Efficient and effective simulation of memory maps for system-on-chip

The design of complex system-on-chip (SOC) requires new methods and tools for the optimization of embedded software which is executed on ever more complex hardware architectures. The tuning of the memory subsystem is particularly difficult due to the many design parameters which are involved and the long time which is required to simulate different design configurations. We propose a very effective mechanism for the simulation of generic memory maps on architectures with instruction and/or data cache memory. An important characteristic of our implementation is its large flexibility: any memory map and any cache configuration can be simulated without the need to modify or to recompile the application code. We implemented such mechanism in our ISA retargetable environment and we showed that it loosely impacts the simulation performance.