Related papers: Skyhook: Towards an Arrow-Native Storage System
Edge caching is a new paradigm that has been exploited over the past several years to reduce the load for the core network and to enhance the content delivery performance. Many existing caching solutions only consider homogeneous caching…
Over the years, hardware trends have introduced various heterogeneous compute units while also bringing network and storage bandwidths within an order of magnitude of memory subsystems. In response, developers have used increasingly exotic…
Next-generation real-time compute-intensive applications, such as extended reality, multi-user gaming, and autonomous transportation, are increasingly composed of heterogeneous AI-intensive functions with diverse resource requirements and…
Existing large language model (LLM) serving systems typically employ Prefill-Decode disaggregated architecture to prevent computational interference between the prefill and decode phases. However, in real-world LLM serving scenarios,…
Adjoint algorithmic differentiation by operator and function overloading is based on the interpretation of directed acyclic graphs resulting from evaluations of numerical simulation programs. The size of the computer system memory required…
The Internet of Things (IoT) bridges the gap between the physical and digital worlds, enabling seamless interaction with real-world objects via the Internet. However, IoT systems face significant challenges in ensuring efficient data…
The growing memory footprints of cloud and big data applications mean that data center CPUs can spend significant time waiting for memory. An attractive approach to improving performance in such centralized compute settings is to employ…
Data lakes hold a growing amount of cold data that is infrequently accessed, yet require interactive response times. Serverless functions are seen as a way to address this use case since they offer an appealing alternative to maintaining…
To achieve reliability in distributed storage systems, data has usually been replicated across different nodes. However the increasing volume of data to be stored has motivated the introduction of erasure codes, a storage efficient…
Decentralized, distributed storage offers a way to reduce the impact of data silos as often fostered by centralized cloud storage. While the intentions of this trend are not new, the topic gained traction due to technological advancements,…
We present IKAROS as a utility that permit us to form scalable storage platforms. IKAROS enable us to create ad-hoc nearby storage formations and use a huge number of I/O nodes in order to increase the available bandwidth. We measure the…
As spatial and temporal resolutions of scientific instruments improve, the explosion in the volume of data produced is becoming a key challenge. It can be a critical bottleneck for integration between scientific instruments at the edge and…
A growing number of Machine Learning Frameworks recently made Deep Learning accessible to a wider audience of engineers, scientists, and practitioners, by allowing straightforward use of complex neural network architectures and algorithms.…
In GPU-accelerated data analytics, the overhead of data transfer from CPU to GPU becomes a performance bottleneck when the data scales beyond GPU memory capacity due to the limited PCIe bandwidth. Data compression has come to rescue for…
Datacenters are witnessing a rapid surge in the adoption of serverless functions for microservices-based applications. A vast majority of these microservices typically span less than a second, have strict SLO requirements, and are chained…
The recent super-exponential growth in the amount of sequencing data generated worldwide has put techniques for compressed storage into the focus. Most available solutions, however, are strictly tied to specific bioinformatics formats,…
As multimodal and AI-driven services exchange hundreds of megabytes per request, existing IPC runtimes spend a growing share of CPU cycles on memory copies. Although both hardware and software mechanisms are exploring memory offloading,…
Large-scale systems with all-flash arrays have become increasingly common in many computing segments. To make such systems resilient, we can adopt erasure coding such as Reed-Solomon (RS) code as an alternative to replication because…
All-pairs compute problems apply a user-defined function to each combination of two items of a given data set. Although these problems present an abundance of parallelism, data reuse must be exploited to achieve good performance. Several…
Modern data analytics applications prefer to use column-storage formats due to their improved storage efficiency through encoding and compression. Parquet is the most popular file format for column data storage that provides several of…