Video textures include padding, so make sure to not sample outside
src rect. Also remove the parameter and always use the offset.
When not scaling, this fixes blurry output.
When scaling, this fixes incorrect color at right/bottom edge.
Acked-by: Leo Liu <leo.liu@amd.com>
Reviewed-by: Thong Thai <thong.thai@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/24869>
This reduces silliness in Dolphin ubershaders by eliminating the double
lowering. It also makes the GLES shader assembly nicer to read.
Dolphin ubershader performance at 4K on MMG improved by about 0.5%. Not massive,
but definitely noticeable and reduces the delta to macOS.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
While desktop GL supports sampler LOD bias, GLES does not. To support the GL use
case, all Gallium drivers are expected to handle sampler LOD bias. However, this
may require shader code to implement (lowering tex to txb, txl to fadd+txl) and
cost resources to push the LOD bias constants into the shader. The issue is
compounded with something like Dolphin's GLES renderer, which does this LOD bias
emulation itself -- meaning that LOD bias is lowered twice when using Dolphin
with GLES! As such, this commit adds a context flag for frontends to communicate
that they will never use sampler LOD bias, allowing the driver to omit the
lowering as a GLES fast path (or, for Dolphin, for performance parity between
GLES and GL).
This will be used on Asahi. It could also be used to optimize a path on
Mali-T720 supported in Panfrost, though I don't intend to write that patch.
Originally https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25034
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
When rendering to a layered depth/stencil attachment, we specify the layer
stride in pages. That means that depth/stencil targets must be page-aligned to
be rendered to correctly.
If we're merely sampling, not rendering, we do not need the extra alignment. So
we add a flag to handle this case so we keep passing the generated ail tests.
Fixes KHR-GLES31.core.texture_cube_map_array.color_depth_attachments
Similarly, we page-align colour attachments. I don't have a good theoretical
justification for this part, but it seems to be necessary and layered rendering
fails otherwise. Possibly the PBE requires page-aligned layers unconditionally?
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
This lets us save a LOT of instructions at the cost of increased register
pressure. However, on my shader-db, this is still coming out ahead since no
shaders are hurt for thread count/spills, and only 1/10 of the shaders helped
for instruction count are hurt for register pressure. The shaders most hurt
for pressure have very low pressure (7 -> 15 is the worst case) and you need a
certain number of registers to use a 4 source instruction at all. Analyzing the
hurt shaders, nothing concerns me too much ... this isn't as bad as I feared.
So I think at this point it's worth ripping off the bandage, given the massive
potential for instruction count win. This is a big improvement for some of the
shaders I'm working on for my $SECRET_PROJECT.
total instructions in shared programs: 1784943 -> 1775169 (-0.55%)
instructions in affected programs: 644211 -> 634437 (-1.52%)
helped: 3498
HURT: 38
Instructions are helped.
total bytes in shared programs: 11720734 -> 11643224 (-0.66%)
bytes in affected programs: 4370986 -> 4293476 (-1.77%)
helped: 3572
HURT: 36
Bytes are helped.
total halfregs in shared programs: 474094 -> 475165 (0.23%)
halfregs in affected programs: 12821 -> 13892 (8.35%)
helped: 65
HURT: 247
Halfregs are HURT.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
Simple greedy thing that has the potential to inflate register pressure but
reduces instructions. Thanks to the recent loop work that turns if { break }
into while_icmp, this also implicitly handles fusing conditions into loops,
which is what actually prompted this.
Surprisingly, this helps register pressure on my shader-db (no change to thread
count), I guess by eliminating the boolean temps in case where the sources are
used multiple times.
total instructions in shared programs: 1786561 -> 1784943 (-0.09%)
instructions in affected programs: 128557 -> 126939 (-1.26%)
helped: 474
HURT: 13
Instructions are helped.
total bytes in shared programs: 11733236 -> 11720734 (-0.11%)
bytes in affected programs: 976034 -> 963532 (-1.28%)
helped: 521
HURT: 13
Bytes are helped.
total halfregs in shared programs: 474245 -> 474094 (-0.03%)
halfregs in affected programs: 1869 -> 1718 (-8.08%)
helped: 28
HURT: 7
Halfregs are helped.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
Apple doesn't do this, but it should be equivalent and it makes it easier to see
that we can use while_icmp for break_if_icmp in loops that don't use continue
(which Apple does do). So, the effect of this commit is to use while_icmp for
most breaks, which saves an instruction.
total instructions in shared programs: 1764199 -> 1764076 (<.01%)
instructions in affected programs: 24149 -> 24026 (-0.51%)
helped: 78
HURT: 0
Instructions are helped.
total bytes in shared programs: 11609306 -> 11608322 (<.01%)
bytes in affected programs: 164604 -> 163620 (-0.60%)
helped: 78
HURT: 0
Bytes are helped.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
The only role of the while_icmp at the end of a NIR loop is to make continue
jumps work. If, after emitting the loop, we learn that there are no continues,
there is no need to insert a while_icmp since it would be a no-op anyway.
total instructions in shared programs: 1764311 -> 1764199 (<.01%)
instructions in affected programs: 26321 -> 26209 (-0.43%)
helped: 82
HURT: 0
Instructions are helped.
total bytes in shared programs: 11609978 -> 11609306 (<.01%)
bytes in affected programs: 178842 -> 178170 (-0.38%)
helped: 82
HURT: 0
Bytes are helped.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
In general, loops need a push_exec at the start for correctness. However, a
push_exec at the top level (non-nested) is a no-op, so we can omit and save a
few cycles.
total instructions in shared programs: 1764350 -> 1764311 (<.01%)
instructions in affected programs: 7339 -> 7300 (-0.53%)
helped: 36
HURT: 0
Instructions are helped.
total bytes in shared programs: 11610212 -> 11609978 (<.01%)
bytes in affected programs: 48638 -> 48404 (-0.48%)
helped: 36
HURT: 0
Bytes are helped.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
Search for code like
if ... {
break
}
and replace with a break_if pseudo-instruction for optimized handling, since the
break_if lowering is better than the original code.
total instructions in shared programs: 1764596 -> 1764350 (-0.01%)
instructions in affected programs: 24540 -> 24294 (-1.00%)
helped: 78
HURT: 0
Instructions are helped.
total bytes in shared programs: 11611196 -> 11610212 (<.01%)
bytes in affected programs: 166458 -> 165474 (-0.59%)
helped: 78
HURT: 0
Bytes are helped.
shader-db probably understates the benefit here, since this optimizes the body
of loops.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
We use it for two different things. Pseudo-instructions are cheap, split it up
for easier optimization passes. This also fixes the schedule classes.. we can
move the cf_begin around if we want, it's inert.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
They're more trouble than they're worth for us. They were originally lifted
unthinkingly from ACO, where I assume they're necessary for software CF
lowering, but they're just an inconvenient convenience for us. Remove em.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
If we bound 4 render targets but we only write to 1 of them, the other 3 need
their contents preserved. This requires either properly configuring HSR to
implement colour masking (TODO) or using the big hammer of setting TRANSLUCENT.
This patch picks the latter for now.
Signed-off-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
The debug flags are already plumbed into driver_flags for the disk
cache, so we just need to actually allow some flags instead of bailing
out of the disk cache init.
We only care about no16 for production right now, and it's probably a
good idea to disable disk caching during most debug sessions, so
allowlist only that one.
Signed-off-by: Asahi Lina <lina@asahilina.net>
Reviewed-by: Eric Engestrom <eric@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
There are way too many broken WebGL apps using the wrong precision
qualifiers, which causes anything from jittery geometry to complete
breakage (e.g. QuakeJS and other games).
In addition, a Firefox bug is breaking basic canvas rendering for the
same reason (mozilla bug #1845309).
Let's just disable fp16 for browsers. There is no hope of getting all
this broken stuff fixed.
Signed-off-by: Asahi Lina <lina@asahilina.net>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Eric Engestrom <eric@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25052>
Jordan Justen