More Like this

1. FReaC Cache: Folded-logic Reconfigurable Computing in the Last Level Cache

   https://doi.org/10.1109/MICRO50266.2020.00021  

   Dhar, Ashutosh ; Wang, Xiaohao ; Franke, Hubertus ; Xiong, Jinjun ; Huang, Jian ; Hwu, Wen-mei ; Kim, Nam Sung ; Chen, Deming ( October 2020 , IEEE/ACM International Symposium on Microarchitecture (MICRO))
2. Logging in persistent memory: to cache, or not to cache?

   https://doi.org/10.1145/3132402.3132429  

   Li, Mengjie ; Ogleari, Matheus ; Zhao, Jishen ( January 2017 , The International Symposium on Memory Systems)
3. RL-Cache: Learning-Based Cache Admission for Content Delivery

   https://doi.org/10.1109/JSAC.2020.3000415  

   Kirilin, Vadim ; Sundarrajan, Aditya ; Gorinsky, Sergey ; Sitaraman, Ramesh K. ( June 2020 , IEEE Journal on Selected Areas in Communications)

   Content delivery networks (CDNs) distribute much of the Internet content by caching and serving the objects requested by users. A major goal of a CDN is to maximize the hit rates of its caches, thereby enabling faster content downloads to the users. Content caching involves two components: an admission algorithm to decide whether to cache an object and an eviction algorithm to determine which object to evict from the cache when it is full. In this paper, we focus on cache admission and propose a novel algorithm called RL-Cache that uses model-free reinforcement learning (RL) to decide whether or not to admit a requested object into the CDN’s cache. Unlike prior approaches that use a small set of criteria for decision making, RL-Cache weights a large set of features that include the object size, recency, and frequency of access. We develop a publicly available implementation of RL-Cache and perform an evaluation using production traces for the image, video, and web traffic classes from Akamai’s CDN. The evaluation shows that RL-Cache improves the hit rate in comparison with the state of the art and imposes only a modest resource overhead on the CDN servers. Further, RL-Cache is robust enough that itmore »can be trained in one location and executed on request traces of the same or different traffic classes in other locations of the same geographic region. The paper also reports extensive analyses of the RL-Cache sensitivity to its features and hyperparameter values. The analyses validate the made design choices and reveal interesting insights into the RL-Cache behavior.« less
4. RL-Cache: Learning-Based Cache Admission for Content Delivery

   https://doi.org/10.1145/3341216.3342214  

   Kirilin, Vadim ; Sundarrajan, Aditya ; Gorinsky, Sergey ; Sitaraman, Ramesh K. ( January 2019 , NetAI'19: Proceedings of the 2019 Workshop on Network Meets AI & ML)

   Content delivery networks (CDNs) distribute much of the Internet content by caching and serving the objects requested by users. A major goal of a CDN is to maximize the hit rates of its caches, thereby enabling faster content downloads to the users. Content caching involves two components: an admission algorithm to decide whether to cache an object and an eviction algorithm to decide which object to evict from the cache when it is full. In this paper, we focus on cache admission and propose a novel algorithm called RL-Cache that uses model-free reinforcement learning (RL) to decide whether or not to admit a requested object into the CDN's cache. Unlike prior approaches that use a small set of criteria for decision making, RL-Cache weights a large set of features that include the object size, recency, and frequency of access. We develop a publicly available implementation of RL-Cache and perform an evaluation using production traces for the image, video, and web traffic classes from Akamai's CDN. The evaluation shows that RL-Cache improves the hit rate in comparison with the state of the art and imposes only a modest resource overhead on the CDN servers. Further, RL-Cache is robust enough that itmore »can be trained in one location and executed on request traces of the same or different traffic classes in other locations of the same geographic region.« less
5. Cache-Aided Interference Management using Hypercube Combinatorial Cache Designs

   https://doi.org/10.1109/ICC.2019.8761238  

   Zhang, Xiang ; Woolsey, Nicholas ; Ji, Mingyue ( May 2019 , ICC 2019 - 2019 IEEE International Conference on Communications (ICC))