Related papers: Avoiding Cross-Datacenter Collective Congestion vi…
On the Internet, sub-millisecond queueing delay and capacity-seeking have traditionally been considered mutually exclusive. We introduce a service that offers both: Low Latency Low Loss Scalable throughput (L4S). When tested under a wide…
With the increased demand on economy and efficiency of measurement technology, Non-Intrusive Load Monitoring (NILM) has received more and more attention as a cost-effective way to monitor electricity and provide feedback to users. Deep…
In this paper, to analyze end-to-end timing behavior in heterogeneous processor and network environments accurately, we adopt a heterogeneous selection value on communication contention (HSV_CC) algorithm, which can synchronize tasks and…
Emerging applications of machine learning in numerous areas involve continuous gathering of and learning from streams of data. Real-time incorporation of streaming data into the learned models is essential for improved inference in these…
This paper introduces a Deep Reinforcement Learning (DRL) based TCP congestion-control algorithm that uses a Deep Q-Network (DQN) to adapt the congestion window (cWnd) dynamically based on observed network state. The proposed approach…
Parallel programming is emerging fast and intensive applications need more resources, so there is a huge demand for on-chip multiprocessors. Accessing L1 caches beside the cores are the fastest after registers but the size of private caches…
The IEEE 802.11 backoff algorithm is very important for controlling system throughput over contentionbased wireless networks. For this reason, there are many studies on wireless network performance focus on developing backoff algorithms.…
Serverless computing that runs functions with auto-scaling is a popular task execution pattern in the cloud-native era. By connecting serverless functions into workflows, tenants can achieve complex functionality. Prior researches adopt the…
In modern server CPUs, the Last-Level Cache (LLC) serves not only as a victim cache for higher-level private caches but also as a buffer for low-latency DMA transfers between CPU cores and I/O devices through Direct Cache Access (DCA).…
Sparsifying the Transformer has garnered considerable interest, as training the Transformer is very computationally demanding. Prior efforts to sparsify the Transformer have either used a fixed pattern or data-driven approach to reduce the…
Modern applications demand high performance and cost efficient database management systems (DBMSs). Their workloads may be diverse, ranging from online transaction processing to analytics and decision support. The cloud infrastructure…
TCP and its variants have suffered from surprisingly poor performance for decades. We argue the TCP family has little hope to achieve consistent high performance due to a fundamental architectural deficiency: hardwiring packet-level events…
Datacenter applications demand both low latency and high throughput; while interactive applications (e.g., Web Search) demand low tail latency for their short messages due to their partition-aggregate software architecture, many…
Fast-evolving machine learning (ML) workloads have increasing requirements for networking. However, host network transport on RDMA NICs is hard to evolve, causing problems for ML workloads. For example, single-path RDMA traffic is prone to…
Large-scale LLM training requires collective communication libraries to exchange data among distributed GPUs. As a company dedicated to building and operating large-scale GPU training clusters, we encounter several challenges when using…
Congestion control plays a pivotal role in large-scale data centers, facilitating ultra-low latency, high bandwidth, and optimal utilization. Even with the deployment of data center congestion control mechanisms such as DCQCN and HPCC,…
Computational offloading has become an enabling component for edge intelligence in mobile and smart devices. Existing offloading schemes mainly focus on mobile devices and servers, while ignoring the potential network congestion caused by…
The evolution of Large Language Model (LLM) serving towards complex, distributed architectures--specifically the P/D-separated, large-scale DP+EP paradigm--introduces distinct scheduling challenges. Unlike traditional deployments where…
Distributed Machine Learning (DML) systems are utilized to enhance the speed of model training in data centers (DCs) and edge nodes. The Parameter Server (PS) communication architecture is commonly employed, but it faces severe long-tail…
Cost of serving large language models (LLM) is high, but the expensive and scarce GPUs are poorly efficient when generating tokens sequentially, unless the batch of sequences is enlarged. However, the batch size is limited by some…