The management of security credentials (e.g., passwords, secret keys) for computational science workflows is a burden for scientists and information security officers. Problems with credentials (e.g., expiration, privilege mismatch) cause workflows to fail to fetch needed input data or store valuable scientific results, distracting scientists from their research by requiring them to diagnose the problems, re-run their computations, and wait longer for their results. In this paper, we introduce SciTokens, open source software to help scientists manage their security credentials more reliably and securely. We describe the SciTokens system architecture, design, and implementation addressing use cases from the Laser Interferometer Gravitational-Wave Observatory (LIGO) Scientific Collaboration and the Large Synoptic Survey Telescope (LSST) projects. We also present our integration with widely-used software that supports distributed scientific computing, including HTCondor, CVMFS, and XrootD. SciTokens uses IETF-standard OAuth tokens for capability-based secure access to remote scientific data. The access tokens convey the specific authorizations needed by the workflows, rather than general-purpose authentication impersonation credentials, to address the risks of scientific workflows running on distributed infrastructure including NSF resources (e.g., LIGO Data Grid, Open Science Grid, XSEDE) and public clouds (e.g., Amazon Web Services, Google Cloud, Microsoft Azure). By improving the interoperability and security of scientific workflows, SciTokens 1) enables use of distributed computing for scientific domains that require greater data protection and 2) enables use of more widely distributed computing resources by reducing the risk of credential abuse on remote systems.
more »
« less
Reproducible Workflow on a Public Cloud for Computational Fluid Dynamics
In a new effort to make our research transparent and reproducible by others, we developed a workflow to run and share computational studies on the public cloud Microsoft Azure. It uses Docker containers to create an image of the application software stack. We also adopt several tools that facilitate creating and managing virtual machines on compute nodes and submitting jobs to these nodes. The configuration files for these tools are part of an expanded "reproducibility package" that includes workflow definitions for cloud computing, input files and instructions. This facilitates re-creating the cloud environment to re-run the computations under identical conditions. We also show that cloud offerings are now adequate to complete computational fluid dynamics studies with in-house research software that uses parallel computing with GPUs. We share with readers what we have learned from nearly two years of using Azure cloud to enhance transparency and reproducibility in our computational simulations.
more »
« less
- Award ID(s):
- 1747669
- NSF-PAR ID:
- 10125028
- Date Published:
- Journal Name:
- Computing in Science & Engineering
- ISSN:
- 1521-9615
- Page Range / eLocation ID:
- 1 to 1
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
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
-
The management of security credentials (e.g., passwords, secret keys) for computational science workflows is a burden for scientists and information security officers. Problems with credentials (e.g., expiration, privilege mismatch) cause workflows to fail to fetch needed input data or store valuable scientific results, distracting scientists from their research by requiring them to diagnose the problems, re-run their computations, and wait longer for their results. SciTokens introduces a capabilities-based authorization infrastructure for distributed scientific computing, to help scientists manage their security credentials more reliably and securely. SciTokens uses IETF-standard OAuth JSON Web Tokens for capability-based secure access to remote scientific data. These access tokens convey the specific authorizations needed by the workflows, rather than general-purpose authentication impersonation credentials, to address the risks of scientific workflows running on distributed infrastructure including NSF resources (e.g., LIGO Data Grid, Open Science Grid, XSEDE) and public clouds (e.g., Amazon Web Services, Google Cloud, Microsoft Azure). By improving the interoperability and security of scientific workflows, SciTokens 1) enables use of distributed computing for scientific domains that require greater data protection and 2) enables use of more widely distributed computing resources by reducing the risk of credential abuse on remote systems. In this extended abstract, we present the results over the past year of our open source implementation of the SciTokens model and its deployment in the Open Science Grid, including new OAuth support added in the HTCondor 8.8 release series.more » « less
-
The HPC community is actively researching and evaluating tools to support execution of scientific applications in cloud-based environ- ments. Among the various technologies, containers have recently gained importance as they have significantly better performance compared to full-scale virtualization, support for microservices and DevOps, and work seamlessly with workflow and orchestration tools. Docker is currently the leader in containerization technology because it offers low overhead, flexibility, portability of applications, and reproducibility. Singularity is another container solution that is of interest as it is designed specifically for scientific applications. It is important to conduct performance and feature analysis of the container technologies to understand their applicability for each application and target execution environment. This paper presents a (1) performance evaluation of Docker and Singularity on bare metal nodes in the Chameleon cloud (2) mecha- nism by which Docker containers can be mapped with InfiniBand hardware with RDMA communication and (3) analysis of mapping elements of parallel workloads to the containers for optimal re- source management with container-ready orchestration tools. Our experiments are targeted toward application developers so that they can make informed decisions on choosing the container tech- nologies and approaches that are suitable for their HPC workloads on cloud infrastructure. Our performance analysis shows that sci- entific workloads for both Docker and Singularity based containers can achieve near-native performance. Singularity is designed specifically for HPC workloads. However, Docker still has advantages over Singularity for use in clouds as it provides overlay networking and an intuitive way to run MPI applications with one container per rank for fine-grained resources allocation. Both Docker and Singularity make it possible to directly use the underlying network fabric from the containers for coarse- grained resource allocation.more » « less
-
Credibility building activities in computational research include verification and validation, reproducibility and replication, and uncertainty quantification. Though orthogonal to each other, they are related. This paper presents validation and replication studies in electromagnetic excitations on nanoscale structures, where the quantity of interest is the wavelength at which resonance peaks occur. The study uses the open-source software PyGBe : a boundary element solver with treecode acceleration and GPU capability. We replicate a result by Rockstuhl et al. (2005, doi:10/dsxw9d) with a two-dimensional boundary element method on silicon carbide (SiC) particles, despite differences in our method. The second replication case from Ellis et al. (2016, doi:10/f83zcb) looks at aspect ratio effects on high-order modes of localized surface phonon-polariton nanostructures. The results partially replicate: the wavenumber position of some modes match, but for other modes they differ. With virtually no information about the original simulations, explaining the discrepancies is not possible. A comparison with experiments that measured polarized reflectance of SiC nano pillars provides a validation case. The wavenumber of the dominant mode and two more do match, but differences remain in other minor modes. Results in this paper were produced with strict reproducibility practices, and we share reproducibility packages for all, including input files, execution scripts, secondary data, post-processing code and plotting scripts, and the figures (deposited in Zenodo). In view of the many challenges faced, we propose that reproducible practices make replication and validation more feasible. This article is part of the theme issue ‘Reliability and reproducibility in computational science: implementing verification, validation and uncertainty quantification in silico ’.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1109/MCSE.2019.2941702
