The Cloud as an OpenMP Offloading Device

Yviquel, Hervé; Araújo, Guido

doi:10.1109/icpp.2017.44

Cited by 4 publications

(4 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Instead of treating cluster nodes as separate devices, Yviquel and Araújo [7] propose a method to handle an entire cloud infrastructure as a single device using map-reduce Spark nodes and remote communication management. Finally, in [8] the authors utilize the device model of OpenMP as an annotation mechanism to denote possibly migratable computation among cluster nodes.…”

Section: Related Workmentioning

confidence: 99%

Experiences with task-based programming using cluster nodes as OpenMP devices

Keftakis¹,

Dimakopoulos²

2022

Preprint

View full text Add to dashboard Cite

Programming a distributed system, such as a cluster, requires extended use of low-level communication libraries and can often become cumbersome and error prone for the average developer. In this work, we consider each node of a cluster as a separate OpenMP device, able to run code with OpenMP directives in parallel. We make use of the OpenMP device model to provide an easy and intuitive way to program available cluster nodes. Based on that, we examine modifications that were necessary to make existing task-based applications able to exploit such an infrastructure. Finally, we evaluate the performance of the system and conclude that one can gain significant speedup, as long as the application tasks do not produce excessive communication overheads.

show abstract

Section: Related Workmentioning

confidence: 99%

Experiences with task-based programming using cluster nodes as OpenMP devices

Keftakis¹,

Dimakopoulos²

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…To illustrate this process, let us consider the matrix multiplication C = A×B presented previously in Listing 1. As shown in Figure 3, the Spark driver node gets the files 1 representing the input data from the cloud storage (HDFS or S3), and loads them as ByteArray objects. It then generates RDD(I ), which contains the successive values taken by the loop index i (0, .…”

Section: Matching Spark Execution Modelmentioning

confidence: 99%

Cluster Programming using the OpenMP Accelerator Model

Yviquel

Cruz

Araújo

2018

ACM Trans. Archit. Code Optim.

Self Cite

View full text Add to dashboard Cite

Computation offloading is a programming model in which program fragments (e.g., hot loops) are annotated so that their execution is performed in dedicated hardware or accelerator devices. Although offloading has been extensively used to move computation to GPUs, through directive-based annotation standards like OpenMP, offloading computation to very large computer clusters can become a complex and cumbersome task. It typically requires mixing programming models (e.g., OpenMP and MPI) and languages (e.g., C/C++ and Scala), dealing with various access control mechanisms from different cloud providers (e.g., AWS and Azure), and integrating all this into a single application. This article introduces computer cluster nodes as simple OpenMP offloading devices that can be used either from a local computer or from the cluster head-node. It proposes a methodology that transforms OpenMP directives to Spark runtime calls with fully integrated communication management, in a way that a cluster appears to the programmer as yet another accelerator device. Experiments using LLVM 3.8, OpenMP 4.5 on well known cloud infrastructures (Microsoft Azure and Amazon EC2) show the viability of the proposed approach, enable a thorough analysis of its performance, and make a comparison with an MPI implementation. The results show that although data transfers can impose overheads, cloud offloading from a local machine can still achieve promising speedups for larger granularity: up to 115× in 256 cores for the 2MM benchmark using 1GB sparse matrices. In addition, the parallel implementation of a complex and relevant scientific application reveals a 80× speedup on a 320 core machine when executed directly from the headnode of the cluster. CCS Concepts: • Computing methodologies → Distributed programming languages; • Software and its engineering → Parallel programming languages; Distributed programming languages; Runtime environments; Source code generation;

show abstract

“…To address such problem, we have previously developed a novel and yet compatible extension of OpenMP 4.X, called OmpCloud 1 . This tool allows programmers to easily integrate computation offloading and MapReduce-based parallelization to remote computer clusters within their software project using simple OpenMP directives [3], [4]. Thus, this would considerably simplifies the integration of cloud render farms to the render engines of 3D modeling softwares for both software developers and designers alike.…”

Section: Introductionmentioning

confidence: 99%

“…[8], [9], we introduced the cloud as a novel target device available on the computer. This was done within a programming framework we call OmpCloud [3] that extends the OpenMP accelerator model to allow transparent cloud offloading and cluster programming. OmpCloud gives the programmer the ability to quickly expand the computing power of their own computer to a large-scale computer cluster available in the cloud.…”

Section: Introductionmentioning

confidence: 99%

Automatic Ray-Tracer Cloud Offloading in OPENMP

Mortatti

Yviquel

Araújo

2018

2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)

Self Cite

View full text Add to dashboard Cite

Rendering an image from a 3D scene requires a large amount of computation which grows exponentially with the complexity of the scene (e.g. number of objects and light sources). With the increasing demand of high definition content, 3D designers need to use high-performance computer systems to keep the rendering time acceptable. Since owning computer clusters is expensive, designers usually rent computing power directly from cloud service providers (e.g. AWS and Azure). However, even though many cloud providers already propose dedicated rendering services, integrating them within the standard workflow of modeling softwares can become a complex and cumbersome task. It typically requires exporting the project from the design software, dealing with various access control mechanisms from different clouds to upload the project, and executing the rendering remotely through command-line. Offloading computation to the cloud is a technique which can considerably simplify such tasks. To achieve that, this paper uses an extension of OpenMP 4.X to eliminate any major interactions with the end-user, while minimizing the complexity of cloud integration and optimizing the design workflow. It applies such approach to a ray-tracing application, a simplified version of the engines used by professional 3D modeling software (e.g. Blender). It automatically offloads the rendering process from the user computer to computer cluster within the Microsoft Azure cloud, brings the resulting images back after the computation ends and displays them directly on the screen of the user computer, thus providing a transparent programming model and good speed-ups over local execution.

show abstract

The Cloud as an OpenMP Offloading Device

Cited by 4 publications

References 28 publications

Experiences with task-based programming using cluster nodes as OpenMP devices

Experiences with task-based programming using cluster nodes as OpenMP devices

Cluster Programming using the OpenMP Accelerator Model

Automatic Ray-Tracer Cloud Offloading in OPENMP

Contact Info

Product

Resources

About