Heterogeneous Memory Benchmarking Toolkit

Abstract: This paper presents an open-source kernel-level heterogeneous memory characterization framework (MemScope) for embedded systems that enables users to understand and precisely characterize the temporal behavior of all available memory modules under configurable contention stress scenarios. Since kernel-level provides a high degree of control over allocation, cache maintenance, $CPUs$, interrupts, and I/O device activity, seeking the most accurate way to benchmark heterogeneous memory subsystems, would be achieved by implementing it in the kernel. 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.