3 January 2023 in IEEE/ACM Transactions on Networking
This paper proposes a new clock offset estimation that mitigates unwanted link asymmetry for precise clock synchronization. The main contribution is to address the primary and traditional design issue of the IEEE 1588 standard precision time protocol (PTP), which estimates clock offset under the assumption that the delays of exchanged packets are symmetric. To mitigate the issue, we focus on the fact that PTP measures asymmetry variation through the derivatives of its timestamps with respect to the time step. By exploiting the measurement of the variation, the proposed approach defines the asymmetry in the form of a linear differential equation (LDE) and leverages the LDE to define and exclude asymmetry-induced errors. Additionally, we clearly derive the state transition of the asymmetry. Subsequently, we derive a novel state-space model from our approach. The model describes PTP clock offset estimation perfectly, allowing optimal clock offset estimation. We verify the theoretical validity of the proposed method with real data. Our approach improves PTP accuracy by more than thousand times and achieves an accuracy at the level of tens to hundreds of nanoseconds on an asymmetric communication link. Our approach realizes an accuracy comparable to that of PTPv2, without the cost of specialized hardware.
27 February 2026 in IEEE Computer Architecture Letters
Analog Computing-in-Memory (ACiM) devices perform matrix operations directly within memory arrays, offering high throughput for deep neural network inference. At the same time, they are susceptible to various noise sources, which reduces the computational accuracy. This inherent trade-off limits the adoption of ACiM devices as a stand-alone accelerator. In this paper, we propose the first heterogeneous inference-serving framework that coordinates ACiM hardware and conventional digital processors during inference. The system dynamically partitions each neural network into an analog sub-network executed on high-throughput ACiM devices and a digital sub-network handled by precise digital devices. Then, it integrates a transition layer and a custom training strategy to maintain accuracy across varying analog-digital partitions. Also, it adopts a two-level scheduler to adjust the partition ratio at runtime in response to varying query demands. We evaluate our system using five network models to demonstrate the benefits of our system.