In the era of big data, materials science workflows need to handle large-scale data distribution, storage, and computation. Any of these areas can become a performance bottleneck. We present a framework for analyzing internal material structures (e.g., cracks) to mitigate these bottlenecks. We demonstrate the effectiveness of our framework for a workflow performing synchrotron X-ray computed tomography reconstruction and segmentation of a silica-based structure. Our framework provides a cloud-based, cutting-edge solution to challenges such as growing intermediate and output data and heavy resource demands during image reconstruction and segmentation. Specifically, our framework efficiently manages data storage, scaling up compute resources on the cloud. The multi-layer software structure of our framework includes three layers. A top layer uses Jupyter notebooks and serves as the user interface. A middle layer uses Ansible for resource deployment and managing the execution environment. A low layer is dedicated to resource management and provides resource management and job scheduling on heterogeneous nodes (i.e., GPU and CPU). At the core of this layer, Kubernetes supports resource management, and Dask enables large-scale job scheduling for heterogeneous resources. The broader impact of our work is four-fold: through our framework, we hide the complexity of the cloud’s software stack to the user who otherwise is required to have expertise in cloud technologies; we manage job scheduling efficiently and in a scalable manner; we enable resource elasticity and workflow orchestration at a large scale; and we facilitate moving the study of nonporous structures, which has wide applications in engineering and scientific fields, to the cloud. While we demonstrate the capability of our framework for a specific materials science application, it can be adapted for other applications and domains because of its modular, multi-layer architecture.
more »
« less
Managing Allocatable Resources
Infrastructure cloud computing allows its clients to allocate on-demand resources, typically consisting of a repre- sentation of a compute node. In general however, there is a need for allocating resources other than nodes and managing them in more controlled ways than simply on demand. This paper generalizes the familiar “compute power on demand” pattern by introducing the abstraction of an allocatable resource, describing its properties, and implementation for different types of resources. We further describe architecture for a generic allocatable resource management service that can be extended to manage diverse types of resources as well as the implementation of this architecture in the OpenStack Blazar service to manage resources ranging from bare-metal compute nodes to network segments. Finally, we provide a usage analysis of this service on the Chameleon testbed and use it to illustrate the effectiveness of resource management methods as well as the need for incentives in usage arbitration.
more »
« less
- Award ID(s):
- 1743358
- NSF-PAR ID:
- 10107201
- Date Published:
- Journal Name:
- IEEE ... International Conference on Cloud Computing
- ISSN:
- 2159-6190
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
null (Ed.)Edge computing is an attractive architecture to efficiently provide compute resources to many applications that demand specific QoS requirements. The edge compute resources are in close geographical proximity to where the applications’ data originate from and/or are being supplied to, thus avoiding unnecessary back and forth data transmission with a data center far away. This paper describes a federated edge computing system in which compute resources at multiple edge sites are dynamically aggregated together to form distributed super-cloudlets and best respond to varying application-driven loads. In its simplest form a super-cloudlet consists of compute resources available at two edge computing sites or cloudlets that are (temporarily) interconnected by dedicated optical circuits deployed to enable low-latency and high-rate data exchanges. A super-cloudlet architecture is experimentally demonstrated over the largest public OpenROADM optical network testbed up to date consisting of commercial equipment from six suppliers. The software defined networking (SDN) PROnet Orchestrator is upgraded to both concurrently manage the resources offered by the optical network equipment, compute nodes, and associated Ethernet switches and achieve three key functionalities of the proposed super-cloudlet architecture, i.e., service placement, auto-scaling, and offloading.more » « less
-
Obeid, I. ; Selesnik, I. ; Picone, J. (Ed.)The Neuronix high-performance computing cluster allows us to conduct extensive machine learning experiments on big data [1]. This heterogeneous cluster uses innovative scheduling technology, Slurm [2], that manages a network of CPUs and graphics processing units (GPUs). The GPU farm consists of a variety of processors ranging from low-end consumer grade devices such as the Nvidia GTX 970 to higher-end devices such as the GeForce RTX 2080. These GPUs are essential to our research since they allow extremely compute-intensive deep learning tasks to be executed on massive data resources such as the TUH EEG Corpus [2]. We use TensorFlow [3] as the core machine learning library for our deep learning systems, and routinely employ multiple GPUs to accelerate the training process. Reproducible results are essential to machine learning research. Reproducibility in this context means the ability to replicate an existing experiment – performance metrics such as error rates should be identical and floating-point calculations should match closely. Three examples of ways we typically expect an experiment to be replicable are: (1) The same job run on the same processor should produce the same results each time it is run. (2) A job run on a CPU and GPU should produce identical results. (3) A job should produce comparable results if the data is presented in a different order. System optimization requires an ability to directly compare error rates for algorithms evaluated under comparable operating conditions. However, it is a difficult task to exactly reproduce the results for large, complex deep learning systems that often require more than a trillion calculations per experiment [5]. This is a fairly well-known issue and one we will explore in this poster. Researchers must be able to replicate results on a specific data set to establish the integrity of an implementation. They can then use that implementation as a baseline for comparison purposes. A lack of reproducibility makes it very difficult to debug algorithms and validate changes to the system. Equally important, since many results in deep learning research are dependent on the order in which the system is exposed to the data, the specific processors used, and even the order in which those processors are accessed, it becomes a challenging problem to compare two algorithms since each system must be individually optimized for a specific data set or processor. This is extremely time-consuming for algorithm research in which a single run often taxes a computing environment to its limits. Well-known techniques such as cross-validation [5,6] can be used to mitigate these effects, but this is also computationally expensive. These issues are further compounded by the fact that most deep learning algorithms are susceptible to the way computational noise propagates through the system. GPUs are particularly notorious for this because, in a clustered environment, it becomes more difficult to control which processors are used at various points in time. Another equally frustrating issue is that upgrades to the deep learning package, such as the transition from TensorFlow v1.9 to v1.13, can also result in large fluctuations in error rates when re-running the same experiment. Since TensorFlow is constantly updating functions to support GPU use, maintaining an historical archive of experimental results that can be used to calibrate algorithm research is quite a challenge. This makes it very difficult to optimize the system or select the best configurations. The overall impact of all of these issues described above is significant as error rates can fluctuate by as much as 25% due to these types of computational issues. Cross-validation is one technique used to mitigate this, but that is expensive since you need to do multiple runs over the data, which further taxes a computing infrastructure already running at max capacity. GPUs are preferred when training a large network since these systems train at least two orders of magnitude faster than CPUs [7]. Large-scale experiments are simply not feasible without using GPUs. However, there is a tradeoff to gain this performance. Since all our GPUs use the NVIDIA CUDA® Deep Neural Network library (cuDNN) [8], a GPU-accelerated library of primitives for deep neural networks, it adds an element of randomness into the experiment. When a GPU is used to train a network in TensorFlow, it automatically searches for a cuDNN implementation. NVIDIA’s cuDNN implementation provides algorithms that increase the performance and help the model train quicker, but they are non-deterministic algorithms [9,10]. Since our networks have many complex layers, there is no easy way to avoid this randomness. Instead of comparing each epoch, we compare the average performance of the experiment because it gives us a hint of how our model is performing per experiment, and if the changes we make are efficient. In this poster, we will discuss a variety of issues related to reproducibility and introduce ways we mitigate these effects. For example, TensorFlow uses a random number generator (RNG) which is not seeded by default. TensorFlow determines the initialization point and how certain functions execute using the RNG. The solution for this is seeding all the necessary components before training the model. This forces TensorFlow to use the same initialization point and sets how certain layers work (e.g., dropout layers). However, seeding all the RNGs will not guarantee a controlled experiment. Other variables can affect the outcome of the experiment such as training using GPUs, allowing multi-threading on CPUs, using certain layers, etc. To mitigate our problems with reproducibility, we first make sure that the data is processed in the same order during training. Therefore, we save the data from the last experiment and to make sure the newer experiment follows the same order. If we allow the data to be shuffled, it can affect the performance due to how the model was exposed to the data. We also specify the float data type to be 32-bit since Python defaults to 64-bit. We try to avoid using 64-bit precision because the numbers produced by a GPU can vary significantly depending on the GPU architecture [11-13]. Controlling precision somewhat reduces differences due to computational noise even though technically it increases the amount of computational noise. We are currently developing more advanced techniques for preserving the efficiency of our training process while also maintaining the ability to reproduce models. In our poster presentation we will demonstrate these issues using some novel visualization tools, present several examples of the extent to which these issues influence research results on electroencephalography (EEG) and digital pathology experiments and introduce new ways to manage such computational issues.more » « less
-
null (Ed.)Nearly all principal cloud providers now provide burstable instances in their offerings. The main attraction of this type of instance is that it can boost its performance for a limited time to cope with workload variations. Although burstable instances are widely adopted, it is not clear how to efficiently manage them to avoid waste of resources. In this paper, we use predictive data analytics to optimize the management of burstable instances. We design CEDULE+, a data-driven framework that enables efficient resource management for burstable cloud instances by analyzing the system workload and latency data. CEDULE+ selects the most profitable instance type to process incoming requests and controls CPU, I/O, and network usage to minimize the resource waste without violating Service Level Objectives (SLOs). CEDULE+ uses lightweight profiling and quantile regression to build a data-driven prediction model that estimates system performance for all combinations of instance type, resource type, and system workload. CEDULE+ is evaluated on Amazon EC2, and its efficiency and high accuracy are assessed through real-case scenarios. CEDULE+ predicts application latency with errors less than 10%, extends the maximum performance period of a burstable instance up to 2.4 times, and decreases deployment costs by more than 50%.more » « less
-
To scale the Internet of Things (IoT) beyond a single home or enterprise, we need an effective mechanism to manage the growth of data, facilitate resource discovery and name resolution, encourage data sharing, and foster cross-domain services. To address these needs, we propose a GlObaL Directory for Internet of Everything (GOLDIE). GOLDIE is a hierarchical location-based IoT directory architecture featuring diverse user-oriented modules and federated identity management. IoT-specific features include discoverability, aggregation and geospatial queries, and support for global access. We implement and evaluate the prototype on a Raspberry Pi and Intel mini servers. We show that a global implementation of GOLDIE could decrease service access latency by 87% compared to a centralized-server solution.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- The DOI is not currently available.
