To decide which variables to spill, we must use the distances at the
beginning of the loop-header, and not the distances at the end of the
loop-preheader. The difference are that the former includes phis which are
viable to be spilled as opposed to the phi operands which would be reloaded
by add_coupling_code(), ending up in potentially too high register pressure
before the loop.
Totals from 206 (0.15% of 136546) affected shaders (Raven):
SpillSGPRs: 5154 -> 5000 (-2.99%)
CodeSize: 3654072 -> 3647184 (-0.19%); split: -0.19%, +0.00%
Instrs: 701482 -> 700526 (-0.14%); split: -0.14%, +0.00%
Latency: 40988780 -> 40872506 (-0.28%); split: -0.29%, +0.00%
InvThroughput: 20364560 -> 20306006 (-0.29%)
SClause: 20192 -> 20198 (+0.03%)
Copies: 77732 -> 77688 (-0.06%); split: -0.08%, +0.03%
Branches: 24204 -> 24050 (-0.64%)
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9196>
This also fixes some hypothetical issue for loops without phis
and for loops with higher register pressure at the end of the
loop preheader.
No fossil-db changes.
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9196>
This handles the case of
exec = p_linear_phi %a, %b
where %a or %b might have been spilled.
By directly reloading these variables into the exec mask register,
we can avoid additional CSSA parallelcopies.
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9196>
This patch delays the calculation of GPR limits in order to
precisely incorporate extra registers (VCC etc.) and shared VGPRs.
Additionally, the allocation granularity is used to set the config.
This has some effect on the reported SGPR stats.
Totals (Navi10):
SGPRs: 6971787 -> 17753642 (+154.65%)
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8921>
The small DCE of the spiller only removes the original instructions
of rematerialized variables in case they are unused. If a variable
has been renamed, it cannot match any original instruction anymore.
Thus, the lookup is then unnecessary and can be omitted.
No fossil-db changes.
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8055>
A future change will switch the liveness sets to bit vectors, which don't
contain regclass information.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/6733>
SMEM does the addition with 64-bits, not 32. So if the original code
relied on wrapping around (for example, for subtraction), it would break.
Apparently swizzled MUBUF accesses also have issues with combining
additions that could overflow. Normal MUBUF accesses seem fine.
fossil-db (Navi):
Totals from 27219 (20.02% of 135946) affected shaders:
CodeSize: 128303256 -> 131062756 (+2.15%); split: -0.00%, +2.15%
Instrs: 24818911 -> 25280558 (+1.86%); split: -0.01%, +1.87%
VMEM: 162311926 -> 177226874 (+9.19%); split: +9.36%, -0.17%
SMEM: 18182559 -> 20218734 (+11.20%); split: +11.53%, -0.34%
VClause: 423635 -> 424398 (+0.18%); split: -0.02%, +0.20%
SClause: 865384 -> 1104986 (+27.69%); split: -0.00%, +27.69%
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/2748
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/2720>
This won't add interferences between spill ids of different types and will
exit early if there's already an interference.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5805>
I don't think this is much of an optimization in the typical case, but for
very complex shaders this should work much better.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5805>
It looks like the attempt to fix this in 1e791e51a6 was incomplete.
This fixes crashes with Devil May Cry 5 with a debug build.
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5828>
For all VMEM instructions, the resource constant is now
in operands[0]. For MIMG instructions, the sampler shares
operands[1] with write data in case this instruction writes memory.
Moving the VADDR to be the last operand for MIMG is the first step to
support Navi NSA encoding.
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3602>
process_block() will use this to determine the register demand of the
before the current instruction. Previously, it was filled with zeroes
which could result in process_block() only using the register demand
of after the current instruction.
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3257>
Loops without continues create header blocks with only 1 predecessor.
CC: <mesa-stable@lists.freedesktop.org>
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3257>
A shader might require vgpr spilling but not require sgpr spilling. In
that case, the spiller lowers the sgpr target by 5 which could mean sgpr
spilling is then required. Then the vgpr target has to be lowered to make
space for the linear vgprs. Previously, space wasn't make for the linear
vgprs.
Found while testing the spiller on the pipeline-db with a lowered limit
Fixes: a7ff1bb5b9
('aco: simplify calculation of target register pressure when spilling')
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/3257>
