English

MemorySim: An RTL-level, timing accurate simulator model for the Chisel ecosystem

Hardware Architecture 2025-08-19 v1

Abstract

The rapid growth of AI applications has driven increased demand for specialized AI hardware, highlighting critical opportunities within the memory subsystem, which often serves as a performance bottleneck in high-demand workloads such as large language models (LLMs). Existing high-level memory simulators, such as DRAMSim2 and DRAMSim3, offer timing simulations but frequently compromise on correctness or integration at the register-transfer level (RTL). We present MemorySim, an RTL-level memory simulator designed to deliver both accurate timing and functional correctness. MemorySim integrates seamlessly with existing Chisel and Verilog simulations and is fully compatible with the Chisel/Chipyard ecosystem. This enables users to obtain precise performance and power estimates, supporting downstream evaluation through simulation platforms such as FireSim.

Keywords

Cite

@article{arxiv.2508.12636,
  title  = {MemorySim: An RTL-level, timing accurate simulator model for the Chisel ecosystem},
  author = {Ansh Chaurasia},
  journal= {arXiv preprint arXiv:2508.12636},
  year   = {2025}
}
R2 v1 2026-07-01T04:54:15.050Z