aco: fix WQM coalescing

get_reg_specified() doesn't handle special registers like SCC.
Fixes: a5fc96b533418dc2d68f17f3f19ac5f82d59b978 ('aco: coalesce parallelcopies during register allocation')

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/5036>

diff --git a/src/amd/compiler/aco_register_allocation.cpp b/src/amd/compiler/aco_register_allocation.cpp
index a5c8ba7..613e55f 100644 (file)
--- a/src/amd/compiler/aco_register_allocation.cpp
+++ b/src/amd/compiler/aco_register_allocation.cpp
@@ -1864,7 +1864,9 @@ void register_allocation(Program *program, std::vector<TempSet>& live_out_per_bl
                   definition.setFixed(reg);
             } else if (instr->opcode == aco_opcode::p_wqm || instr->opcode == aco_opcode::p_parallelcopy) {
                PhysReg reg = instr->operands[i].physReg();
-               if (get_reg_specified(ctx, register_file, definition.regClass(), parallelcopy, instr, reg))
+               if (instr->operands[i].isTemp() &&
+                   instr->operands[i].getTemp().type() == definition.getTemp().type() &&
+                   !register_file.test(reg, definition.bytes()))
                   definition.setFixed(reg);
             } else if (instr->opcode == aco_opcode::p_extract_vector) {
                PhysReg reg;