Learned Performance Model for SSD

Hyeon Gyu Lee, Minwook Kim, Juwon Lee, Eunji Lee, Bryan S. Kim, Sungjin Lee, Yeseong Kim, Sang Lyul Min, Jin Soo Kim

Research output: Contribution to journalArticlepeer-review


The advent of new SSDs with ultra-low latency makes the validation of their firmware critical in the development process. However, existing SSD simulators do not sufficiently achieve high accuracy in their performance estimations for their firmware. In this paper, we present an accurate and data-driven performance model that builds a cross-platform relationship between the simulator and target platform. We directly execute the firmware on both platforms, collect its related performance profiles, and construct a performance model that infers the firmware's performance on the target platform using performance events from the simulation. We explore both a linear regression model and a deep neural network model, and our cross-validation shows that our model achieves a percent error of 3.1%, significantly lower than 18.9% from a state-of-the-art simulator.

Original languageEnglish (US)
Pages (from-to)154-157
Number of pages4
JournalIEEE Computer Architecture Letters
Issue number2
StatePublished - 2021


  • Cross-platform
  • performance prediction
  • simulation
  • solid state drives

ASJC Scopus subject areas

  • Hardware and Architecture


Dive into the research topics of 'Learned Performance Model for SSD'. Together they form a unique fingerprint.

Cite this