 2
Haswell and Broadwell had similar results. (Broadwell shown)
total loops in shared programs: 5346 -> 5298 (-0.90%)
loops in affected programs: 66 -> 18 (-72.73%)
helped: 39 / HURT: 0
fossil-db results:
Skylake, Ice Lake, and Tiger Lake had similar results. (Tiger Lake shown)
Instructions in all programs: 157374679 -> 157397421 (+0.0%)
Instructions hurt: 28
SENDs in all programs: 7463800 -> 7467639 (+0.1%)
SENDs hurt: 28
Loops in all programs: 38980 -> 38950 (-0.1%)
Loops helped: 28
Cycles in all programs: 7559486451 -> 7557455384 (-0.0%)
Cycles helped: 28
Spills in all programs: 11405 -> 11403 (-0.0%)
Spills helped: 1
Fills in all programs: 19578 -> 19588 (+0.1%)
Fills hurt: 1
Lost: 1
Signed-off-by: Yevhenii Kolesnikov <yevhenii.kolesnikov@globallogic.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3445>
These operations are covered:
- imul
- fmul
- ishl
- ishr
- ushr
The only cases that can be currently affected are those where the
calculated loop-trip count would be zero.
v2 (idr): Split out from original commit. Rebase on lots of other work.
v3 (idr): Move operand size assertion. This code only cares that the
operands have the same size for the iadd and fadd cases. In other
cases, such as shifts, the sizes may not match. Fixes assertion
failures in
tests/spec/arb_gpu_shader_int64/glsl-fs-loop-unroll-ishl-int64.shader_test.
No shader-db or fossil-db changes on any Intel platform.
Signed-off-by: Yevhenii Kolesnikov <yevhenii.kolesnikov@globallogic.com>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3445>
This dramatically simplifies will_break_on_first_iteration, and, much
more importantly, makes it significantly more flexible. It is now
possible to handle loops with more complex exit condition and other
kinds of increment operations.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/3445>
