Related papers: The benefits of prefetching for large-scale cloud-…

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.…

Advancement in Processor technology has made it easy to handle data-intensive workloads, but limiting main memory advances has created performance bottlenecks. In DRAM, there have been improvements in DRAM access latency as well as…

Historically, medical imaging repositories have been supported by indoor infrastructures. However, the amount of diagnostic imaging procedures has continuously increased over the last decades, imposing several challenges associated with the…

Many algorithms in workflow scheduling and resource provisioning rely on the performance estimation of tasks to produce a scheduling plan. A profiler that is capable of modeling the execution of tasks and predicting their runtime…

The processing, computation and memory requirements posed by emerging mobile broadband services require adaptive memory management and prefetching techniques at the mobile terminals for satisfactory application performance and sustained…

For the last several months the main focus of development in the ROOT I/O package has been code consolidation and performance improvements. Access to remote files is affected both by bandwidth and latency. We introduced a pre-fetch…

I/O is emerging as a major bottleneck for machine learning training, especially in distributed environments. Indeed, at large scale, I/O takes as much as 85% of training time. Addressing this I/O bottleneck necessitates careful…

Prefetching web pages is a well-studied solution to reduce network latency by predicting users' future actions based on their past behaviors. However, such techniques are largely unexplored on mobile platforms. Today's privacy regulations…

The convergence of high-performance computing (HPC) and artificial intelligence (AI) is driving the emergence of increasingly complex parallel applications and workloads. These workloads often combine multiple parallel runtimes within the…

Predictive autoscaling (autoscaling with workload forecasting) is an important mechanism that supports autonomous adjustment of computing resources in accordance with fluctuating workload demands in the Cloud. In recent works, Reinforcement…

When training neural rankers using Large Language Models, it's expected that a practitioner would make use of multiple GPUs to accelerate the training time. By using more devices, deep learning frameworks, like PyTorch, allow the user to…

Modern high-performance architectures employ large last-level caches (LLCs). While large LLCs can reduce average memory access latency for workloads with a high degree of locality, they can also increase latency for workloads with irregular…

Deep learning datasets are expanding at an unprecedented pace, creating new challenges for data processing in model training pipelines. A crucial aspect of these pipelines is dataset shuffling, which significantly improves unbiased learning…

Hardware prefetching is critical to fill the performance gap between CPU speeds and slower memory accesses. With multicore architectures becoming commonplace, traditional prefetchers are severely challenged. Independent core operation…

We propose an approach to data memory prefetching which augments the standard prefetch buffer with selection criteria based on performance and usage pattern of a given instruction. This approach is built on top of a pattern matching based…

The prevailing paradigm for enhancing the reasoning abilities of LLMs revolves around post-training on high-quality, reasoning-intensive data. While emerging literature suggests that reasoning data is increasingly incorporated also during…

Layerwise offloading reduces the GPU memory footprint of large diffusion transformer (DiT) inference by prefetching upcoming layers from host memory, but its effectiveness hinges on hiding prefetch latency behind per-layer computation. This…

Hyperscalars run services across a large fleet of servers, serving billions of users worldwide. These services, however, behave differently than commonly available benchmark suites, resulting in server architectures that are not optimized…

Hardware based memory pooling enabled by interconnect standards like CXL have been gaining popularity amongst cloud providers and system integrators. While pooling memory resources has cost benefits, it comes at a penalty of increased…

An important topic in medical research is the process of improving the images obtained from medical devices. As a consequence, there is also a need to improve medical image resolution and analysis. Another issue in this field is the large…