Multicore vs Safety 2010-01-0207

It is the beginning of a new age: multicore technology from the PC desktop market is now also hitting the automotive domain after several years of maturation. New microcontrollers with two or more main processing cores have been announced to provide the next step change in available computing power while keeping costs and power consumption at a reasonable level. These new multicore devices should not be confused with the specialized safety microcontrollers using two redundant cores to detect possible hardware failures which are already available. Nor should they be confused with the heterogeneous multicore solutions employing an additional support core to offload a single main processing core from real-time tasks (e.g. handling peripherals). On the contrary these new products are designed to significantly increase the available processing performance without running into the restrictions on maximum clock frequencies by offering two or more processing cores in a single devices, with each capable of running independent tasks in parallel.

Fundamental changes in software architecture will be required to take full advantage of the potential performance benefits of the (mostly) independent processing units. The architectural changes in the microcontroller hardware will also provide many additional possibilities to restructure automotive electronic systems based on the new multicore generation of these devices. Nevertheless, existing and upcoming safety standards must also be applied to these systems to address the opportunities and challenges that the new technology presents.

This paper will examine the impact of safety requirements when using multicore technology by analyzing which parts of current safety concepts can still be applied to multicore controllers and where new ways of ensuring electronics safety have to be developed. Finally it will explore how possible approaches for a multicore microcontroller could be realized together with the associated benefits and drawbacks.