25 research outputs found
A cost model for autonomic reconfigurations in high-performance pervasive applications
No full textIn the last years we have seen the diffusion of platforms
including high- performance nodes (e.g. multicores) and
powerful mobile devices (e.g. smartphones) interconnected
by heterogeneous networks. Relevant examples of applications
targeting these kinds of platforms are Emergency Management
and Homeland Protection which provide computing/
communication activities characterized by user-defined
Quality of Service constraints. In this paper we introduce
the ASSISTANT programming model for adaptive parallel
applications. ASSISTANT components are specified in multiple
versions, each one dynamically selected according to an
adaptation strategy aimed to target the required QoS levels.
For these applications a key-issue is a well-defined adaptation
semantics featuring a cost model which describes the
overhead for reconfiguring a component (e.g. when switching
between versions). In this paper we introduce our approach
and we evaluate this cost on a flood management application.
Author Keywords
High-Performance Computing, Adaptivity, Autonomic Computing,
Application Reconfigurations
Progetto e realizzazione di un reflectarray riconfigurabile a MEMS per imaging a onde millimetriche
No full textI Reflectarray a scansione elettronica rappresentano un’ottima soluzione per ottenere antenne riconfigurabili operanti alle frequenze delle onde millimetriche. Se la scansione è ottenuta mediante l’utilizzo di sfasatori a MEMS, le potenzialità di tali
dispositivi diventano enormi in termini di costi e velocità di scansione del fascio. In questo articolo si presenta il progetto di un reflectarray riconfigurabile elettronicamente tramite carichi riflettenti variabili a MEMS da utilizzare per applicazioni di imaging passivo alle onde millimetriche in ambienti esterni. L’obiettivo è quello di ottenere un sistema d’antenna a basso costo, veloce nella scansione della scena e di dimensioni e peso ridotti in modo da essere implementato anche su dispositivi portatili. Di seguito vengono presentati il progetto del reflectarray e i risultati simulati. Il prototipo è in costruzione presso i laboratori dell’ITC-irst
Design and Realization of a MEMS Tunable Reflectarray for mm-Wave Imaging Application
No full textElectronic beam scanning reflectarrays represent a very interesting solution to obtain reconfigurable antennas at mm-wave frequencies. The potentialities of such systems could be further increased in terms of costs and performance by employing MEMS devices. In this paper we present the design and the simulated results of a two-layer MEMS tuneable reflectarray. This antenna is designed for outdoor passive mm-waves imaging applications (35 GHz). The target is to realize a low cost, fast, small and light antenna system to be implemented in portable devices. The manufacturing of the prototype is on the way at the ITC-irst (Trento – IT) laboratories
A dataflow runtime environment and static scheduler for edge, fog and in-situ computing
No full textIn the dataflow computation model, tasks are executed according to data dependencies, instead of following program order, enabling natural parallelism exploitation. Sucuri is a dataflow library for Python that allows transparent execution of applications on clusters of multicores, while taking care of scheduling issues. Recent trends in edge/fog/In-situ computing assume that storage and network devices will have processing elements with lower power consumption and performance, which would make a good case for runtime environments that deal with the data versus computation movements trade-off in a more transparent and automated way. This work presents a study on different factors that should be considered when running dataflow applications in in-situ environments, using Sucuri to conduct experiments in a small system emulating a smart storage (in-situ device) utilisation. A static scheduling solution is also presented, allowing Sucuri to choose the most suited approach regarding this in-situ trade-off
Dynamic community analysis in decentralized online social networks
No full textCommunity structure is one of the most studied features of Online Social Networks (OSNs). Community detection guarantees several advantages for both centralized and decentralized social networks. Decentralized Online Social Networks (DOSNs) have been proposed to provide more control over private data. One of the main challenge in DOSNs concerns the availability of social data and communities can be exploited to guarantee a more efficient solution about the data availability problem. The detection of communities and the management of their evolution represents a hard process, especially in highly dynamic social networks, such as DOSNs, where the online/offline status of user changes very frequently. In this paper, we focus our attention on a preliminary analysis of dynamic community detection in DOSNs by studying a real Facebook dataset to evaluate how frequent the communities change over time and which events are more frequent. The results prove that the social graph has a high instability and distributed solutions to manage the dynamism are needed
Benchmarking the NVIDIA V100 GPU and Tensor Cores
No full textThe V100 GPU is the newest server-grade GPU produced by NVIDIA and introduces a number of new hardware and API features. This paper details the results of benchmarking the V100 GPU and demonstrates that it is a significant generational improvement, increasing memory bandwidth, cache bandwidth, and reducing latency. A major new addition is the Tensor core units, which have been marketed as deep learning acceleration features that enable the computation of a 4 × 4 × 4 half precision matrix-multiply-accumulate operation in a single clock cycle. This paper confirms that the Tensor cores offer considerable performance gains for half precision general matrix multiplication; however, programming them requires fine control of the memory hierarchy that is typically unnecessary for other applications.</p
A lightweight approach to GPU resilience
No full textResilience for HPC applications typically is implemented as a CPU-based rollback-recovery technique. In this context, long running accelerator computations on GPUs pose a major challenge as these devices usually do not offer any means of interrupt. This paper proposes a solution to the aforementioned problem: it suggests a novel approach that rewrites GPU kernels so that a soft interrupt of their execution becomes possible. Our approach is based on the Compute Unified Device Architecture (CUDA) by Nvidia and works by taking advantage of CUDA’s execution model of partitioning threads into blocks. In essence, we re-write the kernel so that each block determines whether it should continue execution or return control to the CPU. By doing so we are able to perform a premature interrupt of kernels.</p
THECAMAP: Terahertz Camera for Medical Application
No full textWe are developing a THz imager system to identify the tumors such as in vivo and in vitro detection. THECAMAP (terahertz camera for medical applications) system will design to allow a real time detection of the reflected THz radiation by the MUT (material under test) and to provide a high sensitivity and spatial resolution
FINJ: A fault injection tool for HPC systems
No full textWe present FINJ, a high-level fault injection tool for High-Performance Computing (HPC) systems, with a focus on the management of complex experiments. FINJ provides support for custom workloads and allows generation of anomalous conditions through the use of fault-triggering executable programs. FINJ can also be integrated seamlessly with most other lower-level fault injection tools, allowing users to create and monitor a variety of highly-complex and diverse fault conditions in HPC systems that would be difficult to recreate in practice. FINJ is suitable for experiments involving many, potentially interacting nodes, making it a very versatile design and evaluation tool
