diff --git a/src/amd/compiler/aco_optimizer.cpp b/src/amd/compiler/aco_optimizer.cpp
index 5bb52baf177..311b8ad4d04 100644
--- a/src/amd/compiler/aco_optimizer.cpp
+++ b/src/amd/compiler/aco_optimizer.cpp
@@ -3993,15 +3993,18 @@ combine_output_conversion(opt_ctx& ctx, aco_ptr<Instruction>& instr)
       return false;
    Instruction* conv = def_info.instr;
 
-   if (!can_use_mad_mix(ctx, instr) || ctx.uses[instr->definitions[0].tempId()] != 1)
-      return false;
-
-   if (!ctx.uses[conv->definitions[0].tempId()])
+   if (!ctx.uses[conv->definitions[0].tempId()] || ctx.uses[instr->definitions[0].tempId()] != 1)
       return false;
 
    if (conv->usesModifiers())
       return false;
 
+   if (instr->opcode == aco_opcode::v_interp_p2_f32_inreg)
+      interp_p2_f32_inreg_to_fma_dpp(instr);
+
+   if (!can_use_mad_mix(ctx, instr))
+      return false;
+
    if (!instr->isVOP3P())
       to_mad_mix(ctx, instr);
 
diff --git a/src/amd/compiler/tests/test_optimizer.cpp b/src/amd/compiler/tests/test_optimizer.cpp
index 04a710d6bfa..f09b94cc43b 100644
--- a/src/amd/compiler/tests/test_optimizer.cpp
+++ b/src/amd/compiler/tests/test_optimizer.cpp
@@ -2225,5 +2225,11 @@ BEGIN_TEST(optimize.vinterp_inreg_output_modifiers)
    tmp = bld.vop2(aco_opcode::v_mul_f16, bld.def(v2b), Operand::c16(0x4000u), tmp);
    writeout(3, tmp);
 
+   //! v2b: %res4 = v_fma_mixlo_f16 %c, %b, %a quad_perm:[2,2,2,2] fi
+   //! p_unit_test 4, %res4
+   tmp = bld.vinterp_inreg(aco_opcode::v_interp_p2_f32_inreg, bld.def(v1), inputs[2], inputs[1],
+                           inputs[0]);
+   writeout(4, f2f16(tmp));
+
    finish_opt_test();
 END_TEST