Code generation for complex integer loops within the context of a VLIW architecture, has to date, been handled by several disparate methodologies. We provide an empirical study to characterize what a typical complex integer loop is and propose a general solution that optimally modifies the key control dependencies in common integer loops. This single algorithm, integrates several software techniques (assuming key architectural features) in order to provide for varying degrees of nested complex control flow. A number of techniques, including loop peeling, loop unrolling, software pipelining, if-conversion, and procedure inlining are combined cohesively to make the best transformation decisions, for a typical integer loop, before scheduling and register allocation. Optimal fusion and distribution decisions are assumed.