The problem of scheduling of workloads onto heterogeneous processors (e.g., CPUs, GPUs, FPGAs) is of fundamental importance in modern data centers. Current system schedulers rely on application/system-specific heuristics that have to be built on a case-by-case basis. Recent work has demonstrated ML techniques for automating the heuristic search by using black-box approaches which require significant training data and time, which make them challenging to use in practice. This paper presents Symphony, a scheduling framework that addresses the challenge in two ways: (i) a domain-driven Bayesian reinforcement learning (RL) model for scheduling, which inherently models the resource dependencies identified from the system architecture; and (ii) a sampling-based technique to compute the gradients of a Bayesian model without performing full probabilistic inference. Together, these techniques reduce both the amount of training data and the time required to produce scheduling policies that significantly outperform black-box approaches by up to 2.2x.
EpiSys Science（EpiSys科学公司）；University of Alberta（阿尔伯塔大学）
Access to parallel and distributed computation has enabled researchers and developers to improve algorithms and performance in many applications. Recent research has focused on next generation special purpose systems with multiple kinds of coprocessors, known as heterogeneous system-on-chips (SoC). In this paper, we introduce a method to intelligently schedule--and learn to schedule--a stream of tasks to available processing elements in such a system. We use deep reinforcement learning enabling complex sequential decision making and empirically show that our reinforcement learning system provi…
Kwangwoon University（光云大学）；Chungnam National University（忠南国立大学）；Imperial College London（帝国理工学院）；EpiSys Science（EpiSys科学公司）
In this paper, we~present a novel scheduling solution for a class of System-on-Chip (SoC) systems where heterogeneous chip resources (DSP, FPGA, GPU, etc.) must be efficiently scheduled for continuously arriving hierarchical jobs with their tasks represented by a directed acyclic graph. Traditionally, heuristic algorithms have been widely used for many resource scheduling domains, and Heterogeneous Earliest Finish Time (HEFT) has been a dominating state-of-the-art technique across a broad range of heterogeneous resource scheduling domains over many years. Despite their long-standing popularity…
Georgia Institute of Technology（佐治亚理工学院）；Institute for Robotics and Intelligent Machines（机器人与智能机器研究所）
As human-robot collaboration increases in the workforce, it becomes essential for human-robot teams to coordinate efficiently and intuitively. Traditional approaches for human-robot scheduling either utilize exact methods that are intractable for large-scale problems and struggle to account for stochastic, time varying human task performance, or application-specific heuristics that require expert domain knowledge to develop. We propose a deep learning-based framework, called HybridNet, combining a heterogeneous graph-based encoder with a recurrent schedule propagator for scheduling stochastic …
A Learning Method with Gap-Aware Generation for Heterogeneous DAG Scheduling
School of Mathematical Science, Peking University（北京大学数学科学学院）；State Key Laboratory of Mathematical Sciences, Institute of Computational Mathematics and Scientific/Engineering Computing, Academy of Mathematics and Systems Science, Chinese Academy of Sciences（数学科学国家重点实验室，计算数学与科学/工程计算研究所，中国科学院数学系统科学研究院）；Theory Lab, Central Research Institute, 2012 Labs, Huawei Technologies Co., Ltd（华为技术有限公司2012实验室理论实验室，中央研究院）；Beijing International Center for Mathematical Research, Peking University（北京大学北京国际数学研究中心）
Faculty of Information Technology（信息技术学院）；Monash University（莫纳什大学）
Scarcity of parallel sentence pairs is a major challenge for training high quality neural machine translation (NMT) models in bilingually low-resource scenarios, as NMT is data-hungry. Multi-task learning is an elegant approach to inject linguistic-related inductive biases into NMT, using auxiliary syntactic and semantic tasks, to improve generalisation. The challenge, however, is to devise effective training schedules, prescribing when to make use of the auxiliary tasks during the training process to fill the knowledge gaps of the main translation task, a setting referred to as biased-MTL. Cu…
Model-Based Reinforcement Learning for Heterogeneous Multi-Robot Task Assignment Under Distribution Shifts
John A. Paulson School Of Engineering And Applied Sciences, Harvard University（哈佛大学约翰·A·保尔森工程与应用科学学院）；Harvard Medical School（哈佛医学院）；Beth Israel Deaconess Medical Center（贝斯以色列女执事医疗中心）；Stanford University School of Medicine（斯坦福大学医学院）
Large-scale interactive web services and advanced AI applications make sophisticated decisions in real-time, based on executing a massive amount of computation tasks on thousands of servers. Task schedulers, which often operate in heterogeneous and volatile environments, require high throughput, i.e., scheduling millions of tasks per second, and low latency, i.e., incurring minimal scheduling delays for millisecond-level tasks. Scheduling is further complicated by other users' workloads in a shared system, other background activities, and the diverse hardware configurations inside datacenters.…
Performance-, power-, and energy-aware scheduling techniques play an essential role in optimally utilizing processing elements (PEs) of heterogeneous systems. List schedulers, a class of low-complexity static schedulers, have commonly been used in static execution scenarios. However, list schedulers are not suitable for runtime decision making, particularly when multiple concurrent applications are interleaved dynamically. For such cases, the static task execution times and expectation of idle PEs assumed by list schedulers lead to inefficient system utilization and poor performance. To addres…
Domain-specific systems-on-chip (DSSoCs) aim at bridging the gap between application-specific integrated circuits (ASICs) and general-purpose processors. Traditional operating system (OS) schedulers can undermine the potential of DSSoCs since their execution times can be orders of magnitude larger than the execution time of the task itself. To address this problem, we propose a dynamic adaptive scheduling (DAS) framework that combines the benefits of a fast (low-overhead) scheduler and a slow (sophisticated, high-performance but high-overhead) scheduler. Experiments with five real-world stream…
The critical path of a group of tasks is an important measure that is commonly used to guide task allocation and scheduling on parallel computers. The critical path is the longest chain of dependencies in an acyclic task dependence graph. A problem arises on heterogeneous parallel machines where computation and communication costs can vary between different types of processor. Existing solutions for heterogeneous machines attempt to estimate the critical path using average values of computation and communication costs. However, this ignores opportunities to match specific tasks to specific cla…
The efficient scheduling of independent computational tasks in a heterogeneous computing environment is an important problem that occurs in domains such as Grid and Cloud computing. Finding optimal schedules is an NP-hard problem in general, so we have to rely on approximate algorithms to come up schedules that are as near to optimal as possible. In our previous work on this problem, we applied a fast, effective local search to generate reasonably good schedules in a short amount of time and used ant colony optimisation (ACO) to incrementally improve those schedules over a longer time period. …
Hard real-time systems like image processing, autonomous driving, etc. require an increasing need of computational power that classical multi-core platforms can not provide, to fulfill with their timing constraints. Heterogeneous Instruction Set Architecture (ISA) platforms allow accelerating real-time workloads on application-specific cores (e.g. GPU, DSP, ASICs) etc. and are suitable for these applications. In addition, these platforms provide larger design choices as a given functionnality can be implemented onto several types of compute elements. HPC-DAG (Heterogeneous Parallel Directed Ac…
East China Normal University（华东师范大学）；Huawei Cloud Computing Technologies Co.（华为云计算技术有限公司）
With the rapid development of cloud computing, virtual machine scheduling has become one of the most important but challenging issues for the cloud computing community, especially for practical heterogeneous request sequences. By analyzing the impact of request heterogeneity on some popular heuristic schedulers, it can be found that existing scheduling algorithms can not handle the request heterogeneity properly and efficiently. In this paper, a plug-and-play virtual machine scheduling intensifier, called Resource Assigner (ReAssigner), is proposed to enhance the scheduling efficiency of any g…
Scientific workflows typically comprise a multitude of different processing steps which often are executed in parallel on different partitions of the input data. These executions, in turn, must be scheduled on the compute nodes of the computational infrastructure at hand. This assignment is complicated by the facts that (a) tasks typically have highly heterogeneous resource requirements and (b) in many infrastructures, compute nodes offer highly heterogeneous resources. In consequence, predictions of the runtime of a given task on a given node, as required by many scheduling algorithms, are of…
In this paper, a method for efficient scheduling to obtain optimum job throughput in a distributed campus grid environment is presented; Traditional job schedulers determine job scheduling using user and job resource attributes. User attributes are related to current usage, historical usage, user priority and project access. Job resource attributes mainly comprise of soft requirements (compilers, libraries) and hard requirements like memory, storage and interconnect. A job scheduler dispatches jobs to a resource if a job's hard and soft requirements are met by a resource. In current scenario d…
Modern production data processing and machine learning pipelines on the cloud are critical components for many cloud-based companies. These pipelines are typically composed of complex workflows represented by directed acyclic graphs (DAGs). Cloud environments are attractive to these workflows due to the wide range of choice with heterogeneous instances and prices that can provide the flexibility for different cost-performance needs. However, this flexibility also leads to the complexity of selecting the right resource configuration (e.g., instance type, resource demands) for each task in the D…
Heterogeneity has grown in popularity both at the core and server level as a way to improve both performance and energy efficiency. However, despite these benefits, scheduling applications in heterogeneous machines remains challenging. Additionally, when these heterogeneous resources accommodate multiple applications to increase utilization, resources are prone to contention, destructive interference, and unpredictable performance. Existing solutions examine heterogeneity either across or within a server, leading to missed performance and efficiency opportunities. We present Mage, a practical …
The tremendous increase in the size and heterogeneity of supercomputers makes it very difficult to predict the performance of a scheduling algorithm. Therefore, dynamic solutions, where scheduling decisions are made at runtime have overpassed static allocation strategies. The simplicity and efficiency of dynamic schedulers such as Hadoop are a key of the success of the MapReduce framework. Dynamic schedulers such as StarPU, PaRSEC or StarSs are also developed for more constrained computations, e.g. task graphs coming from linear algebra. To make their decisions, these runtime systems make use …
In this paper, to analyze end-to-end timing behavior in heterogeneous processor and network environments accurately, we adopt a heterogeneous selection value on communication contention (HSV_CC) algorithm, which can synchronize tasks and messages simultaneously, for stream processing distribution. In order to adapt HSV_CC to automotive data stream management system (DSMSs), one must address three issues: (i) previous task and message schedules might lead to less efficient resource usages; (ii) the conventional method to determine the task scheduling order may not be best suited to deal with st…
Heterogeneous multi core processors can offer diverse computing capabilities. The efficiency of Market Basket Analysis Algorithm can be improved with heterogeneous multi core processors. Market basket analysis algorithm utilises apriori algorithm and is one of the popular data mining algorithms which can utilise Map/Reduce framework to perform analysis. The algorithm generates association rules based on transactional data and Map/Reduce motivates to redesign and convert the existing sequential algorithms for efficiency. Hadoop is the parallel programming platform built on Hadoop Distributed Fi…
Modern commodity computing systems are composed by a number of different heterogeneous processing units, each of which has its own unique performance and energy characteristics. However, the majority of current network packet processing frameworks targets only a specific processing unit (either the CPU or accelerator), leaving the remaining computational resources under-utilized or even idle. In this paper, we propose an adaptive scheduling approach for network packet processing applications, that supports any heterogeneous and asymmetric architectures that can be found in a commodity high-end…
Federated Learning (FL) is a decentralized machine-learning paradigm, in which a global server iteratively averages the model parameters of local users without accessing their data. User heterogeneity has imposed significant challenges to FL, which can incur drifted global models that are slow to converge. Knowledge Distillation has recently emerged to tackle this issue, by refining the server model using aggregated knowledge from heterogeneous users, other than directly averaging their model parameters. This approach, however, depends on a proxy dataset, making it impractical unless such a pr…
Specialized accelerators such as GPUs, TPUs, FPGAs, and custom ASICs have been increasingly deployed to train deep learning models. These accelerators exhibit heterogeneous performance behavior across model architectures. Existing schedulers for clusters of accelerators, which are used to arbitrate these expensive training resources across many users, have shown how to optimize for various multi-job, multi-user objectives, like fairness and makespan. Unfortunately, existing schedulers largely do not consider performance heterogeneity. In this paper, we propose Gavel, a heterogeneity-aware sche…
Systems-on-Chips (SoCs) that power autonomous vehicles (AVs) must meet stringent performance and safety requirements prior to deployment. With increasing complexity in AV applications, the system needs to meet these real-time demands of multiple safety-critical applications simultaneously. A typical AV-SoC is a heterogeneous multiprocessor consisting of accelerators supported by general-purpose cores. Such heterogeneity, while needed for power-performance efficiency, complicates the art of task scheduling. In this paper, we demonstrate that hardware heterogeneity impacts the scheduler's effect…
Domain-specific systems-on-chip, a class of heterogeneous many-core systems, are recognized as a key approach to narrow down the performance and energy-efficiency gap between custom hardware accelerators and programmable processors. Reaching the full potential of these architectures depends critically on optimally scheduling the applications to available resources at runtime. Existing optimization-based techniques cannot achieve this objective at runtime due to the combinatorial nature of the task scheduling problem. As the main theoretical contribution, this paper poses scheduling as a classi…
Today's clusters often have to divide resources among a diverse set of jobs. These jobs are heterogeneous both in execution time and in their rate of arrival. Execution time heterogeneity has lead to the development of hybrid schedulers that can schedule both short and long jobs to ensure good task placement. However, arrival rate heterogeneity, or burstiness, remains a problem in existing schedulers. These hybrid schedulers manage resources on statically provisioned cluster, which can quickly be overwhelmed by bursts in the number of arriving jobs. In this paper we propose CloudCoaster, a hyb…
In order to improve system performance efficiently, a number of systems choose to equip multi-core and many-core processors (such as GPUs). Due to their discrete memory these heterogeneous architectures comprise a distributed system within a computer. A data-flow programming model is attractive in this setting for its ease of expressing concurrency. Programmers only need to define task dependencies without considering how to schedule them on the hardware. However, mapping the resulting task graph onto hardware efficiently remains a challenge. In this paper, we propose a graph-partition schedul…
Personalized recommendation is an important class of deep-learning applications that powers a large collection of internet services and consumes a considerable amount of datacenter resources. As the scale of production-grade recommendation systems continues to grow, optimizing their serving performance and efficiency in a heterogeneous datacenter is important and can translate into infrastructure capacity saving. In this paper, we propose Hercules, an optimized framework for personalized recommendation inference serving that targets diverse industry-representative models and cloud-scale hetero…
In this paper we describe HeSP, a complete simulation framework to study a general task scheduling-partitioning problem on heterogeneous architectures, which treats recursive task partitioning and scheduling decisions on equal footing. Considering recursive partitioning as an additional degree of freedom, tasks can be dynamically partitioned or merged at runtime for each available processor type, exposing additional or reduced degrees of parallelism as needed. Our simulations reveal that, for a specific class of dense linear algebra algorithms taken as a driving example, simultaneous decisions…
In light of continued advances in loop scheduling, this work revisits the OpenMP loop scheduling by outlining the current state of the art in loop scheduling and presenting evidence that the existing OpenMP schedules are insufficient for all combinations of applications, systems, and their characteristics. A review of the state of the art shows that due to the specifics of the parallel applications, the variety of computing platforms, and the numerous performance degradation factors, no single loop scheduling technique can be a 'one-fits-all' solution to effectively optimize the performance of…
Emerging AI-enabled applications such as augmented/virtual reality (AR/VR) leverage multiple deep neural network (DNN) models for sub-tasks such as object detection, hand tracking, and so on. Because of the diversity of the sub-tasks, the layers within and across the DNN models are highly heterogeneous in operation and shape. Such layer heterogeneity is a challenge for a fixed dataflow accelerator (FDA) that employs a fixed dataflow on a single accelerator substrate since each layer prefers different dataflows (computation order and parallelization) and tile sizes. Reconfigurable DNN accelerat…
Many HPC applications can be expressed as mixed-mode computations, in which each node of a computational DAG is itself a parallel computation that can be molded at runtime to allocate different amounts of processing resources. At the same time, modern HPC systems are becoming increasingly heterogeneous to address the requirements of energy efficiency. Effectively using heterogeneous devices is complex, requiring the developer to be aware of each DAG nodes' criticality, and the relative performance of the underlying heterogeneous resources. This paper studies how irregular mixed-mode parallel c…
GrapheonRL: A Graph Neural Network and Reinforcement Learning Framework for Constraint and Data-Aware Workflow Mapping and Scheduling in Heterogeneous HPC Systems
