Dedicated BOs waste memory and are also a significant cause of CPU
overhead when applications use hundreds of them per frame due to
all the work the kernel has to do to page in all these BOs for a job.
The UE4 Vehicle demo was hitting this causing it to freeze and stutter
under 1fps.
The hardware allows us to setup groups of 16 queries in consecutive
4-byte addresses, requiring only that each group of 16 queries is
aligned to a 1024 byte boundary. With this change, we allocate all
the queries in a pool in a single BO and we assign them different
offsets based on the above restriction. This eliminates the freezes
and stutters in the Vehicle sample.
One caveat of this solution is that we can only wait or test for
completion of a query by testing if the GPU is still using its BO,
which basically means that we can only wait for all active queries
in a pool to complete and not just the ones being requested by the
API. Since the Vulkan recommendation is to use a different query
pool per frame this should not be a big issue though.
If this ever becomes a problem (for example if an application does't
follow the recommendation and instead allocates a single pool and
splits its queries between frames), we could try to group queries
in a pool into a number of BOs to try and find a balance, but for
now this should work fine in most cases.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10253>
The resource indices we get point to descriptor map entries that include
all shader stages, so we need to size the arrays to account for more than
just one stage.
For now we only support up to 2 stages in a pipeline, so we use that.
Fixes: 002304482c ('v3dv: avoid redundant BO job additions for UBO/SSBO')
Fixes: fa170dab4c ('v3dv: avoid redundant BO job additions for textures and samplers')
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10252>
There were various issues here:
- MAX_DYNAMIC_UNIFORM_BUFFERS was larger than MAX_UNIFORM_BUFFERS.
- In some cases we were exposing more than the minimums required.
While that is not incorrect, it is not following what we have
been doing in general.
- The Vulkan spec states that some of the MaxDescriptorSet limits
need to be multipled by 6 to include all shader stages, even
if the implementation doesn't support all shader stages.
Fixes: cbd299b051 ('v3dv/device: do not compute per-pipeline limits multiplying per-stage')
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10252>
Among other things, this gets us GCC 10 (was 6).
Requires some changes to third party components we use:
* Install apitrace (& waffle) from Debian; was hitting issues with the
local build, and it's the same version 9.0 anyway.
* Update Fossilize to a newer commit which builds with GCC 10.
* apt.llvm.org repositories are no longer needed.
* Use an SPIRV-LLVM-Translator commit which builds with LLVM 11.0.1.
* Install XCB packages from Debian, 1.13 fails to build with Python 3.9.
* Install wayland-protocols from Debian, 1.12 is too old for
libgtk-3-dev in bullseye.
LLVM 7/8 packages are no longer available.
Also adapt expected test results to Xvfb now exposing multi-samle
GLXFBConfigs.
v2:
* Install clang instead of clang-11.
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/3124
Reviewed-by: Eric Anholt <eric@anholt.net> # v1
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9833>
64 was a temporary and conservative "big enough" value, but we can do
better.
Note that as mentioned on the FIXME, we could be even more detailed,
adding a descriptor map allocate method based on the descriptor
type. That would mean more individual allocations, and slightly more
complexity.
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10207>
We had some cases were we have defined a value on v3dv_limits but
using other when setting it at GetPhysicalDeviceProperties (like
dynamic storage buffers).
Also we do a cleanup. So far we were adding on v3dv_limits only the
limits that were used on more that one place. But then we had the
definition of several limits on different places. It is clearer to
have a common place for those, even if it is used on just one place.
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10207>
There were two problems here:
* We were multiplying by 6, when for graphics pipelines, we only
support 2.
* Right now we are tracking descriptors through the descriptor
maps, and we have one per pipeline. So in practice there is no
difference between per-stage and per-pipeline limits. So far this
was not a problem, we could revisit in the future.
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10207>
Somewhat terrifyingly, we never sent this for direct contexts, which
means the server never knew the context/drawable bindings. To handle
this sanely, pull the request code up out of the indirect backend, and
rewrite the context switch path to call it as appropriate. This
attempts to preserve the existing behavior of not calling unbind() on
the context if its refcount would not drop to zero.
Of course, you can't just do this indiscriminately, because this is GLX
and extant X servers have bugs and everything is terrible. To wit:
- For 1.20.x prior to 1.20.6, you can bind a direct context once, but
the second time you try to modify the context's binding you will get
GLXBadContextTag. This includes unbinding the context. And "deleting"
the context will leak memory, because it will still appear to be
current.
- For 1.19 and earlier, glXMakeCurrent(dpy, None, ctx) should be legal
for GL 3.0+ contexts, but the server will throw BadMatch.
To guard against this, we only send the request for indirect contexts
unless the server is known good, and only mention one context at a time
in such a request; if switching between contexts, we first unbind the
old, and then bind the new. Note that the second VendorRelease() version
is to catch XFree86 4.x and Xorg [67].x, which almost certainly have the
above bugs. Other servers might report different version numbers here,
but we can't do direct rendering against them, so this should be safe.
Fixes: mesa/mesa#4418
Acked-By: Mike Blumenkrantz <michael.blumenkrantz@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9992>
Vertex Shader has a store_out lowering pass that converts gallium driver
locations in offsets inside the VPM.
One of the consequences is that these offsets are consecutives; that is,
if the VS stores VARYING_SLOT_VAR0.xyz and VARYING_SLOT_VAR1.xyzw, there
isn't a hole in the VPM offsets for the un-stored VARYING_SLOT_VAR0.w.
Thus we need to change how the VPM offset is computed in the Geometry
Shader when loading the inputs.
This bug is exposed by !9050.
v2 (Iago):
- Include explanatory comment.
- Use assert.
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10129>
`qpu.raddr_b` is an unsigned int, so it is always positive, even after
casting to signed int.
Fixes CID#1438117 "Operands don't affect result
(CONSTANT_EXPRESSION_RESULT)":
"result_independent_of_operands: (int)inst->qpu.raddr_b >= -16 is
always true regardless of the values of its operands. This occurs as
the logical first operand of "&&".
v2:
- Use signed pointers (Iago)
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10131>
This implements a NIR pass that groups together constant UBO loads
for the same UBO index in order of increasing offset when the distance
between them is small enough that it enables the "skip unifa write"
optimization.
This may increase register pressure because it can move UBO loads
earlier, so we also add a compiler strategy fallback to disable the
optimization if we need to drop thread count to compile the shader
with this optimization enabled.
total instructions in shared programs: 13557555 -> 13550300 (-0.05%)
instructions in affected programs: 814684 -> 807429 (-0.89%)
helped: 4485
HURT: 2377
Instructions are helped.
total uniforms in shared programs: 3777243 -> 3760990 (-0.43%)
uniforms in affected programs: 112554 -> 96301 (-14.44%)
helped: 7226
HURT: 36
Uniforms are helped.
total max-temps in shared programs: 2318133 -> 2333761 (0.67%)
max-temps in affected programs: 63230 -> 78858 (24.72%)
helped: 23
HURT: 3044
Max-temps are HURT.
total sfu-stalls in shared programs: 32245 -> 32567 (1.00%)
sfu-stalls in affected programs: 389 -> 711 (82.78%)
helped: 139
HURT: 451
Inconclusive result.
total inst-and-stalls in shared programs: 13589800 -> 13582867 (-0.05%)
inst-and-stalls in affected programs: 817738 -> 810805 (-0.85%)
helped: 4478
HURT: 2395
Inst-and-stalls are helped.
total nops in shared programs: 354365 -> 342202 (-3.43%)
nops in affected programs: 31000 -> 18837 (-39.24%)
helped: 4405
HURT: 265
Nops are helped.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10100>
This adds a minimum thread count parameter to each compilation strategy with
the intention to limit the minimum allowed thread count that can be used to
register allocate with that strategy.
For now all strategies allow the minimum thread count supported by the
hardware, but we will be using this infrastructure to impose a more
strict limit in an upcoming optimization.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10100>
This can be called outside a render pass so we should not expect to have
a job available. Also, we should not be emitting state here, instead we
should do in the pre-draw handler with all the other draw call state.
Fixes cases of crashes in RenderDoc when selecting elements in the
Event Browser.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10130>
first_component is an uint, and thus if it takes value 0 we can't know
if it is because writemask has its first bit to 1, or all bits to 0.
As we want to ensure that at least one bit is set, apply the assertion
in writemask.
Fixes CID#1472829 "Macro compares unsigned to 0 (NO_EFFECT)".
v2:
- Restore "first_component <= last_component" assertion (Iago)
Reviewed-by: Iago Toral Quiroga <itoral@igalia.com>
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10103>
The meson.build was unaware of transitive dependencies introduced by
Python imports.
Android still needs fixing. But I did not update the Android files lest
I break the build.
Ideally, we would fix this by using a Python runner that generates
a depfile, similar to how meson creates depfiles for C files by passing
flags -MD -MQ -MF to gcc. But this patch gets the job done, without
stalling on the ideal general solution, by manually tracking the Python
imports in new 'foo_depend_files' variables.
CC: mesa-stable@lists.freedesktop.org
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/1466>
A break/continue in a loop is typically emitted like this:
if (cond) {
break/continue;
} else {
}
If cond is uniform, we'll emit code for a uniform if statement and
that will emit a branch right before the if to jump directly to the
else (or the block after the else in this case, since the else is
empty) in case cond evaluates to false. This means we end up emitting
two consecutive branch instructions, one before the if and one for the
THEN block right after:
branch(!cond) -> jump to else (or after else) if cond is false
nop
nop
nop
branch -> unconditional jump to break/continue
nop
nop
nop
Instead, if we are in this scenario, we can do better by emitting the
conditional jump directly and avoiding the "jump to else" case:
branch(cond) -> jump to break/continue if cond is true
nop
nop
nop
We need to be careful when emitting the break/continue for the case
where all lanes are disabled to avoid infinite loops: if we have a
break we always want to take the jump, but we don't want to take it
if it is a continue.
total instructions in shared programs: 13563672 -> 13557348 (-0.05%)
instructions in affected programs: 348034 -> 341710 (-1.82%)
helped: 1158
HURT: 10
Instructions are helped.
total uniforms in shared programs: 3779137 -> 3777535 (-0.04%)
uniforms in affected programs: 90583 -> 88981 (-1.77%)
helped: 1169
HURT: 0
Uniforms are helped.
total max-temps in shared programs: 2317670 -> 2317575 (<.01%)
max-temps in affected programs: 1943 -> 1848 (-4.89%)
helped: 85
HURT: 4
Max-temps are helped.
total sfu-stalls in shared programs: 32247 -> 32247 (0.00%)
sfu-stalls in affected programs: 69 -> 69 (0.00%)
helped: 7
HURT: 9
Inconclusive result (value mean confidence interval includes 0).
total inst-and-stalls in shared programs: 13595919 -> 13589595 (-0.05%)
inst-and-stalls in affected programs: 350674 -> 344350 (-1.80%)
helped: 1154
HURT: 11
Inst-and-stalls are helped.
total nops in shared programs: 358202 -> 354325 (-1.08%)
nops in affected programs: 17367 -> 13490 (-22.32%)
helped: 1168
HURT: 1
Nops are helped.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9948>
Doing so in an x86 container via qemu was slow, and started failing
recently after updating to a newer qemu version.
This also results in smaller arm*_test* docker images, since we need to
install fewer Debian packages in them.
As a bonus, this turns some piglit tests from fail to pass (Or maybe
they'll turn out to be flakes? They've passed at least 3 times in a
row).
Reviewed-by: Eric Anholt <eric@anholt.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9955>
If we have an unconditional branch then we can try to fill up its
delay slots with the initial instructions of its successor block by
copying them into the delay slots and adjusting the branch offset to
skip the copied instructions.
total nops in shared programs: 365640 -> 364471 (-0.32%)
nops in affected programs: 15416 -> 14247 (-7.58%)
helped: 462
HURT: 0
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9918>
For this we do something similar to what we do with thrsw where we try to
move the branch instruction earlier so the previous instructions execute
in the delay slots of the branch.
Generally, we can do this with any instruction except:
- If the instruction reads a uniform: since our branches do as well and
uniforms come from an ordered FIFO stream.
- If the instruction writes flags, since our branch instruction will
probably read them.
- If the instruction is in the delay slots of another thread switch,
branch, or unifa write, which is disallowed.
total instructions in shared programs: 13648140 -> 13613972 (-0.25%)
instructions in affected programs: 2209552 -> 2175384 (-1.55%)
helped: 6765
HURT: 0
Instructions are helped.
total max-temps in shared programs: 2318687 -> 2318436 (-0.01%)
max-temps in affected programs: 5046 -> 4795 (-4.97%)
helped: 152
HURT: 0
Max-temps are helped.
total inst-and-stalls in shared programs: 13680494 -> 13646326 (-0.25%)
inst-and-stalls in affected programs: 2220394 -> 2186226 (-1.54%)
helped: 6765
HURT: 0
Inst-and-stalls are helped.
total nops in shared programs: 399818 -> 365640 (-8.55%)
nops in affected programs: 127311 -> 93133 (-26.85%)
helped: 6765
HURT: 0
Nops are helped.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9918>
Michel Dänzer