Temp size = emit_extract_vector(ctx, desc, 2, s1);
Temp size_div3 = bld.vop3(aco_opcode::v_mul_hi_u32, bld.def(v1), bld.copy(bld.def(v1), Operand(0xaaaaaaabu)), size);
- size_div3 = bld.sop2(aco_opcode::s_lshr_b32, bld.def(s1), bld.as_uniform(size_div3), Operand(1u));
+ size_div3 = bld.sop2(aco_opcode::s_lshr_b32, bld.def(s1), bld.def(s1, scc), bld.as_uniform(size_div3), Operand(1u));
Temp stride = emit_extract_vector(ctx, desc, 1, s1);
stride = bld.sop2(aco_opcode::s_bfe_u32, bld.def(s1), bld.def(s1, scc), stride, Operand((5u << 16) | 16u));