Message Passing Interface (MPI) is a foundational programming model for high-performance computing. MPI libraries traditionally employ network interconnects (e.g., Ethernet and InfiniBand) and network protocols (e.g., TCP and RoCE) with complex software stacks for cross-node communication.This paper presents cMPI, the first work to optimize MPI point-to-point communication (both one-sided and two-sided) using CXL memory sharing on a real CXL platform, transforming cross-node communication into memory transactions and data copies within CXL memory, bypassing traditional network protocols. We analyze performance across various interconnects and find that CXL memory sharing achieves 7.2 × -8.1 × lower latency than TCP-based interconnects deployed in small- and medium-scale clusters. We address challenges of CXL memory sharing for MPI communication, including data object management over the dax representation [50], cache coherence, and atomic operations. Overall, cMPI outperforms TCP over standard Ethernet NIC and high-end SmartNIC by up to 49 × and 72 × in latency and bandwidth, respectively, for small messages.

In-storage computing with modern solid-state drives (SSDs) enables developers to offload programs from the host to the SSD. It has been proven to be an effective approach to alleviate the I/O bottleneck. To facilitate in-storage computing, many frameworks have been proposed. However, few of them treat the in-storage security as the first citizen. Specifically, since modern SSD controllers do not have a trusted execution environment, an offloaded (malicious) program could steal, modify, and even destroy the data stored in the SSD.

In this work-in-progress paper, we present a network coding scheme based on random linear coding (RLC), named cumulative RLC. Cumulative RLC applies RLC in a cumulative manner such that the end-to-end delay is minimized and it can be used for real-time one-to-many video distribution over wireless networks. The proposed cumulative RLC is well-suited especially for media applications with low-latency constraints such as real-time resilient video distribution for interactive service scenarios. The key property of cumulative RLC is reducing the waiting delay during the RLC encoding procedure. To verify the efficiency of the proposed cumulative RLC, we implement a real-time resilient video distribution system employing cumulative RLC over a IEEE 802.11-based wireless network. Experimental results show that in a typical setting, cumulative RLC yields reducing RLC encoding delay so it can help efficient real-time video distribution.

CPS (cyber-physical system) is a kind of system that exhibits a tight combination of system computation and physical elements. This tight integration of computing and physical elements is achievable depending on the performance of reliable data communication among CPS nodes. To support the domain-specific quality requirements of reliable real-time CPS networking, we should deploy a network-adaptive reliable data distribution scheme while paying extra attention to the incurring computational complexity of selected error control modules. In this paper, by taking the example of reliable real-time data distribution for UAV (unmanned aviation vehicle)-aided tactical networks, we discuss how to build a simulation environment that can evaluate the tradeoff of CPS networking performance and resource consumption (in terms of computing and networking resources). To validate the appropriateness of constructed simulation environment, we apply specific error control building blocks on the resource-constrained multi-level hierarchical UAV-aided tactical WiMax networks and evaluate their performance and resource consumption.