Bounding memory interference delay in COTS-based multi-core systems
Open accessThe DOI matches its Crossref record; 21 of the 21 references it cites were found in a registry or an index.
Abstract
In commercial-off-the-shelf (COTS) multi-core systems, a task running on one core can be delayed by other tasks running simultaneously on other cores due to interference in the shared DRAM main memory. Such memory interference delay can be large and highly variable, thereby posing a significant challenge for the design of predictable real-time systems. In this paper, we present techniques to provide a tight upper bound on the worst-case memory interference in a COTS-based multi-core system. We explicitly model the major resources in the DRAM system, including banks, buses and the memory controller. By considering their timing characteristics, we analyze the worst-case memory interference delay imposed on a task by other tasks running in parallel. To the best of our knowledge, this is the first work bounding the request re-ordering effect of COTS memory controllers. Our work also enables the quantification of the extent by which memory interference can be reduced by partitioning DRAM banks. We evaluate our approach on a commodity multi-core platform running Linux/RK. Experimental results show that our approach provides an upper bound very close to our measured worst-case interference.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Scheduling algorithms for multiprogramming in a hard-real-time environment
Liu, C. L., & Layland, J. W. (1973) · Journal of the ACM · doi:10.1145/321738.321743 · Cited by 8,433 · cited 1×
“We do not make any assumptions on the priority assignment schemes, so any fixed-priority assignment can be used, such as Rate Monotonic [21].”
MethodThe PARSEC benchmark suite: characterization and architectural implications
Bienia, C., Kumar, S., Singh, J. P., & Li, K. (2008) · Proceedings of the 17th international conference on Parallel architectures and compilation techniques · doi:10.1145/1454115.1454128 · Cited by 3,444 · cited 1×
“We use the eleven PARSEC benchmarks [8] and the two types of synthetic tasks (memory-intensive and memory-nonintensive) for our experiment.”
MethodScheduling Algorithms for Multiprogramming in a Hard-Real-Time Environment
LIU, C. L., & LAYLAND, J. W. (2002) · Readings in Hardware/Software Co-Design · doi:10.1016/b978-155860702-6/50016-8 · Cited by 3,233
Finding Response Times in a Real-Time System
Joseph, M. (1986) · The Computer Journal · doi:10.1093/comjnl/29.5.390 · Cited by 1,169 · cited 1×
“Based on the analyses of the two approaches, the iterative response time test [14] is extended as follows to incorporate the memory interference delay:”
MethodParallelism-Aware Batch Scheduling: Enhancing both Performance and Fairness of Shared DRAM Systems
Mutlu, O., & Moscibroda, T. (2008) · ACM SIGARCH Computer Architecture News · doi:10.1145/1394608.1382128 · Cited by 516 · cited 1×
“, [28, 19]).”
Self-citationThread Cluster Memory Scheduling: Exploiting Differences in Memory Access Behavior
Kim, Y., Papamichael, M., Mutlu, O., & Harchol-Balter, M. (2010) · 2010 43rd Annual IEEE/ACM International Symposium on Microarchitecture · doi:10.1109/micro.2010.51 · Cited by 408 · cited 1×
“, [28, 19]).”
Self-citationParallelism-Aware Batch Scheduling: Enhancing both Performance and Fairness of Shared DRAM Systems
Mutlu, O., & Moscibroda, T. (2008) · 2008 International Symposium on Computer Architecture · doi:10.1109/isca.2008.7 · Cited by 345
Self-citationStall-Time Fair Memory Access Scheduling for Chip Multiprocessors
Mutlu, O., & Moscibroda, T. (2007) · 40th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO 2007) · doi:10.1109/micro.2007.21 · Cited by 327
Self-citationResource kernels: a resource-centric approach to real-time and multimedia systems:
Rajkumar, R., Juvva, K., Molano, A., & Oikawa, S. (1997) · SPIE Proceedings · doi:10.1117/12.298417 · Cited by 317 · cited 5×
“We used the latest version of Linux/RK [30, 33] for software cache and bank partitioning [16, 39].9 Cache partitioning divides the shared L3 cache of the processor into 32 partitions, and bank partitioning divides the DRAM banks into 16 partitions (1 DRAM bank per partition).”
MethodInfluentialSelf-citationMemory Hierarchies, Pipelines, and Buses for Future Architectures in Time-Critical Embedded Systems
Wilhelm, R., Grund, D., Reineke, J., Schlickling, M., Pister, M., & Ferdinand, C. (2009) · IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems · doi:10.1109/tcad.2009.2013287 · Cited by 285 · cited 1×
“In this paper, we assume that each core has a fully timing-compositional architecture as described in [40].”
Method
Cited by
Scheduling Techniques for GPU Architectures with Processing-In-Memory Capabilities
Pattnaik, A., Tang, X., Jog, A., Kayiran, O., Mishra, A. K., Kandemir, M. T., Mutlu, O., & Das, C. R. (2016) · Proceedings of the 2016 International Conference on Parallel Architectures and Compilation · doi:10.1145/2967938.2967940 · Cited by 186
“The average latency is higher due to significant contention observed in the DRAM system [10, 26,54,57,59–61,63,75,76,78,79,100–102,107,108].”
BackgroundSelf-citationPipelined Data-Parallel CPU/GPU Scheduling for Multi-DNN Real-Time Inference
Xiang, Y., & Kim, H. (2019) · 2019 IEEE Real-Time Systems Symposium (RTSS) · doi:10.1109/rtss46320.2019.00042 · Cited by 159
“Temporal interference caused by shared memory resources, such as caches, DRAM, and memory buses, has been considered a serious problem in multi-core real-time systems [6, 24, 33, 42, 44, 47].”
BackgroundSelf-citation
Metadata
- Authors
- Kim, H., de Niz, D., Andersson, B., Klein, M., Mutlu, O., & Rajkumar, R.
- Venue
- 2014 IEEE 19th Real-Time and Embedded Technology and Applications Symposium (RTAS)
- Publisher
- IEEE
- Published
- 2014-04
- Pages
- 145-154
- ISSN
- 1080-1812 (ISSN-L)
- OpenAlex
- W1981588964
- Cited by
- 210
- References
- 21
- FWCI
- 24.71
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.