Instruction Level Parallelism (ILP) machines, such as Very Long Instruction Word (VLIW) architectures, and customised architectures are two para-digms that are used to increase the performance of processors. While a VLIW machine has multiple functional units, a customised processor is equipped with Application-specific Functional Units (AFUs). Customisation has been proved beneficial on single issue machines, but its effect on multiple issue machines remains unanswered. Is a VLIW machine powerful enough to nullify the benefit of customisation? Or are the two benefits orthogonal and can be exploited together? In this paper, we answer positively to the latter question. We experimentally prove that insertion of automatically identified AFUs can improve performance of a VLIW architecture, and allow the designer of ILP processor to trade-off either issue-width or register file size. We have customised the Trimaran architecture and toolchain framework to model AFUs accurately and discuss the challenges of adding instruction-set extension support to a legacy toolchain.