Heterogeneous Memory Benchmarking Toolkit

TL;DR

This paper introduces MemScope, an open-source kernel-level benchmarking toolkit for embedded systems that accurately characterizes heterogeneous memory performance under various contention scenarios.

Contribution

It provides a novel kernel-level framework for precise, configurable benchmarking of heterogeneous memory modules in embedded systems, surpassing previous user-space solutions.

Findings

Accurately benchmarks bandwidth and latency of diverse memory types.

Demonstrates effectiveness on a Xilinx Zynq UltraScale+ platform.

Enables fine control over memory interference and contention.

Abstract

This paper presents an open-source kernel-level heterogeneous memory characterization framework (MemScope) for embedded systems. MemScope enables precise characterization of the temporal behavior of available memory modules under configurable contention stress scenarios. MemScope leverages kernel-level control over physical memory allocation, cache maintenance, CPU state, interrupts, and I/O device activity to accurately benchmark heterogeneous memory subsystems. This gives us the privilege to directly map pieces of contiguous physical memory and instantiate allocators, allowing us to finely control cores to create and eliminate interference. Additionally, we can minimize noise and interruptions, guaranteeing more consistent and precise results compared to equivalent user-space solutions. Running our Framework on a Xilinx Zynq UltraScale+ ZCU102 CPU-FPGA platform demonstrates its capability to precisely benchmark bandwidth and latency across various memory types, including PL-side DRAM and BRAM, in a multi-core system.