We weren't doing much motion in nir-to-tgsi because we considered all our
lowered load-ubos as unmovable.
softpipe shader-db:
total temps in shared programs: 563942 -> 563136 (-0.14%)
temps in affected programs: 9833 -> 9027 (-8.20%)
r300 shader-db:
instructions in affected programs: 22858 -> 23575 (3.14%)
temps in affected programs: 2039 -> 1813 (-11.08%)
(NIR had given r300 -19% instrs for +40% temps, so this feels like a
worthwhile trade back).
Reivewed-by: Jesse Natalie <jenatali@microsoft.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14138>
Can uncover opportunities to move other instructions. This can increase
register usage, but that doesn't seem to actually happen.
This optimizes a pattern of a load_per_vertex_input followed by several
moves and then a store_output in a different block.
v2: add nir_move_copies to make it optional
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Acked-by: Jason Ekstrand <jason@jlekstrand.net> (v1)
Acked-by: Rob Clark <robdclark@chromium.org>
Tested-by: Marge Bot <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/2420>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/merge_requests/2420>
Previously, this could have made the resource divergent in code like
that which is genereated by nir_lower_non_uniform_access.
Fixes: da8ed68a ('nir: replace nir_move_load_const() with nir_opt_sink()')
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Previously, for code like:
loop {
loop {
a = load_ubo()
}
use(a)
}
adjust_block_for_loops() would return the block before the first loop.
Now we compute the range of allowed blocks and then walk the dominance
tree directly, guaranteeing directly that we always choose a block that
dominates all the uses and is dominated by the definition.
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
This is mostly the same as nir_move_load_const() but can also move
undef instructions, comparisons and some intrinsics (being careful with
loops).
v2: actually delete nir_move_load_const.c
v3: fix nir_opt_sink() usage in freedreno
v3: update Makefile.sources
v4: replace get_move_def with nir_can_move_instr and nir_instr_ssa_def
v4: handle if uses
v4: fix handling of nested loops
v5: re-write adjust_block_for_loops
v5: re-write setting of use_block for if uses
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Co-authored-by: Daniel Schürmann <daniel@schuermann.dev>
Reviewed-by: Eric Anholt <eric@anholt.net>
