In the past, multiple writes to a single register were pretty common,
but since we've transitioned to NIR, and leave the IR in SSA form for
everything not captured in a phi-web, the pattern of generating new
temporary registers at each step is a lot more common.
This pass isn't nearly as useful now. Across fossil-db on Alchemist,
this affects only 0.55% of shaders, which fall into two cases:
- Coarse pixel shading pixel-X/Y setup. There are a few cases where
we write a partial calculation into a register, then have a second
instruction read that as a source and overwrite it as a destination.
While we could use a temporary here, it doesn't actually help with
register pressure at all, since there's the same amount of values
live at both instructions regardless. So while this pass kicks in,
it doesn't do anything useful.
- Geometry shader control data bits (5 shaders total). We track masks
for handling EndPrimitive in a single register across the program,
and apparently in some cases can split the live range. However, it's
a single register...only in geometry shaders...which use EndPrimitive.
None of them appear to be in danger of spilling, either. So this tiny
benefit doesn't seem to justify the cost of running the pass.
So, just throw it out. It's not worth keeping.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26343>
Per Ian suggestion. Also clear up a few unnecessary casts around the code and
use `s` for fs_visitor ("shader"). Note to include a reference in ntf we need
to set it during initialization, so create an explicit mem_ctx for it.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26323>
Uses the dispatch_width from the shader (fs_visitor). This was not
possible before because the dispatch_width was not part of
backend_shader.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26323>
This will allow fs_builder have a reference to an fs_visitor (a
"fs_shader" really), instead of a reference to a backend_shader.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26323>
At this point this is more a header dependency due to inline functions,
so shuffle them around. The end goal is to allow fs_builder have a
reference to a fs_visitor (really a fs_shader).
Note the header is still included, a later patch will move the includes
to the call-sites.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26323>
The remaining users can simply create a new builder at_end() if needed.
In many places a new builder object is already being constructed, so
just give more specific instructions.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26323>
The current name doesn't cover all the tex related instructions and
in all usages, we already have a switch statement to dispatch
per instruction type, so is more natural to list the instructions we
care there.
In fs::is_send_from_grf() we can simply ignore them since the
instructions are either lowered directly to SEND (Gfx7+) or use
MRF (Gfx6-).
With this change, the fs_inst::size_read() generated code gets
simplified (the "tex" entries get added to the switch jump table
in gcc) and the default case loses the conditional handling tex.
This reduces shader compilation time, as illustrated by replaying
fossils (tested on my TGL laptop):
```
// Rise of the Tomb Raider (N=13)
Difference at 95.0% confidence
-1.32231 +/- 0.0170138
-4.37605% +/- 0.0563054%
(Student's t, pooled s = 0.0210159)
// Cyberpunk 2077 (N=7)
Difference at 95.0% confidence
-3.64 +/- 0.114993
-2.95188% +/- 0.0932544%
(Student's t, pooled s = 0.09873)
```
Suggested-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25721>
The workaround applies specifically to Cube and Cube Arrays, so we can
still apply the optimization for the others.
Ideally we would like to pull opt_zero_samples logic into the lowering
sends -- to avoid adding a bit to communicate between passes. However
the texture coordinates for the LOGICAL backend instructions, which
are a common target for the optimization, are combined into offsets over
a single VGRF, so we can't easily identify the constant cases. The
copy-prop pass make this more visible for opt_zero_samples.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25742>
Inadvertently, because of a sequence of changes elsewhere, this pass
ended up not having any effect:
- Before Gfx5 the optimization is not applicable.
- On Gfx5-6 it doesn't apply because it sampler operations don't
currently use LOAD_PAYLOAD, but write the MOVs directly. Not clear to
me whether they ever did.
- On Gfx7+ it doesn't apply anymore because now the logical sampler
operations are now lowered directly to SENDs, and the is_tex() check
would skip them.
Since the LOAD_PAYLOAD implementation applies for Gfx7+ only, rework the
pass to work again by handling SEND instructions. To make the pass
easier, the optimization will happen before opt_split_sends() so only
one LOAD_PAYLOAD needs to be cared for.
Update the code to accept BAD_FILE sources in addition to zeros, these
are added in some cases as padding and effectively are don't care
values, so we can assume them zeros.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25742>
This is a preparation to (re-)enable opt_zero_samples(), which will reduce
a SEND mlen before we split it. When that happen, opt_split_sends()
won't be able to rely on the fact that mlen covers the entire
LOAD_PAYLOAD.
Since we are changing that, take the opportunity to also not modify the
existing LOAD_PAYLOAD, just create two new ones with the exact set of
sources. This allows the pass to be further simplified by iterating
forward and not require live_variables analysis.
The helper function was added so can be used later for
opt_zero_samples().
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25742>
For Task/Mesh WorkgroupID is now lowered to WorkgroupIndex by the
generic NIR pass, so we shouldn't hit this. We can now simplify the
asserting code in emit_work_group_id_setup().
Reviewed-by: Ivan Briano <ivan.briano@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25977>
Sandybridge uses this code and needs MRFs, but all other platforms send
from GRFs. Do that directly rather than relying on the MRF hack.
Ivybridge and later also use SHADER_OPCODE_SEND directly rather than
a virtual opcode that's handled in the generator, so we follow suit.
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20172>
We never set key->clamp_fragment_color when compiling the BLORP fast
clear shaders. Besides, we were setting saturate on an FB write opcode,
which...isn't even a thing. We would need it on the MOV, and weren't
setting it there. So it wouldn't have even worked.
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20172>
This is basically just once through the loop but copy and pasted. One
difference is that the single render target case used a headerless
message, and the multiple render target case always used headers.
Now we use headerless messages for the first render target, even in the
multiple render target case. While we already have it set up for the
other RTs, it's still 2 fewer registers to send. Minor improvement.
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20172>
A long time ago, we used a uniform for the clear color. Back in 2014,
we added support for using a flat input instead, as this was easier for
Vulkan, but we left the option of using a uniform for OpenGL.
Eventually nobody used the uniform approach anymore, but the compiler
code to handle it remained. Drop the dead code.
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20172>
This code is compiled out, but has been left in place in case we wanted
to use it for debugging something. In the olden days, we'd use it for
platform enabling. I can't think of the last time we did that, though.
I also used to use it for debugging. If something was misrendering, I'd
iterate through shaders 0..N, replacing them with "draw hot pink" until
whatever shader was drawing the bad stuff was brightly illuminated.
Once it was identified, I'd start investigating that shader.
These days, we have frameretrace and renderdoc which are like, actual
tools that let you highlight draws and replace shaders. So we don't
need to resort iterative driver hacks anymore. Again, I can't think of
the last time I actually did that.
So, this code is basically just dead. And it's using legacy MRF paths,
which we could update...or we could just delete it.
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20172>
First, we need to give the parent_instr field a unique name to be able to
replace with a helper. We have parent_instr fields for both nir_src and
nir_def, so let's rename nir_src::parent_instr in preparation for rework.
This was done with a combination of sed and manual fix-ups.
Then we use semantic patches plus manual fixups:
@@
expression s;
@@
-s->renamed_parent_instr
+nir_src_parent_instr(s)
@@
expression s;
@@
-s.renamed_parent_instr
+nir_src_parent_instr(&s)
@@
expression s;
@@
-s->parent_if
+nir_src_parent_if(s)
@@
expression s;
@@
-s.renamed_parent_if
+nir_src_parent_if(&s)
@@
expression s;
@@
-s->is_if
+nir_src_is_if(s)
@@
expression s;
@@
-s.is_if
+nir_src_is_if(&s)
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Acked-by: Faith Ekstrand <faith.ekstrand@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24671>
While working on cooperative matrix support, I noticed some invalid
DP4A instructions being generated.
dp4a(32) g33<1>UD g21<8,8,1>UD g1.0<0,1,0>UD g9<1,1,1>UD
This violates the constraint that the destination or a source can only
access two consecutive GRFs.
I'm a little surprised that validation didn't catch this. Perhaps
because it's a 3 source instruction? Either way, it seems like a bigger
project to fix that.
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Fixes: 0f809dbf40 ("intel/compiler: Basic support for DP4A instruction")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25554>
In the default case, there's a special case with a few conditions.
Prefer the cheapest conditions first, so we can take advantage of
short-circuiting.
Effect is a small but still significant reduce in shader compilation
times, as can be seen by:
- Fossil replay for Rise of the Tomb Raider
```
Difference at 95.0% confidence
-0.433333 +/- 0.028609
-1.42556% +/- 0.0941163%
(Student's t, pooled s = 0.0337886)
```
- Fossil replay for Batman Arkham City
```
Difference at 95.0% confidence
-8.84 +/- 0.146083
-1.65932% +/- 0.0274207%
(Student's t, pooled s = 0.125423)
```
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25549>
This is what most logical SEND messages do when they take a variable
number of components. 'inst->mlen' is expected to be zero for logical
SEND opcodes, which are expected to behave like plain arithmetic
operations, so certain automated transformations (like SIMD lowering)
can manipulate them without opcode-specific special-casing.
Guessing the number of components from 'inst->mlen' has other
disadvantages, because it requires duplicating the logic that infers
the message payload size in every use of the instruction -- Instead we
can just do the computation once during logical send lowering. In
addition on LNL platform this causes the 'inst->mlen' field of URB
writes to have units inconsistent with every other SEND instruction,
which is likely to lead to confusion and bugs down the road.
Rework:
* Marcin: update emit_urb_indirect_vec4_write
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25195>
Those are used in the failure paths and are easily retriavable from the
stage itself, so no need to store them.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25367>
The position in the error array already indicate the SIMD in question,
so take off all the formatted printing from the errors -- which in some
cases were just not needed. We lose a little bit of extra context but
it is all easily derivable from the message and the SIMD.
This also will remove the overhead when SIMD selection is being used to
just to find the selected dispatch width -- at a point where the shaders
were already compiled -- and the errors are not used at all.
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/9849
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25336>
Up until now, the mesh pipeline assumed it would be always linked to the
fragment shader, and so the calculated MUE map would always be
available.
That is not the case for fast linked pipeline libraries, so the URB
setup needs to account for this. We do this by replicating what's done
for non-mesh pipelines, defining the URB based on the FS inputs, and
always assuming they will be laid out in order of varying number, except
that we also account for per-primitive attributes.
Fixes all GPL using tests under dEQP-VK.mesh_shader.ext.smoke.*
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25047>
We try various pre-RA scheduler modes and see if any of them allow
us to register allocate without spilling. If all of them spill,
however, we left it on the last mode: LIFO. This is unfortunately
sometimes significantly worse than other modes (such as "none").
This patch makes us instead select the pre-RA scheduling mode that
gives the lowest register pressure estimate, if none of them manage
to avoid spilling. The hope is that this scheduling will spill the
least out of all of them.
fossil-db stats (on Alchemist) speak for themselves:
Totals:
Instrs: 197297092 -> 195326552 (-1.00%); split: -1.02%, +0.03%
Cycles: 14291286956 -> 14303502596 (+0.09%); split: -0.55%, +0.64%
Spill count: 190886 -> 129204 (-32.31%); split: -33.01%, +0.70%
Fill count: 361408 -> 225038 (-37.73%); split: -39.17%, +1.43%
Scratch Memory Size: 12935168 -> 10868736 (-15.98%); split: -16.08%, +0.10%
Totals from 1791 (0.27% of 668386) affected shaders:
Instrs: 7628929 -> 5658389 (-25.83%); split: -26.50%, +0.67%
Cycles: 719326691 -> 731542331 (+1.70%); split: -10.95%, +12.65%
Spill count: 110627 -> 48945 (-55.76%); split: -56.96%, +1.20%
Fill count: 221560 -> 85190 (-61.55%); split: -63.89%, +2.34%
Scratch Memory Size: 4471808 -> 2405376 (-46.21%); split: -46.51%, +0.30%
Improves performance when using XeSS in Cyberpunk 2077 by 90% on A770.
Improves performance of Borderlands 3 by 1.54% on A770.
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24707>
This moves a bit of code out of a large function, but also lets us reuse
it a few extra places in the next commit.
I opted to stop using ralloc here since this is short-lived data that
doesn't need to stick around for the rest of the compile, and it's easy
enough to free.
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24707>
pre_modes[] is an array with the modes ordered in our desired
preference. scheduler_mode_name[] was also in that order, and the two
had to be kept in sync. This is a little silly; we should just have
a mode enum -> string table and look it up via the enum.
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24707>
I'm going to introduce another call site for this function, and just
handling SCHEDULE_NONE in the scheduler itself makes more sense than
duplicating the logic.
Reviewed-by: Emma Anholt <emma@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24707>
