作者:
Rakov, DmitryPecheykina, Marina
Department of Technological Processes and Systems Control Moscow Russia
Department of Industrial Electronics Moscow Russia
The paper deals with Industry 4.0 as an information industry in which computersystems and networks are highly integrated with physical manufacturing processes. It includes the use of various technologies such as the ...
详细信息
Wardrobe is basically a must for every family. When the environment is humid, ordinary wardrobe will make clothes moldy and breed bacteria, cause damage to clothes, intelligent wardrobe can be a good solution to these...
详细信息
In the Post-Epidemic Era, with the development of the Internet and the birth of various new entertainment methods, children are disconnected from nature. To promote the connection between children and nature, we propo...
详细信息
In predictive control, the Finite control Set Model Predictive control (FCS-MPC) approach relies heavily on system modeling. Its optimised performance, high precision, and structural simplicity are some of its boasts....
详细信息
Machine learning (ML) has become a prevalent approach to tame the complexity of design space exploration for domain-specific architectures. While appealing, using ML for design space exploration poses several challeng...
详细信息
ISBN:
(纸本)9798400700958
Machine learning (ML) has become a prevalent approach to tame the complexity of design space exploration for domain-specific architectures. While appealing, using ML for design space exploration poses several challenges. First, it is not straightforward to identify the most suitable algorithm from an ever-increasing pool of ML methods. Second, assessing the trade-offs between performance and sample efficiency across these methods is inconclusive. Finally, the lack of a holistic framework for fair, reproducible, and objective comparison across these methods hinders the progress of adopting ML-aided architecture design space exploration and impedes creating repeatable artifacts. To mitigate these challenges, we introduce ArchGym, an open-source gymnasium and easy-to-extend framework that connects a diverse range of search algorithms to architecture simulators. To demonstrate its utility, we evaluate ArchGym across multiple vanilla and domain-specific search algorithms in the design of a custom memory controller, deep neural network accelerators, and a custom SoC for AR/VR workloads, collectively encompassing over 21K experiments. The results suggest that with an unlimited number of samples, ML algorithms are equally favorable to meet the user-defined target specification if its hyperparameters are tuned thoroughly;no one solution is necessarily better than another (e.g., reinforcement learning vs. Bayesian methods). We coin the term "hyperparameter lottery" to describe the relatively probable chance for a search algorithm to find an optimal design provided meticulously selected hyperparameters. Additionally, the ease of data collection and aggregation in ArchGym facilitates research in ML-aided architecture design space exploration. As a case study, we show this advantage by developing a proxy cost model with an RMSE of 0.61% that offers a 2,000-fold reduction in simulation time. Code and data for ArchGym is available at https://***/ArchGym.
The paper presents a technology of computeraideddesign (CAD) for integrated navigation systems (INS). The paper describes the information systemdesigned for automation of software development, its verification and ...
详细信息
With the development of China's economy, more and more people are traveling. At the same time, there are more and more problems in the hygiene and management of public toilets. This paper designs a smart toilet sy...
详细信息
Processing-using-DRAM (PUD) is a processing-in-memory (PIM) approach that uses a DRAM array's massive internal parallelism to execute very-wide (e.g., 16,384-262,144-bit-wide) data-parallel operations, in a single...
详细信息
ISBN:
(纸本)9798350393132;9798350393149
Processing-using-DRAM (PUD) is a processing-in-memory (PIM) approach that uses a DRAM array's massive internal parallelism to execute very-wide (e.g., 16,384-262,144-bit-wide) data-parallel operations, in a single-instruction multiple-data (SIMD) fashion. However, DRAM rows' large and rigid granularity limit the effectiveness and applicability of PUD in three ways. First, since applications have varying degrees of SIMD parallelism (which is often smaller than the DRAM row granularity), PUD execution often leads to underutilization, throughput loss, and energy waste. Second, due to the high area cost of implementing interconnects that connect columns in a wide DRAM row, most PUD architectures are limited to the execution of parallel map operations, where a single operation is performed over equally-sized input and output arrays. Third, the need to feed the wide DRAM row with tens of thousands of data elements combined with the lack of adequate compiler support for PUD systems create a programmability barrier, since programmers need to manually extract SIMD parallelism from an application and map computation to the PUD hardware. Our goal is to design a flexible PUD system that overcomes the limitations caused by the large and rigid granularity of PUD. To this end, we propose MIMDRAM, a hardware/software co-designed PUD system that introduces new mechanisms to allocate and control only the necessary resources for a given PUD operation. The key idea of MIMDRAM is to leverage finegrained DRAM (i.e., the ability to independently access smaller segments of a large DRAM row) for PUD computation. MIMDRAM exploits this key idea to enable a multiple-instruction multiple-data (MIMD) execution model in each DRAM subarray (and SIMD execution within each DRAM row segment). We evaluate MIMDRAM using twelve real-world applications and 495 multi-programmed application mixes. Our evaluation shows that MIMDRAM provides 34x the performance, 14.3x the energy efficiency, 1.7x the throughp
Collaborative exploration using unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) has become increasingly popular in the past decade. This study addresses real-time autonomous tracking and landing of...
详细信息
ISBN:
(纸本)9798350398687
Collaborative exploration using unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) has become increasingly popular in the past decade. This study addresses real-time autonomous tracking and landing of a UAV on a moving ground vehicle, which is fundamental for the UAV-UGV collaborative exploration. The method proposed in this study estimates the relative pose and velocity between a UAV and UGV, and uses model predictive control for UAV trajectory planning while considering the field of view of the camera onboard the UAV. We elaborate the hardware-in-the-loop simulator (HITL) with a physical companion computer, and confirm that the proposed method enables a UAV to land on a UGV traversing on rough terrain based on online computations in the HITL. Additionally, we present statistical analysis of the simulation results of typical and computationally demanding scenarios to elucidate the computational cost on the real machine.
The root locus cluster is an extension of the conventional root locus method, with applications in multi-parameter analysis and tuning. To help students master this method, this paper introduces the basic principles a...
详细信息
暂无评论