Although multi-core architectures with a large number of cores ("many-cores'') are considered the future of computing systems, there are currently few practical tools to quickly explore both their design and general program scalability. In this paper, we present \emph{SiMany}, a discrete-event-based many-core simulator able to support more than a thousand cores while being orders of magnitude faster than existing flexible approaches. One of the difficult challenges for a reasonably realistic many-core simulation is to model faithfully the potentially high concurrency a program can exhibit. SiMany uses a novel virtual time synchronization technique, called \emph{spatial synchronization}, to achieve this goal in a completely \emph{local} and \emph{distributed} fashion, which diminishes interactions and preserves locality. Compared to previous simulators, it raises the level of \emph{abstraction} by focusing on modeling concurrent interactions between cores, which enables fast coarse comparisons of high-level architecture design choices and parallel programs performance. Sequential pieces of code are executed \emph{natively} for maximal speed. We exercise the simulator with a set of dwarf-like task-based benchmarks with dynamic control flow and irregular data structures. Scalability results are validated through comparison with a cycle-level simulator up to 64 cores. They are also shown consistent with well-known benchmark characteristics. We finally demonstrate how SiMany can be used to efficiently compare the benchmarks' behavior over a wide range of architectural organizations, such as polymorphic architectures and network of clusters.