Azalia Mirhoseini, Anna Goldie, Mustafa Yazgan, Joe Jiang, Ebrahim Songhori, Shen Wang, Young-Joon Lee, Eric Johnson, Omkar Pathak, Sungmin Bae, Azade Nazi, Jiw… 展开作者
Azalia Mirhoseini, Anna Goldie, Mustafa Yazgan, Joe Jiang, Ebrahim Songhori, Shen Wang, Young-Joon Lee, Eric Johnson, Omkar Pathak, Sungmin Bae, Azade Nazi, Jiwoo Pak, Andy Tong, Kavya Srinivasa, William Hang, Emre Tuncer, Anand Babu, Quoc V. Le, James Laudon, Richard Ho, Roger Carpenter, Jeff Dean
In this work, we present a learning-based approach to chip placement, one of the most complex and time-consuming stages of the chip design process. Unlike prior methods, our approach has the ability to learn from past experience and improve over time. In particular, as we train over a greater number of chip blocks, our method becomes better at rapidly generating optimized placements for previously unseen chip blocks. To achieve these results, we pose placement as a Reinforcement Learning (RL) problem and train an agent to place the nodes of a chip netlist onto a chip canvas. To enable our RL policy to generalize to unseen blocks, we ground representation learning in the supervised task of predicting placement quality. By designing a neural architecture that can accurately predict reward across a wide variety of netlists and their placements, we are able to generate rich feature embeddings of the input netlists. We then use this architecture as the encoder of our policy and value networks to enable transfer learning. Our objective is to minimize PPA (power, performance, and area), and we show that, in under 6 hours, our method can generate placements that are superhuman or comparable on modern accelerator netlists, whereas existing baselines require human experts in the loop and take several weeks.
ChiPFormer: Transferable Chip Placement via Offline Decision Transformer
The University of Hong Kong（香港大学）；Shanghai AI Laboratory（上海人工智能实验室）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）；Zhejiang University（浙江大学）；Tianjin University（天津大学）
For its advantage in GPU acceleration and less dependency on human experts, machine learning has been an emerging tool for solving the placement and routing problems, as two critical steps in modern chip design flow. Being still in its early stage, there are fundamental issues: scalability, reward design, and end-to-end learning paradigm etc. To achieve end-to-end placement learning, we first propose a joint learning method termed by DeepPlace for the placement of macros and standard cells, by the integration of reinforcement learning with a gradient based optimization scheme. To further bridg…
Recently, successful applications of reinforcement learning to chip placement have emerged. Pretrained models are necessary to improve efficiency and effectiveness. Currently, the weights of objective metrics (e.g., wirelength, congestion, and timing) are fixed during pretraining. However, fixed-weighed models cannot generate the diversity of placements required for engineers to accommodate changing requirements as they arise. This paper proposes flexible multiple-objective reinforcement learning (MORL) to support objective functions with inference-time variable weights using just a single pre…
TDPNavigator-Placer: Thermal- and Wirelength-Aware Chiplet Placement in 2.5D Systems Through Multi-Agent Reinforcement Learning
Institute for Infocomm Research (I2R), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局（A*STAR）信息通信研究院（I2R））；Institute of Microelectronics (IME), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局（A*STAR）微电子研究院（IME））
Chip placement has been one of the most time consuming task in any semi conductor area, Due to this negligence, many projects are pushed and chips availability in real markets get delayed. An engineer placing macros on a chip also needs to place it optimally to reduce the three important factors like power, performance and time. Looking at these prior problems we wanted to introduce a new method using Reinforcement Learning where we train the model to place the nodes of a chip netlist onto a chip canvas. We want to build a neural architecture that will accurately reward the agent across a wide…
Department of EECS, UC Berkeley, CA, USA（UC伯克利电子工程与计算机科学系）；SambaNova Systems Inc., Palo Alto, CA, USA（SambaNova Systems公司）；Computer Science Department, Stanford University, CA, USA（斯坦福大学计算机科学系）
BBOPlace-Bench: Benchmarking Black-Box Optimization for Chip Placement
National Key Laboratory for Novel Software Technology（国家新型软件技术重点实验室）；School of Artificial Intelligence, Nanjing University（人工智能学院，南京大学）；Huawei Noah’s Ark Lab（华为诺亚实验室）
The University of Texas at Austin（德克萨斯大学奥斯汀分校）；Google（谷歌）
In physical design, human designers typically place macros via trial and error, which is a Markov decision process. Reinforcement learning (RL) methods have demonstrated superhuman performance on the macro placement. In this paper, we propose an extension to this prior work (Mirhoseini et al., 2020). We first describe the details of the policy and value network architecture. We replace the force-directed method with DREAMPlace for placing standard cells in the RL environment. We also compare our improved method with other academic placers on public benchmarks.
Physical design and production of Integrated Circuits (IC) is becoming increasingly more challenging as the sophistication in IC technology is steadily increasing. Placement has been one of the most critical steps in IC physical design. Through decades of research, partition-based, analytical-based and annealing-based placers have been enriching the placement solution toolbox. However, open challenges including long run time and lack of ability to generalize continue to restrict wider applications of existing placement tools. We devise a learning-based placement tool based on cyclic applicatio…
Placement Optimization is an important problem in systems and chip design, which consists of mapping the nodes of a graph onto a limited set of resources to optimize for an objective, subject to constraints. In this paper, we start by motivating reinforcement learning as a solution to the placement problem. We then give an overview of what deep reinforcement learning is. We next formulate the placement problem as a reinforcement learning problem and show how this problem can be solved with policy gradient optimization. Finally, we describe lessons we have learned from training deep reinforceme…
Recent advances in GPU accelerated global and detail placement have reduced the time to solution by an order of magnitude. This advancement allows us to leverage data driven optimization (such as Reinforcement Learning) in an effort to improve the final quality of placement results. In this work we augment state-of-the-art, force-based global placement solvers with a reinforcement learning agent trained to improve the final detail placed Half Perimeter Wire Length (HPWL). We propose novel control schemes with either global or localized control of the placement process. We then train reinforcem…
Google Brain（谷歌大脑）；Google Brain Residency Program（谷歌大脑驻留计划）；Google（谷歌）
The past few years have witnessed a growth in size and computational requirements for training and inference with neural networks. Currently, a common approach to address these requirements is to use a heterogeneous distributed environment with a mixture of hardware devices such as CPUs and GPUs. Importantly, the decision of placing parts of the neural models on devices is often made by human experts based on simple heuristics and intuitions. In this paper, we propose a method which learns to optimize device placement for TensorFlow computational graphs. Key to our method is the use of a seque…
For deep neural network accelerators, memory movement is both energetically expensive and can bound computation. Therefore, optimal mapping of tensors to memory hierarchies is critical to performance. The growing complexity of neural networks calls for automated memory mapping instead of manual heuristic approaches; yet the search space of neural network computational graphs have previously been prohibitively large. We introduce Evolutionary Graph Reinforcement Learning (EGRL), a method designed for large search spaces, that combines graph neural networks, reinforcement learning, and evolution…
Concordia Institute for Information Systems Engineering, Concordia University（康考迪亚大学康考迪亚信息系统工程研究所）；Lebanese American University（黎巴嫩美国大学）
Cloud computing is a reliable solution to provide distributed computation power. However, real-time response is still challenging regarding the enormous amount of data generated by the IoT devices in 5G and 6G networks. Thus, multi-access edge computing (MEC), which consists of distributing the edge servers in the proximity of end-users to have low latency besides the higher processing power, is increasingly becoming a vital factor for the success of modern applications. This paper addresses the problem of minimizing both, the network delay, which is the main objective of MEC, and the number o…
We present a hybrid ML-heuristic approach that we name "Heuristically Assisted Deep Reinforcement Learning (HA-DRL)" to solve the problem of Network Slice Placement Optimization. The proposed approach leverages recent works on Deep Reinforcement Learning (DRL) for slice placement and Virtual Network Embedding (VNE) and uses a heuristic function to optimize the exploration of the action space by giving priority to reliable actions indicated by an efficient heuristic algorithm. The evaluation results show that the proposed HA-DRL algorithm can accelerate the learning of an efficient slice placem…
Deep Reinforcement Learning (DRL) underlies in a simulated environment and optimizes objective goals. By extending the conventional interaction scheme, this paper proffers gym-ds3, a scalable and reproducible open environment tailored for a high-fidelity Domain-Specific System-on-Chip (DSSoC) application. The simulation corroborates to schedule hierarchical jobs onto heterogeneous System-on-Chip (SoC) processors and bridges the system to reinforcement learning research. We systematically analyze the representative SoC simulator and discuss the primary challenging aspects that the system (1) co…
Advancing Forest Fire Prevention: Deep Reinforcement Learning for Effective Firebreak Placement
University of Chile（智利大学）；Universidad Tecnológica Metropolitana（大都会技术大学）；Complex Engineering System Institute - ISCI（复杂工程系统研究所）；Rey Juan Carlos University（胡安卡洛斯国王大学）；Centre de Ciència i Tecnologia Forestal de Catalunya（加泰罗尼亚森林科学与技术中心）
The emergence of technologies such as 5G and mobile edge computing has enabled provisioning of different types of services with different resource and service requirements to the vehicles in a vehicular network.The growing complexity of traffic mobility patterns and dynamics in the requests for different types of services has made service placement a challenging task. A typical static placement solution is not effective as it does not consider the traffic mobility and service dynamics. In this paper, we propose a reinforcement learning-based dynamic (RL-Dynamic) service placement framework to …
The growth of 5G and edge computing has enabled the emergence of Internet of Vehicles. It supports different types of services with different resource and service requirements. However, limited resources at the edge, high mobility of vehicles, increasing demand, and dynamicity in service request-types have made service placement a challenging task. A typical static placement solution is not effective as it does not consider the traffic mobility and service dynamics. Handling dynamics in IoV for service placement is an important and challenging problem which is the primary focus of our work in …
Beijing University of Posts and Telecommunications（北京邮电大学）；SUTD（新加坡科技设计大学）；Commonwealth Scientific and Industrial Research Organisation (CSIRO)（联邦科学与工业研究组织（CSIRO））；NTU（南洋理工大学）
This paper proposes an effective and novel multiagent deep reinforcement learning (MADRL)-based method for solving the joint virtual network function (VNF) placement and routing (P&R), where multiple service requests with differentiated demands are delivered at the same time. The differentiated demands of the service requests are reflected by their delay- and cost-sensitive factors. We first construct a VNF P&R problem to jointly minimize a weighted sum of service delay and resource consumption cost, which is NP-complete. Then, the joint VNF P&R problem is decoupled into two iterative subtasks…
Network Slice placement with the problem of allocation of resources from a virtualized substrate network is an optimization problem which can be formulated as a multiobjective Integer Linear Programming (ILP) problem. However, to cope with the complexity of such a continuous task and seeking for optimality and automation, the use of Machine Learning (ML) techniques appear as a promising approach. We introduce a hybrid placement solution based on Deep Reinforcement Learning (DRL) and a dedicated optimization heuristic based on the Power of Two Choices principle. The DRL algorithm uses the so-ca…
Volkswagen Group（大众汽车集团）；L3S Research Center, University of Hannover（汉诺威大学L3S研究中心）；University of Bonn（波恩大学）
The transition from conventional mobility to electromobility largely depends on charging infrastructure availability and optimal placement.This paper examines the optimal placement of charging stations in urban areas. We maximise the charging infrastructure supply over the area and minimise waiting, travel, and charging times while setting budget constraints. Moreover, we include the possibility of charging vehicles at home to obtain a more refined estimation of the actual charging demand throughout the urban area. We formulate the Placement of Charging Stations problem as a non-linear integer…
Deep Reinforcement Learning for Urban Air Quality Management: Multi-Objective Optimization of Pollution Mitigation Booth Placement in Metropolitan Environments
School of Computer Science（计算机科学学院）；Engineering, Vellore Institute of Technology（工程学院，维洛雷理工学院）；Chennai Campus（钦奈校区）；Chennai, Tamil Nadu 600127, India（钦奈，泰米尔纳德邦600127，印度）
University of Texas at Austin（德克萨斯大学奥斯汀分校）；University of Colorado, Boulder（科罗拉多大学博尔德分校）
The placement of charging stations in areas with developing charging infrastructure is a critical component of the future success of electric vehicles (EVs). In Albany County in New York, the expected rise in the EV population requires additional charging stations to maintain a sufficient level of efficiency across the charging infrastructure. A novel application of Reinforcement Learning (RL) is able to find optimal locations for new charging stations given the predicted charging demand and current charging locations. The most important factors that influence charging demand prediction includ…
Fog/Edge computing is a novel computing paradigm supporting resource-constrained Internet of Things (IoT) devices by the placement of their tasks on the edge and/or cloud servers. Recently, several Deep Reinforcement Learning (DRL)-based placement techniques have been proposed in fog/edge computing environments, which are only suitable for centralized setups. The training of well-performed DRL agents requires manifold training data while obtaining training data is costly. Hence, these centralized DRL-based techniques lack generalizability and quick adaptability, thus failing to efficiently tac…
Exploring the most task-friendly camera setting -- optimal camera placement (OCP) problem -- in tasks that use multiple cameras is of great importance. However, few existing OCP solutions specialize in depth observation of indoor scenes, and most versatile solutions work offline. To this problem, an OCP online solution to depth observation of indoor scenes based on reinforcement learning is proposed in this paper. The proposed solution comprises a simulation environment that implements scene observation and reward estimation using shadow maps and an agent network containing a soft actor-critic…
Optimizing Electric Vehicle Charging Station Placement Using Reinforcement Learning and Agent-Based Simulations
organization= Center for Environmental Intelligence, VinUniversity , city= Hanoi , country= Vietnam；organization= College of Engineering \& Computer Science, VinUniversity , city= Hanoi , country= Vietnam
Graph Neural Networks and Reinforcement Learning for Proactive Application Image Placement
Harokopio University of Athens（雅典哈罗科皮奥大学）；National Technical University of Athens（雅典国家技术大学）；Institute of Information Science and Technologies, National Research Council (CNR)（国家研究委员会信息科学与技术研究所）；University of Pisa（比萨大学）
Universidade Federal de Pernambuco (UFPE)（伯南布哥联邦大学（UFPE））；Dublin City University (DCU)（都柏林城市大学（DCU））；Universidade de Pernambuco (UPE)（伯南布哥大学（UPE））
Software defined networking (SDN) and network functions virtualisation (NFV) are making networks programmable and consequently much more flexible and agile. To meet service level agreements, achieve greater utilisation of legacy networks, faster service deployment, and reduce expenditure, telecommunications operators are deploying increasingly complex service function chains (SFCs). Notwithstanding the benefits of SFCs, increasing heterogeneity and dynamism from the cloud to the edge introduces significant SFC placement challenges, not least adding or removing network functions while maintaini…
The evaluation of the impact of using Machine Learning in the management of softwarized networks is considered in multiple research works. Beyond that, we propose to evaluate the robustness of online learning for optimal network slice placement. A major assumption to this study is to consider that slice request arrivals are non-stationary. In this context, we simulate unpredictable network load variations and compare two Deep Reinforcement Learning (DRL) algorithms: a pure DRL-based algorithm and a heuristically controlled DRL as a hybrid DRL-heuristic algorithm, to assess the impact of these …
Unmanned aerial vehicles (UAVs) can be utilized as aerial base stations (ABSs) to assist terrestrial infrastructure for keeping wireless connectivity in various emergency scenarios. To maximize the coverage rate of N ground users (GUs) by jointly placing multiple ABSs with limited coverage range is known to be a NP-hard problem with exponential complexity in N. The problem is further complicated when the coverage range becomes irregular due to site-specific blockage (e.g., buildings) on the air-ground channel in the 3-dimensional (3D) space. To tackle this challenging problem, this paper appli…
Learning to Optimise Climate Sensor Placement using a Transformer
National Institute of Water and Atmospheric Research（水与大气研究所）；School of Engineering and Computer Science（工程与计算机科学学院）；Victoria University of Wellington（惠灵顿维多利亚大学）
It's-A-Me, Quantum Mario: Scalable Quantum Reinforcement Learning with Multi-Chip Ensembles
Interdisciplinary Program in Artificial Intelligence（人工智能交叉学科计划）；Computational Science Initiative（计算科学倡议）；Wells Fargo（沃尔斯福戈）；Department of Psychology（心理学系）；Department of Brain and Cognitive Sciences（脑与认知科学系）
NTT Communication Science Laboratories（NTT通信科学实验室）；Institute of Mathematics for Industry, Kyushu University（九州大学数学工学研究所）；Center for Advanced Intelligence Project, RIKEN（理化学研究所高级智能项目中心）
We propose a data-driven method for controlling the frequency and convergence rate of black-box nonlinear dynamical systems based on the Koopman operator theory. With the proposed method, a policy network is trained such that the eigenvalues of a Koopman operator of controlled dynamics are close to the target eigenvalues. The policy network consists of a neural network to find a Koopman invariant subspace, and a pole placement module to adjust the eigenvalues of the Koopman operator. Since the policy network is differentiable, we can train it in an end-to-end fashion using reinforcement learni…
Department of Electrical and Computer Engineering, National University of Singapore（新加坡国立大学电气与计算机工程系）
Machine learning (ML) has made incredible impacts and transformations in a wide range of vehicular applications. As the use of ML in Internet of Vehicles (IoV) continues to advance, adversarial threats and their impact have become an important subject of research worth exploring. In this paper, we focus on Sybil-based adversarial threats against a deep reinforcement learning (DRL)-assisted IoV framework and more specifically, DRL-based dynamic service placement in IoV. We carry out an experimental study with real vehicle trajectories to analyze the impact on service delay and resource congesti…
University of Southern California（南加利福尼亚大学）；Oregon State University（俄勒冈州立大学）
Machine learning applied to architecture design presents a promising opportunity with broad applications. Recent deep reinforcement learning (DRL) techniques, in particular, enable efficient exploration in vast design spaces where conventional design strategies may be inadequate. This paper proposes a novel deep reinforcement framework, taking routerless networks-on-chip (NoC) as an evaluation case study. The new framework successfully resolves problems with prior design approaches being either unreliable due to random searches or inflexible due to severe design space restrictions. The framewo…
