An approach to analyze the compatibility of real-time multi-task applications with various combinations of scheduling modes and protocols of access to shared resources when run on multi-core platforms. The approach is based on the recently introduced notion of application density derived from estimation of application feasibility for various values of the processor performance. The software architecture of a relatively simple simulation tool for estimation of the task response time (and therefore, application feasibility) is described, which provides more exact data compared to the known analytical methods when they are applicable. Results of running this tool on a number of benchmarks, including balanced Liu-Layland configurations, are presented along with their analysis and interpretation. The suggested approach allows to indentify an optimal combination of the scheduling mode and access protocol for the given application structure.