相关论文: Evaluating the Overhead of the Performance Profile…
Heterogeneous computing, which combines devices with different architectures, is rising in popularity, and promises increased performance combined with reduced energy consumption. OpenCL has been proposed as a standard for programing such…
Concept drift detection is crucial for many AI systems to ensure the system's reliability. These systems often have to deal with large amounts of data or react in real-time. Thus, drift detectors must meet computational requirements or…
In highly distributed environments such as cloud, edge and fog computing, the application of machine learning for automating and optimizing processes is on the rise. Machine learning jobs are frequently applied in streaming conditions,…
As enterprises move to a cloud-first approach, their network becomes crucial to their daily operations and has to be continuously monitored. Although passive monitoring can be convenient from a deployment viewpoint, inferring the state of…
A key challenge for supporting elastic behaviour in cloud systems is to achieve a good performance in automated (de-)provisioning and scheduling of computing resources. One of the key aspects that can be significant is the overheads…
Real-world applications are now processing big-data sets, often bottlenecked by the data movement between the compute units and the main memory. Near-memory computing (NMC), a modern data-centric computational paradigm, can alleviate these…
Efficient on-device neural network (NN) inference offers predictable latency, improved privacy and reliability, and lower operating costs for vendors than cloud-based inference. This has sparked recent development of microcontroller-scale…
Debugging CUDA programs has long been challenging because failures often arise from subtle interactions among hardware behavior, compiler decisions, memory hierarchy, and asynchronous execution. More importantly, with the rapid expansion of…
We aim to resolve this problem by introducing a comprehensive distributed deep learning (DDL) profiler, which can determine the various execution "stalls" that DDL suffers from while running on a public cloud. We have implemented the…
Memory performance is often the main bottleneck in modern computing systems. In recent years, researchers have attempted to scale the memory wall by leveraging new technology such as CXL, HBM, and in- and near-memory processing. Developers…
This paper presents a compression framework for Reservoir Computing that enables systematic design-space exploration of trade-offs among quantization levels, pruning rates, model accuracy, and hardware efficiency. The proposed approach…
Profiling techniques are used extensively at different parts of the computing stack to achieve many goals. One major goal is to make a piece of software execute more efficiently on a specific hardware platform, where efficiency spans…
When clustering devices at the edge, inter-node latency poses a significant challenge that directly impacts the application performance. In this paper, we experimentally examine the impact that inter-node latency has on application…
Modern machine learning training is increasingly bottlenecked by data I/O rather than compute. GPUs often sit idle at below 50% utilization waiting for data. This paper presents a machine learning approach to predict I/O performance and…
Java is the "go-to" programming language choice for developing scalable enterprise cloud applications. In such systems, even a few percent CPU time savings can offer a significant competitive advantage and cost saving. Although performance…
Kubernetes (K8s) serves as a mature orchestration system for the seamless deployment and management of containerized applications spanning across cloud and edge environments. Since high-performance connectivity and minimal resource…
Cloud computing recently developed into a viable alternative to on-premises systems for executing high-performance computing (HPC) applications. With the emergence of new vendors and hardware options, there is now a growing need to…
Monitoring the performance of large shared computing systems such as the cloud computing infrastructure raises many challenging algorithmic problems. One common problem is to track users with the largest deviation from the norm (outliers),…
Automated benchmarking environments aim to support researchers in understanding how different algorithms perform on different types of optimization problems. Such comparisons provide insights into the strengths and weaknesses of different…
Services hosted in multi-tenant cloud platforms often encounter performance interference due to contention for non-partitionable resources, which in turn causes unpredictable behavior and degradation in application performance. To grapple…