A Requests Bundling DRAM Controller for Mixed-Criticality Systems

We design a novel DRAM controller that bundles and executes memory requests of hard real-time applications in consecutive rounds based on their type to reduce read/write switching delay. At the same time, our controller provides a configurable, guaranteed bandwidth for soft real-time requests. We show that there is a fundamental trade-off between the latency guarantee for hard real-time requests and the bandwidth provided to soft requests. Finally, we compare our approach analytically and experimentally with the current state-of-theart real-time memory controller for single-rank DRAM devices, which applies type reordering at the level of DRAM commands rather than requests. Our evaluation shows that for tasks exhibiting average row hit ratios, or for which computing a row hit guarantee might be difficult, our controller provides both smaller guaranteed latency and larger bandwidth.

[1]  Kees G. W. Goossens,et al.  Predator: A predictable SDRAM memory controller , 2007, 2007 5th IEEE/ACM/IFIP International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS).

[2]  William J. Dally,et al.  Memory access scheduling , 2000, Proceedings of 27th International Symposium on Computer Architecture (IEEE Cat. No.RS00201).

[3]  Jason A. Poovey Characterization of the EEMBC Benchmark Suite , 2007 .

[4]  Selma Saidi,et al.  A mixed critical memory controller using bank privatization and fixed priority scheduling , 2014, 2014 IEEE 20th International Conference on Embedded and Real-Time Computing Systems and Applications.

[5]  Francisco J. Cazorla,et al.  An Analyzable Memory Controller for Hard Real-Time CMPs , 2009, IEEE Embedded Systems Letters.

[6]  Francisco J. Cazorla,et al.  A Dual-Criticality Memory Controller (DCmc): Proposal and Evaluation of a Space Case Study , 2014, 2014 IEEE Real-Time Systems Symposium.

[7]  Kees G. W. Goossens,et al.  Architecture and optimal configuration of a real-time multi-channel memory controller , 2013, 2013 Design, Automation & Test in Europe Conference & Exhibition (DATE).

[8]  Rodolfo Pellizzoni,et al.  Worst Case Analysis of DRAM Latency in Multi-requestor Systems , 2013, 2013 IEEE 34th Real-Time Systems Symposium.

[9]  Hiren D. Patel,et al.  A Comparative Study of Predictable DRAM Controllers , 2018, ACM Trans. Embed. Comput. Syst..

[10]  Rolf Ernst,et al.  Minimizing DRAM Rank Switching Overhead for Improved Timing Bounds and Performance , 2016, 2016 28th Euromicro Conference on Real-Time Systems (ECRTS).

[11]  Pascal Sainrat,et al.  Accurate analysis of memory latencies for WCET estimation , 2008 .

[12]  Jan Reineke,et al.  Memory Hierarchies, Pipelines, and Buses for Future Architectures in Time-Critical Embedded Systems , 2009, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[13]  Rodolfo Pellizzoni,et al.  A Rank-Switching, Open-Row DRAM Controller for Time-Predictable Systems , 2014, 2014 26th Euromicro Conference on Real-Time Systems.

[14]  Kees G. W. Goossens,et al.  Dynamic Command Scheduling for Real-Time Memory Controllers , 2014, 2014 26th Euromicro Conference on Real-Time Systems.

[15]  Hiren D. Patel,et al.  A framework for scheduling DRAM memory accesses for multi-core mixed-time critical systems , 2015, 21st IEEE Real-Time and Embedded Technology and Applications Symposium.

[16]  Heechul Yun,et al.  MEDUSA: A Predictable and High-Performance DRAM Controller for Multicore Based Embedded Systems , 2015, 2015 IEEE 3rd International Conference on Cyber-Physical Systems, Networks, and Applications.

[17]  Rolf Ernst,et al.  Improved DRAM Timing Bounds for Real-Time DRAM Controllers with Read/Write Bundling , 2015, 2015 IEEE Real-Time Systems Symposium.