首页|Investigators at University of Trento Detail Findings in Machine Learning (Cram- based Acceleration for Intermittent Computing of Parallelizable Tasks)
Investigators at University of Trento Detail Findings in Machine Learning (Cram- based Acceleration for Intermittent Computing of Parallelizable Tasks)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news reporting originating in Trento, Italy, by NewsRx journalists, research stated, “There is an emerging requirement for p erforming data-intensive parallel computations, e.g., machine-learning inference , locally on batteryless sensors. These devices are resource-constrained and ope rate intermittently due to the irregular energy availability in the environment. ” The news reporters obtained a quote from the research from the University of Tre nto, “Intermittent execution might lead to several side effects that might preve nt the correct execution of computational tasks. Even though recent studies prop osed methods to cope with these side effects and execute these tasks correctly, they overlooked the efficient intermittent execution of parallelizable data-inte nsive machine-learning tasks. In this article, we present PiMCo-a novel programm able CRAM-based in-memory coprocessor that exploits the Processing In-Memory (PI M) paradigm and facilitates the power-failure resilient execution of paralleliza ble computational loads. Contrary to existing PIM solutions for intermittent com puting, PiMCo promotes better programmability to accelerate a variety of paralle lizable tasks.”
TrentoItalyEuropeCyborgsEmerging TechnologiesMachine LearningUniversity of Trento
NETL
NSTL
