Related papers: Maxwell: a hardware and software highly integrated…

Shuffle exchanges intermediate results between upstream and downstream operators in distributed data processing and is usually the bottleneck due to factors such as small random I/Os and network contention. Several systems have been…

We present MaxMem, a tiered main memory management system that aims to maximize Big Data application colocation and performance. MaxMem uses an application-agnostic and lightweight memory occupancy control mechanism based on fast memory…

The public cloud offers a myriad of services which allows its tenants to process large scale big data in a flexible, easy and cost effective manner. Tenants generally use large scale data processing frameworks such as MapReduce, Tez, Spark…

Cloud-native systems represent a significant leap in constructing scalable, large systems, employing microservice architecture as a key element in developing distributed systems through self-contained components. However, the decentralized…

The increasing computational and memory requirements of Deep Learning (DL) workloads has led to outstanding innovations in hardware architectures. An archetype of such architectures is the novel Versal AI Engine (AIE) by AMD/Xilinx. The AIE…

Most cloud services and distributed applications rely on hashing algorithms that allow dynamic scaling of a robust and efficient hash table. Examples include AWS, Google Cloud and BitTorrent. Consistent and rendezvous hashing are algorithms…

As more and more organizations rely on data-driven decision making, large-scale analytics become increasingly important. However, an analyst is often stuck waiting for an exact result. As such, organizations turn to Cloud providers that…

Traffic load-balancing in datacenters alleviates hot spots and improves network utilization. In this paper, a stable in-network load-balancing algorithm is developed in the setting of software-defined networking. A control plane configures…

With its decentralization and immutability, blockchain has emerged as a trusted foundation for data management and querying. Because blockchain storage space is limited, large multimodal data files, such as videos, are often stored offline,…

In-memory (transactional) data stores are recognized as a first-class data management technology for cloud platforms, thanks to their ability to match the elasticity requirements imposed by the pay-as-you-go cost model. On the other hand,…

Multi-modal Large Language Models (MLLMs) serving systems commonly employ KV-cache compression to reduce memory footprint. However, existing compression methods introduce significant processing overhead and queuing delays, particularly in…

The ability to scale out training workloads has been one of the key performance enablers of deep learning. The main scaling approach is data-parallel GPU-based training, which has been boosted by hardware and software support for highly…

Cloud computing is becoming an essential component of modern computer and communication systems. The available resources at the cloud such as computing nodes, storage, databases, etc. are often packaged in the form of virtual machines (VMs)…

To break the bottlenecks of mainstream cloud-based machine learning (ML) paradigm, we adopt device-cloud collaborative ML and build the first end-to-end and general-purpose system, called Walle, as the foundation. Walle consists of a…

Hyper-converged cloud refers to an architecture that an operator runs compute and storage services on the same set of physical servers. Although the hyper-converged design comes with a number of benefits, it makes crucial operational tasks,…

While prior researches focus on CPU-based microservices, they are not applicable for GPU-based microservices due to the different contention patterns. It is challenging to optimize the resource utilization while guaranteeing the QoS for GPU…

Operating systems include many heuristic algorithms designed to improve overall storage performance and throughput. Because such heuristics cannot work well for all conditions and workloads, system designers resorted to exposing numerous…

Disaggregated storage with NVMe-over-Fabrics (NVMe-oF) has emerged as the standard solution in modern supercomputers and data center clusters, achieving superior performance, resource utilization, and power efficiency. Simultaneously,…

Recently, there are significant advances in the areas of networking, caching and computing. Nevertheless, these three important areas have traditionally been addressed separately in the existing research. In this paper, we present a novel…

Modern large-scale systems such as recommender system and online advertising system are built upon computation-intensive infrastructure. The typical objective in these applications is to maximize the total revenue, e.g. GMV~(Gross…