A software-defined architecture and prototype for disaggregated memory rack scale systems
Ημερομηνία
2018Γλώσσα
en
Λέξη-κλειδί
Επιτομή
Disaggregation and rack-scale systems have the potential of drastically increasing TCO and utilization of cloud datacenters, while maintaining performance. In this paper, we present a novel rack-scale system architecture featuring software-defined remote memory disaggregation. Our hardware design and operating system extensions enable unmodified applications to dynamically attach to memory segments residing on physically remote memory pools and use such remote segments in a byte-addressable manner, as if they were local to the application. Our system features also a control plane that automates software-defined dynamic matching of compute to memory resources, as driven by datacenter workload needs. We prototyped our system on the commercially available Zynq Ultrascale+ MPSoC platform. To our knowledge, this is the first time a software-defined disaggregated system has been prototyped on commercial hardware and evaluated through industry standard software benchmarks. Our initial results-using benchmarks that are artificially highly adversarial in terms of memory bandwidth-show that disaggregated memory access exhibits a round-trip latency of only 134 clock cycles; and a throughput penalty of as low as 55%, relative to locally-attached memory. We also discuss estimations as to how our findings may translate to applications with pragmatically milder memory aggressiveness levels, as well as innovation avenues across the stack opened up by our work. © 2017 IEEE.
Collections
Related items
Showing items related by title, author, creator and subject.
-
Shortening design time through multiplatform simulations with a portable OpenCL golden-model: The LDPC decoder case
Falcao, G.; Owaida, M.; Novo, D.; Purnaprajna, M.; Bellas, N.; Antonopoulos, C. D.; Karakonstantis, G.; Burg, A.; Ienne, P. (2012)Hardware designers and engineers typically need to explore a multi-parametric design space in order to find the best configuration for their designs using simulations that can take weeks to months to complete. For example, ... -
A comparison of distributed spatial data management systems for processing distance join queries
García-García F., Corral A., Iribarne L., Mavrommatis G., Vassilakopoulos M. (2017)Due to the ubiquitous use of spatial data applications and the large amounts of spatial data that these applications generate, the processing of large-scale distance joins in distributed systems is becoming increasingly ... -
Survey on Grid Resource Allocation Mechanisms
Qureshi, M. B.; Dehnavi, M. M.; Min-Allah, N.; Qureshi, M. S.; Hussain, H.; Rentifis, I.; Tziritas, N.; Loukopoulos, T.; Khan, S. U.; Xu, C. Z.; Zomaya, A. Y. (2014)Grid is a distributed high performance computing paradigm that offers various types of resources (like computing, storage, communication) to resource-intensive user tasks. These tasks are scheduled to allocate available ...