Related papers: Nf-PEAK: Process-Based Energy Attribution for Next…
Distributed dataflow systems such as Apache Spark or Apache Flink enable parallel, in-memory data processing on large clusters of commodity hardware. Consequently, the appropriate amount of memory to allocate to the cluster is a crucial…
Shared L1-memory clusters of streamlined instruction processors (processing elements - PEs) are commonly used as building blocks in modern, massively parallel computing architectures (e.g. GP-GPUs). Scaling out these architectures by…
Future networks must meet stringent requirements while operating within tight energy and carbon constraints. Current autoscaling mechanisms remain workload-centric and infrastructure-siloed, and are largely unaware of their environmental…
The surge for computing resource demand is increasing global electricity consumption in data centers which is expected to exceed 1000 TWh by 2026, mainly attributable to adoption of new AI technologies. Carbon-aware computing strategies can…
Modern GPUs adopt chiplet-based designs with multiple private cache hierarchies, but current programming models (CUDA/HIP) expose a flat execution hierarchy that cannot express chiplet-level locality or synchronization. This mismatch leads…
Complex workflows play a critical role in accelerating scientific discovery. In many scientific domains, efficient workflow management can lead to faster scientific output and broader user groups. Workflows that can leverage resources…
We describe a new 512-CPU Beowulf cluster with Teraflop performance dedicated to problems in computational astrophysics. The cluster incorporates a cubic network topology based on inexpensive commodity 24-port gigabit switches and point to…
In addition to hardware wall-time restrictions commonly seen in high-performance computing systems, it is likely that future systems will also be constrained by energy budgets. In the present work, finite difference algorithms of varying…
We consider offline scheduling algorithms that incorporate speed scaling to address the bicriteria problem of minimizing energy consumption and a scheduling metric. For makespan, we give linear-time algorithms to compute all non-dominated…
With the advent of exascale computing, effective load balancing in massively parallel software applications is critically important for leveraging the full potential of high performance computing systems. Load balancing is the distribution…
In this paper, we introduce Heteroflow, a new C++ library to help developers quickly write parallel CPU-GPU programs using task dependency graphs. Heteroflow leverages the power of modern C++ and task-based approaches to enable efficient…
Due to densification of wireless networks, there exist abundance of idling computation resources at edge devices. These resources can be scavenged by offloading heavy computation tasks from small IoT devices in proximity, thereby overcoming…
Large data and computing centers consume a significant share of the world's energy consumption. A prominent subset of the workloads in such centers are workflows with interdependent tasks, usually represented as directed acyclic graphs…
In this paper we analyze the problem of optimal task scheduling for data centers. Given the available resources and tasks, we propose a fast distributed iterative algorithm which operates over a large scale network of nodes and allows each…
Many-core accelerators, as represented by the XeonPhi coprocessors and GPGPUs, allow software to exploit spatial and temporal sharing of computing resources to improve the overall system performance. To unlock this performance potential…
In this paper, we propose a low-power hardware for efficient deployment of binarized neural networks (BNNs) that have been trained for physiological datasets. BNNs constrain weights and feature-map to 1 bit, can pack in as many 1-bit…
Distributed Stream Processing (DSP) focuses on the near real-time processing of large streams of unbounded data. To increase processing capacities, DSP systems are able to dynamically scale across a cluster of commodity nodes, ensuring a…
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…
Today, many scientific and engineering areas require high performance computing to perform computationally intensive experiments. For example, many advances in transport phenomena, thermodynamics, material properties, computational…
For current High Performance Computing systems to scale towards the holy grail of ExaFLOP performance, their power consumption has to be reduced by at least one order of magnitude. This goal can be achieved only through a combination of…