Scalability of operating system kernels is important especially for real-time systems. The existing real-time kernels, however are made scalable by providing only basic functionalities; thus they often sacrifice the capability of hardware platforms. We introduce the separation of abstractions into software functionalities and hardware resources and their implementation by a scalable kernel architecture. The separation of abstractions into software and hardware are parts enables the provision of rich abstractions. Rich abstractions make it possible to exploit the capability of higher-end hardware platforms, and the separation makes it possible that their software functionalities are available also on low-end platforms. Our scalable kernel can scale up its implementation incrementally as the capability of hardware platforms scales up. In this paper, we describe the design and implementation of a scalable real-time kernel based on that architecture model, and show the experimental results of a prototype implementation.