Scientific workflows are often represented as directed acyclic graphs (DAGs), where vertices correspond to tasks and edges represent the dependencies between them. Since these graphs are often large in both the number of tasks and their resource requirements, it is important to schedule them efficiently on parallel or distributed compute systems. Typically, each task requires a certain amount of memory to be executed and needs to communicate data to its successor tasks. The goal is thus to execute the workflow as fast as possible (i.e., to minimize its makespan) while satisfying the memory constraints. Hence, we investigate the partitioning and mapping of DAG-shaped workflows onto heterogeneous platforms where each processor can have a different speed and a different memory size. We first propose a baseline algorithm in the absence of existing memory-aware solutions. As our main contribution, we then present a four-step heuristic. Its first step is to partition the input DAG into smaller blocks with an existing DAG partitioner. The next two steps adapt the resulting blocks of the DAG to fit the processor memories and optimize for the overall makespan by further splitting and merging these blocks. Finally, we use local search via block swaps to further improve the makespan. Our experimental evaluation on real-world and simulated workflows with up to 30,000 tasks shows that exploiting the heterogeneity with the four-step heuristic reduces the makespan by a factor of 2.44 on average (even more on large workflows), compared to the baseline that ignores heterogeneity.
Global Optimization of Data Pipelines in Heterogeneous Cloud Environments
云上的现代生产数据处理和机器学习管道是许多基于云的公司的关键组件。这些管道通常由复杂的工作流组成，这些工作流由有向无环图（DAG）表示。云环境对这些工作流很有吸引力，因为它具有异构实例和价格的广泛选择，可以为不同的性价比需求提供灵活性。然而，这种灵活性也导致选择正确的资源配置的复杂性（例如，实例类型、资源需求），同时使用选定的资源调度任务，以达到最佳的端到端性能和成本。这两个决策往往是相互依赖的，导致NP-难调度优化瓶颈。现有的解决方案只关注这两个问题中的任何一个，而忽略了端到端优化的共同影响。我们提出了AGORA，一个调度器，同时考虑任务级资源分配和执行DAG工作流作为一个整体，在异构云环境。AGORA首先（1）研究先前运行的任务的特征，并给出资源配置的预测，并且（2）自动为整个工作流找到最佳配置及其相应的调度，具有成本性能目标。我们在异构的Amazon Web Services（AWS）云环境中评估AGORA，其中多租户工作流由Airflow提供服务，与最先进的服务器相比，性能提高了45%，成本降低了77%。此外，我们将AGORA应用于阿里巴巴的实际生产跟踪，并显示成本降低了65%，DAG完成时间缩短了57%。
GrapheonRL: A Graph Neural Network and Reinforcement Learning Framework for Constraint and Data-Aware Workflow Mapping and Scheduling in Heterogeneous HPC Systems
Serving and Optimizing Machine Learning Workflows on Heterogeneous Infrastructures
Duke University（杜克大学）；Microsoft Research（微软研究院）
随着智能设备和物联网的无处不在的部署，用于机器学习推理的数据源越来越多地移动到网络边缘。现有的机器学习推理平台通常假设同构基础设施，并且不考虑更复杂和分层的计算基础设施，包括边缘设备、本地集线器、边缘计算中心和云计算中心。另一方面，最近的AutoML努力为异构环境的模型压缩、修剪和量化提供了可行的解决方案;对于机器学习模型，现在我们可以很容易地找到甚至生成一系列在准确性和效率之间具有不同权衡的模型。我们设计并实现了JellyBean，一个在异构基础设施上服务和优化机器学习推理工作流的系统。给定服务级别目标（例如，吞吐量、准确性），JellyBean选择符合准确性目标的最具成本效益的模型，并决定如何在不同的基础架构层中部署它们。评估表明，与最先进的模型选择和工人分配解决方案相比，JellyBean将视觉问答的总服务成本降低了58%，将NVIDIA AI城市挑战赛的车辆跟踪成本降低了36%。JellyBean还优于先前的ML服务系统（例如，Spark on the Cloud），服务成本高达5倍。
Enabling Hybrid HPCQC Workflows with a Heterogeneous Software Stack
Leibniz Supercomputing Centre (LRZ)（莱布尼茨超级计算中心）；IQM Quantum Computers (IQM)（IQM量子计算机公司）；Argonne National Laboratory (ANL)（阿贡国家实验室）；Munich Quantum Valley (MQV)（慕尼黑量子谷）
