This paper makes a case for a new cross-layer interface, Expressive Memory (XMem), to communicate higher-level program semantics from the application to the system software and hardware architecture. XMem provides (i) a flexible and extensible abstraction, called an Atom, enabling the application to express key program semantics in terms of how the program accesses data and the attributes of the data itself, and (ii) new cross-layer interfaces to make the expressed higher-level information available to the underlying OS and architecture. By providing key information that is otherwise unavailable, XMem exposes a new, rich view of the program data to the OS and the different architectural components that optimize memory system performance (e.g., caches, memory controllers). By bridging the semantic gap between the application and the underlying memory resources, XMem provides two key benefits. First, it enables architectural/system-level techniques to leverage key program semantics that are challenging to predict or infer. Second, it improves the efficacy and portability of software optimizations by alleviating the need to tune code for specific hardware resources (e.g., cache space). While XMem is designed to enhance and enable a wide range of memory optimizations, we demonstrate the benefits of XMem using two use cases: (i) improving the performance portability of software-based cache optimization by expressing the semantics of data locality in the optimization and (ii) improving the performance of OS-based page placement in DRAM by leveraging the semantics of data structures and their access properties.

In this paper we consider the case of a network of Electronic Control Units (ECUs) connected through a Flex Ray bus in the automotive domain. Multiple distributed applications can run on this underlying architecture, each partitioned into tasks that are mapped on different ECUs. These applications can often be executed in different functional modes with different requirements on the communication resources in terms of data size and sampling period. Moreover, new applications can be deployed on to the ECUs at run-time. To efficiently utilize the communication resources and accommodate new applications, a certain flexibility in reallocation of the resource is necessary. However, the Flex Ray bus requires static configuration of schedules and data mapping in order to guarantee a more deterministic system behavior, allowing little room for flexibility. In order to address this problem, we propose a reconfigurable communication middleware that lies between the application layer and the communication controller layer, which maps messages onto Flex Ray schedules, and can be reconfigured at runtime. The configuration is synthesized and deployed online, allowing a certain reallocation of communication resources to applications. In this paper, we describe the design of such a reconfigurable communication middleware and demonstrate its function with an implementation using industry-strength Flex Ray design tools.