Multicore architecture brings a significant challenge in designing critical real-time systems because of timing variability caused by concurrent accesses to shared memory. We propose a memory bandwidth regulated system architecture and a novel analysis method to address this challenge. In the proposed architecture, each core's memory access rate is regulated in a globally coordinated manner. The architecture allows system designers to control the system to satisfy desired real-time performance. The proposed analysis method provides a way to calculate worst case response time of each real-time task independently from other activities on other cores; it only depends on the task under analysis, the assigned bandwidth, and the number of cores in the system. We believe this independence is critical to enable modular certification of critical real-time systems. We implement the proposed system model on the gem5 architecture simulator. We evaluate the proposed analysis method by comparing the computed runtime with the measured runtime on the modified simulator. We show that the analysis method provides reasonable upper-bounds based on the SPEC2006 benchmark suite.

We introduce ROC, a Rank-switching, Open-row Controller for Double Data Rate Dynamic RAM (DDR DRAM). ROC is optimized for mixed-criticality multicore systems using modern DDR devices: compared to existing real-time memory controllers, it provides significantly lower worst case latency bounds for hard real-time tasks and supports throughput-oriented optimizations for soft real-time applications. The key to improved performance is an innovative rank-switching mechanism which hides the latency of write-read transitions in DRAM devices without requiring unpredictable request reordering. We further employ open row policy to take advantage of the data caching mechanism (row buffering) in each device. ROC provides complete timing isolation between hard and soft tasks and allows for compositional timing analysis over the number of cores and memory ranks in the system. We implemented and synthesized the ROC back end in Verilog RTL, and evaluated its performance on both synthetic tasks and a set of representative benchmarks.

DRAM consists of multiple resources called banks that can be accessed in parallel and independently maintain state information. In Commercial Off-The-Shelf (COTS) multicore platforms, banks are typically shared among all cores, even though programs running on the cores do not share memory space. In this situation, memory performance is highly unpredictable due to contention in the shared banks. In this paper, we propose PALLOC, a DRAM bank-aware memory allocator which exploits the page-based virtual memory system to allocate memory pages of each application to specific banks. With PALLOC, we can dynamically partition banks to avoid bank sharing among cores, thereby improving isolation on COTS multicore platforms without requiring any special hardware support. We performed an extensive set of experiments to investigate the performance impact of DRAM bank partitioning on two COTS multicore platforms with a set of synthetic and SPEC2006 benchmarks. Our evaluation results demonstrate that DRAM bank partitioning significantly improves isolation and real-time performance.

As multi-core systems are becoming more popular in real-time embedded systems, strict timing requirements for accessing shared resources must be met. In particular, a detailed latency analysis for Double Data Rate Dynamic RAM (DDR DRAM) is highly desirable. Several researchers have proposed predictable memory controllers to provide guaranteed memory access latency. However, the performance of such controllers sharply decreases as DDR devices become faster and the width of memory buses is increased. In this paper, we present a novel, composable worst case analysis for DDR DRAM that provides improved latency bounds compared to existing works by explicitly modeling the DRAM state. In particular, our approach scales better with increasing number of requestors and memory speed. Benchmark evaluations show up to 62% improvement in worst case task execution time compared to a competing predictable memory controller for a system with 8 requestors.