Related papers: CAFT: Congestion-Aware Fault-Tolerant Load Balanci…
We present novel oblivious routing algorithms for both splittable and unsplittable multicommodity flow. Our algorithm for minimizing congestion for \emph{unsplittable} multicommodity flow is the first oblivious routing algorithm for this…
In this work, we look at the impact of router configurations on DCTCP and Cubic traffic when both algorithms share router buffers in the data center. Modern data centers host traffic with mixed congestion controls, including DCTCP and Cubic…
Recent years have seen a great increase in the capacity and parallel processing power of data centers and cloud services. To fully utilize the said distributed systems, optimal load balancing for parallel queuing architectures must be…
The increasing penetration of electric vehicles over the coming decades, taken together with the high cost to upgrade local distribution networks and consumer demand for home charging, suggest that managing congestion on low voltage…
The exponential growth in model sizes has significantly increased the communication burden in Federated Learning (FL). Existing methods to alleviate this burden by transmitting compressed gradients often face high compression errors, which…
The Low Latency Fault Tolerance (LLFT) system provides fault tolerance for distributed applications, using the leader-follower replication technique. The LLFT system provides application-transparent replication, with strong replica…
In safety-critical autonomous systems, data freshness presents a fundamental design challenge. While the Logical Execution Time (LET) paradigm ensures compositional determinism, it often does so at the cost of injected latency, degrading…
Today's datacenters face important challenges for providing low-latency high-quality interactive services to meet user's expectation. For improving the application throughput, recent research works have embedded application deadline…
Although delay-based congestion control protocols such as FAST promise to deliver better performance than traditional TCP Reno, they have not yet been widely incorporated to the Internet. Several factors have contributed to their lack of…
A major concern in modern power systems is that the popularity and fluctuating characteristics of renewable energy may cause more and more transmission congestion events. Traditional congestion management modeling involves AC or DC power…
The behavior of loss-based TCP congestion control algorithms like TCP CUBIC continues to be a challenge in modern cellular networks. Due to the large RLC layer buffers required to deal with short-term changes in channel capacity, the…
Efficient and accurate path-sensitive analyses pose the challenges of: (a) analyzing an exponentially-increasing number of paths in a control-flow graph (CFG), and (b) checking feasibility of paths in a CFG. We address these challenges by…
Coflow is a prominent network abstraction for modeling communication patterns in data centers. Since coflow scheduling in large-scale data centers is $\mathcal{NP}$-hard, this paper investigates this problem within heterogeneous parallel…
In the operation of networked control systems, where multiple processes share a resource-limited and time-varying cost-sensitive network, communication delay is inevitable and primarily influenced by, first, the control systems deploying…
Fair queuing is becoming increasingly prevalent in the internet and has been shown to improve performance in many circumstances. Performance could be improved even more if endpoints could detect the presence of fair queuing on a certain…
Reducing the average memory access time is crucial for improving the performance of applications running on multi-core architectures. With workload consolidation this becomes increasingly challenging due to shared resource contention.…
We present ASYMP, a distributed graph processing system developed for the timely analysis of graphs with trillions of edges. ASYMP has several distinguishing features including a robust fault tolerance mechanism, a lockless architecture…
The increasing complexity of AI workloads, especially distributed Large Language Model (LLM) training, places significant strain on the networking infrastructure of parallel data centers and supercomputing systems. While Equal-Cost Multi-…
Most of the prior work in massively parallel data processing assumes homogeneity, i.e., every computing unit has the same computational capability, and can communicate with every other unit with the same latency and bandwidth. However, this…
This paper presents ExeGPT, a distributed system designed for constraint-aware LLM inference. ExeGPT finds and runs with an optimal execution schedule to maximize inference throughput while satisfying a given latency constraint. By…