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>
nir_move_load_ubo = (1 << 1),
nir_move_load_input = (1 << 2),
nir_move_comparisons = (1 << 3),
+ nir_move_copies = (1 << 4),
} nir_move_options;
bool nir_can_move_instr(nir_instr *instr, nir_move_options options);
return true;
}
+ if ((options & nir_move_copies) && instr->type == nir_instr_type_alu &&
+ nir_instr_as_alu(instr)->op == nir_op_mov) {
+ return true;
+ }
+
if ((options & nir_move_comparisons) && instr->type == nir_instr_type_alu &&
nir_alu_instr_is_comparison(nir_instr_as_alu(instr))) {
return true;