The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Thread Cluster Memory Scheduling: Exploiting Differences in Memory Access Behavior
Abstract
In a modern chip-multiprocessor system, memory is a shared resource among multiple concurrently executing threads. The memory scheduling algorithm should resolve memory contention by arbitrating memory access in such a way that competing threads progress at a relatively fast and even pace, resulting in high system throughput and fairness. Previously proposed memory scheduling algorithms are predominantly optimized for only one of these objectives: no scheduling algorithm provides the best system throughput and best fairness at the same time. This paper presents a new memory scheduling algorithm that addresses system throughput and fairness separately with the goal of achieving the best of both. The main idea is to divide threads into two separate clusters and employ different memory request scheduling policies in each cluster. Our proposal, Thread Cluster Memory scheduling (TCM), dynamically groups threads with similar memory access behavior into either the latency-sensitive (memory-non-intensive) or the bandwidth-sensitive (memory-intensive) cluster. TCM introduces three major ideas for prioritization: 1) we prioritize the latency-sensitive cluster over the bandwidth-sensitive cluster to improve system throughput, 2) we introduce a ``niceness'' metric that captures a thread's propensity to interfere with other threads, 3) we use niceness to periodically shuffle the priority order of the threads in the bandwidth-sensitive cluster to provide fair access to each thread in a way that reduces inter-thread interference. On the one hand, prioritizing memory-non-intensive threads significantly improves system throughput without degrading fairness, because such ``light'' threads only use a small fraction of the total available memory bandwidth. On the other hand, shuffling the priority order of memory-intensive threads improves fairness because it ensures no thread is disproportionately slowed down or starved. We evaluate TCM on a wide variety of multiprogrammed workloads and compare its performance to four previously proposed scheduling algorithms, finding that TCM achieves both the best system throughput and fairness. Averaged over 96 workloads on a 24-core system with 4 memory channels, TCM improves system throughput and reduces maximum slowdown by 4.6%/38.6% compared to ATLAS (previous work providing the best system throughput) and 7.6%/4.6% compared to PAR-BS (previous work providing the best fairness).
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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
Pin: building customized program analysis tools with dynamic instrumentation
Luk, C.-K., Cohn, R., Muth, R., Patil, H., Klauser, A., Lowney, G., Wallace, S., Reddi, V. J., & Hazelwood, K. (2005) · ACM SIGPLAN Notices · doi:10.1145/1064978.1065034 · Cited by 3,180
Pin: building customized program analysis tools with dynamic instrumentation
Luk, C.-K., Cohn, R., Muth, R., Patil, H., Klauser, A., Lowney, G., Wallace, S., Reddi, V. J., & Hazelwood, K. (2005) · Proceedings of the 2005 ACM SIGPLAN conference on Programming language design and implementation · doi:10.1145/1065010.1065034 · Cited by 2,310
Symbiotic jobscheduling for a simultaneous mutlithreading processor
Snavely, A., & Tullsen, D. M. (2000) · ACM SIGPLAN Notices · doi:10.1145/356989.357011 · Cited by 535
Symbiotic jobscheduling for a simultaneous multithreaded processor
Snavely, A., & Tullsen, D. M. (2000) · Proceedings of the ninth international conference on Architectural support for programming languages and operating systems · doi:10.1145/378993.379244 · Cited by 484
ATLAS: A scalable and high-performance scheduling algorithm for multiple memory controllers
Kim, Y., Han, D., Mutlu, O., & Harchol-Balter, M. (2010) · HPCA - 16 2010 The Sixteenth International Symposium on High-Performance Computer Architecture · doi:10.1109/hpca.2010.5416658 · Cited by 430
Self-citationSelf-Optimizing Memory Controllers: A Reinforcement Learning Approach
Ipek, E., Mutlu, O., Martínez, J. F., & Caruana, R. (2008) · ACM SIGARCH Computer Architecture News · doi:10.1145/1394608.1382172 · Cited by 362
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-citationSelf-Optimizing Memory Controllers: A Reinforcement Learning Approach
Ipek, E., Mutlu, O., Martínez, J. F., & Caruana, R. (2008) · 2008 International Symposium on Computer Architecture · doi:10.1109/isca.2008.21 · Cited by 278
Self-citationAccelerating critical section execution with asymmetric multi-core architectures
Suleman, M. A., Mutlu, O., Qureshi, M. K., & Patt, Y. N. (2009) · Proceedings of the 14th international conference on Architectural support for programming languages and operating systems · doi:10.1145/1508244.1508274 · Cited by 270
Self-citationBhattacharjee, A., & Martonosi, M. (2009) · Proceedings of the 36th annual international symposium on Computer architecture · doi:10.1145/1555754.1555792 · Cited by 192
Adaptive History-Based Memory Schedulers
Hur, I., & Lin, C. (2005) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1109/micro.2004.4 · Cited by 121
Cited by
RowClone: fast and energy-efficient in-DRAM bulk data copy and initialization
Seshadri, V., Kim, Y., Fallin, C., Lee, D., Ausavarungnirun, R., Pekhimenko, G., Luo, Y., Mutlu, O., Gibbons, P. B., Kozuch, M. A., et al. (2013) · Proceedings of the 46th Annual IEEE/ACM International Symposium on Microarchitecture · doi:10.1145/2540708.2540725 · Cited by 337
Self-citationGoogle Workloads for Consumer Devices: Mitigating Data Movement Bottlenecks
Boroumand, A., Ghose, S., Kim, Y., Ausavarungnirun, R., Shiu, E., Thakur, R., Kim, D., Kuusela, A., Knies, A., Ranganathan, P., et al. (2018) · Proceedings of the Twenty-Third International Conference on Architectural Support for Programming Languages and Operating Systems · doi:10.1145/3173162.3173177 · Cited by 273
Self-citationTiered-latency DRAM: A low latency and low cost DRAM architecture
Lee, D., Kim, Y., Seshadri, V., Liu, J., Subramanian, L., & Mutlu, O. (2013) · 2013 IEEE 19th International Symposium on High Performance Computer Architecture (HPCA) · doi:10.1109/hpca.2013.6522354 · Cited by 263
Self-citationA case for exploiting subarray-level parallelism (SALP) in DRAM
Kim, Y., Seshadri, V., Lee, D., Liu, J., & Mutlu, O. (2012) · ACM SIGARCH Computer Architecture News · doi:10.1145/2366231.2337202 · Cited by 259
Self-citationMemory scaling: A systems architecture perspective
Mutlu, O. (2013) · 2013 5th IEEE International Memory Workshop · doi:10.1109/imw.2013.6582088 · Cited by 256
Self-citation
Metadata
- Authors
- Kim, Y., Papamichael, M., Mutlu, O., & Harchol-Balter, M.
- Venue
- 2010 43rd Annual IEEE/ACM International Symposium on Microarchitecture
- Publisher
- IEEE
- Published
- 2010-12
- Pages
- 65-76
- ISSN
- 1072-4451 (ISSN-L)
- OpenAlex
- W2159908132
- Cited by
- 408
- References
- 12
- FWCI
- 17.13
- Type
- conference paper
- Language
- en
- Open access
- closed
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.