An official website of the United States government
While distributed computing infrastructures can provide infrastructure-level techniques for managing energy consumption, application-level energy consumption models have also been developed to support energy-efficient scheduling and resource provisioning algorithms. In this work, we analyze the accuracy of a widely-used application-level model that have been developed and used in the context of scientific workflow executions. To this end, we profile two production scientific workflows on a distributed platform instrumented with power meters. We then conduct an analysis of power and energy consumption measurements. This analysis shows that power consumption is not linearly related to CPU utilization and that I/O operations significantly impact power, and thus energy, consumption. We then propose a power consumption model that accounts for I/O operations, including the impact of waiting for these operations to complete, and for concurrent task executions on multi-socket, multi-core compute nodes. We implement our proposed model as part of a simulator that allows us to draw direct comparisons between real-world and modeled power and energy consumption. We find that our model has high accuracy when compared to real-world executions. Furthermore, our model improves accuracy by about two orders of magnitude when compared to the traditional models used in the energy-efficient workflow scheduling literature.
more »
« less
Evaluating Energy-Aware Scheduling Algorithms for I/O-Intensive Scientific Workflows
Improving energy efficiency has become necessary to enable sustainable computational science. At the same time, scientific workflows are key in facilitating distributed computing in virtually all domain sciences. As data and computational requirements increase, I/O-intensive workflows have become prevalent. In this work, we evaluate the ability of twopopular energy-aware workflow scheduling algorithms to provide effective schedules for this class of workflow applications, that is, schedules that strike a good compromise between workflow execution time and energy consumption. These two algorithms make decisions based on a widely used power consumption model that simply assumes linear correlation to CPU usage. Previous work has shown this model to be inaccurate, in particular for modeling power consumption of I/O-intensive workflow executions, and has proposed an accurate model. We evaluate the effectiveness of the two aforementioned algorithms based on this accurate model. We find that, when making their decisions, these algorithms can underestimate power consumption by up to 360{\%}, which makes it unclear how well these algorithm would fare in practice. To evaluate the benefit of using the more accurate power consumption model in practice, we propose a simple scheduling algorithm that relies on this model to balance the I/O load across the available compute resources. Experimental results show that this algorithm achieves more desirable compromises between energy consumption and workflow execution time than the two popular algorithms.
more »
« less
- PAR ID:
- 10283861
- Date Published:
- Journal Name:
- Computational Science - ICCS 2021
- Page Range / eLocation ID:
- 183-197
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
When designing an algorithm, one cares about arithmetic/compu- tational complexity, but data movement (I/O) complexity plays an increasingly important role that highly impacts performance and energy consumption. For a given algorithm and a given I/O model, scheduling strategies such as loop tiling can reduce the required I/O down to a limit, called the I/O complexity, inherent to the algorithm itself. The objective of I/O complexity analysis is to compute, for a given program, its minimal I/O requirement among all valid schedules. We consider a sequential execution model with two memories, an infinite one, and a small one of size 𝑆 on which the computations retrieve and produce data. The I/O is the number of reads and writes between the two memories. We identify a common “hourglass pattern” in the dependency graphs of several common linear algebra kernels. Using the proper- ties of this pattern, we mathematically prove tighter lower bounds on their I/O complexity, which improves the previous state-of-the- art bound by a parametric ratio. This proof was integrated inside the IOLB automatic lower bound derivation tool.more » « less
-
On the Feasibility of Simulation-driven Portfolio Scheduling for Cyberinfrastructure Runtime SystemsRuntime systems that automate the execution of applications on distributed cyberinfrastructures need to make scheduling deci- sions. Researchers have proposed many scheduling algorithms, but most of them are designed based on analytical models and assumptions that may not hold in practice. The literature is thus rife with algorithms that have been evaluated only within the scope of their underlying as- sumptions but whose practical effectiveness is unclear. It is thus difficult for developers to decide which algorithm to implement in their runtime systems. To obviate the above difficulty, we propose an approach by which the runtime system executes, throughout application execution, simulations of this very execution. Each simulation is for a different algorithm in a scheduling algorithm portfolio, and the best algorithm is selected based on simulation results. The main objective of this work is to evaluate the feasibility and potential merit of this portfolio scheduling approach, even in the presence of simulation inaccuracy, when compared to the traditional one-algorithm approach. We perform this evaluation via a case study in the context of scientific workflows. Our main finding is that portfolio scheduling can outperform the best one-algorithm approach even in the presence of relatively large simulation inaccuracies.more » « less
-
null (Ed.)We propose Zygarde --- which is an energy- and accuracy-aware soft real-time task scheduling framework for batteryless systems that flexibly execute deep learning tasks1 that are suitable for running on microcontrollers. The sporadic nature of harvested energy, resource constraints of the embedded platform, and the computational demand of deep neural networks (DNNs) pose a unique and challenging real-time scheduling problem for which no solutions have been proposed in the literature. We empirically study the problem and model the energy harvesting pattern as well as the trade-off between the accuracy and execution of a DNN. We develop an imprecise computing-based scheduling algorithm that improves the timeliness of DNN tasks on intermittently powered systems. We evaluate Zygarde using four standard datasets as well as by deploying it in six real-life applications involving audio and camera sensor systems. Results show that Zygarde decreases the execution time by up to 26% and schedules 9% -- 34% more tasks with up to 21% higher inference accuracy, compared to traditional schedulers such as the earliest deadline first (EDF).more » « less
-
Scientific workflows drive most modern large-scale science breakthroughs by allowing scientists to define their computations as a set of jobs executed in a given order based on their data dependencies. Workflow management systems (WMSs) have become key to automating scientific workflows-executing computational jobs and orchestrating data transfers between those jobs running on complex high-performance computing (HPC) platforms. Traditionally, WMSs use files to communicate between jobs: a job writes out files that are read by other jobs. However, HPC machines face a growing gap between their storage and compute capabilities. To address that concern, the scientific community has adopted a new approach called in situ, which bypasses costly parallel filesystem I/O operations with faster in-memory or in-network communications. When using in situ approaches, communication and computations can be interleaved. In this work, we leverage the Decaf in situ dataflow framework to accelerate task-based scientific workflows managed by the Pegasus WMS, by replacing file communications with faster MPI messaging. We propose a new execution engine that uses Decaf to manage communications within a sub-workflow (i.e., set of jobs) to optimize inter-job communications. We consider two workflows in this study: (i) a synthetic workflow that benchmarks and compares file- and MPI-based communication; and (ii) a realistic bioinformatics workflow that computes mu-tational overlaps in the human genome. Experiments show that in situ communication can improve the bioinformatics workflow execution time by 22% to 30% compared with file communication. Our results motivate further opportunities and challenges for bridging traditional WMSs with in situ frameworks.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1007/978-3-030-77961-0_16
