A platform for FPGA virtualization in clouds and data centers

Al-Aghbari, Amran; Elrabaa, Muhammad E. S.

doi:10.1016/j.micpro.2018.07.010

Cited by 8 publications

(10 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Al-Aghbari and Elrabaa [9] proposed a scheme that supports MFMA virtualization. It performs resource-level virtualization in FPGA's I/O channels and uses networkattached FPGAs.…”

Section: A Fpga Virtualization Approachesmentioning

confidence: 99%

Virtualizing and Scheduling FPGA Resources in Cloud Computing Datacenters

et al. 2022

View full text Add to dashboard Cite

Cloud service providers consistently leverage their computing infrastructures by adding reconfigurable hardware platforms such as field-programmable gate arrays (FPGAs) to their existing infrastructures. Adding FPGAs to a cloud environment involves non-trivial challenges. The first challenge is virtualizing FPGAs as part of the cloud resources. As a standard virtualization framework is lacking, there is a need for an efficient framework for virtualizing FPGAs. Furthermore, FPGA resources are used in conjunction with central processing units (CPUs) and graphics processing units (GPUs) to accelerate the execution of tasks. Therefore, to gain the benefits of these powerful accelerating platforms, the second challenge is to optimize the allocation of tasks into the capable resources within a cloud data center. This work proposes an FPGA virtualization framework that abstracts the physical FPGAs into virtual pools of FPGA resources. The work further presents an integer linear programming (ILP) optimization model to minimize the makespan of tasks where FPGA resources are part of the cloud data center. Given the complex nature of the problem, a simulated annealing (SA) metaheuristic is developed to achieve gains in performance compared to the exact method and to scale up and handle many tasks and resources while providing nearoptimal solutions. Experimental results show that SA has reduced the makespan of a large dataset with 1000 tasks and 100 resources by up to 30% when compared to first-come-first-served (FCFS) and shortestdeadline-first (SDF) algorithms. Lastly, to quantify the performance of FPGA-enabled cloud datacenters, the work extends the CloudSim simulator (an open-source cloud simulator) to enable FPGA as a resource in its environment. The proposed virtualization framework and the SA scheduler are integrated into the environment. Simulation results show that the execution time of tasks is reduced by up to 78% when FPGA accelerators are used.

show abstract

“…Al-Aghbari and Elrabaa [9] proposed a scheme that supports MFMA virtualization. It performs resource-level virtualization in FPGA's I/O channels and uses networkattached FPGAs.…”

Section: A Fpga Virtualization Approachesmentioning

confidence: 99%

Virtualizing and Scheduling FPGA Resources in Cloud Computing Datacenters

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Still, all these methods require the application developer to redesign the hardware and adapt its interface to match the shell/role interface. In our previous work, we have completely abstracted the virtual FPGA I/Os [27] by integrating an auto-generated wrapper as an abstraction layer between the shell and the role.…”

Section: Related Workmentioning

confidence: 99%

“…In this work, we introduce an API-based (Application Programming Interface) framework for FPGAs attached as stand-alone resources in a public cloud setting. The proposed framework builds on and utilizes our FPGA virtualization scheme [27], and can be easily integrated with any cloud management system. Additional circuitry has been added to the vFPGA platform to secure all traffic between the HW application and the user.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Cloud-Based FPGA Custom Computing Machines for Streaming Applications

Al-Aghbari

Elrabaa

2019

IEEE Access

Self Cite

View full text Add to dashboard Cite

A novel platform for launching and using field-programmable gate arrays (FPFA) custom computing machines (CCMs) in clouds and data centers is proposed. Based on a developed FPGA virtualization scheme, it allows users to create independent computing services on network-attached standalone FPGAs. The interface of the virtual FPGA (vFPGA)-based CCM is automatically generated by a virtualization layer and based on the user's specifications. An FPGA hypervisor has been developed that can be easily integrated with any cloud management tool. It allows the users to launch/use/tear down vFPGA-based CCMs in a similar manner to conventional virtual machines (VMs). A complete prototype of the proposed platform has been realized and tested with a streamed image processing application. Its performance was 3-4x and ∼1.4-2.4x times better than an SW implementation on a VM and a powerful server, respectively. Compared with other platforms for FPGA attachment to a cloud or datacenter, the proposed platform has relatively low overhead in terms of FPGA resources while providing the highest level of abstraction and virtualization. INDEX TERMS Reconfigurable computing, FPGAs, custom computing machines, cloud computing, streamed applications.

show abstract

“…The proposed system is capable of statically sharing predefined co-processors in a single FPGA among a host and several virtual machines; therefore, co-processors are not shareable between domains, while in [115] the system gets augmented with partial reconfiguration support. In [3] A. Al-Aghbari et al…”

Section: Resource Virtualization and Frameworkmentioning

confidence: 99%

UniLogic (unified logic)

Ιωάννου¹

View full text Add to dashboard Cite

Οι εφαρμογές HPC γίνονται όλο και πιο απαιτητικές σε απόδοση και σε ενέργεια, πιέζοντας τα συστήματα στα όριά τους. Τα συστήματα HPC δεν έχουν ακόμη φτάσει σε απόδοση ex-ascale, κυρίως λόγω ενεργειακών περιορισμών, ενώ θα απαιτούνταν περίπου 100-200 MWatts για να φτάσουν την απόδοση σε επίπεδο exaflop. Μια πολλά υποσχόμενη λύση είναι η χρησιμοποίηση ενεργειακά-αποδοτικών επαναδιαμορφώσιμων πόρων, στη μορφή των FPGAs. Ωστόσο, τα σημερινά περιβάλλοντα για FPGAs είναι βελτιστοποιημένα για να επιταχύνουν μία μόνο εφαρμογή, σε μία μόνο FPGA. Σε αυτή τη διατριβή παρουσιάζουμε το UNILOGIC (Ενοποιημένη Λογική), μία πρότυπη, παράλληλη αρχιτεκτονική προσαρμοσμένη για HPC, η οποία συμπεριλαμβάνει αποδοτικά τις FPGAs. Το UNILOGIC υιοθετεί το μοντέλο PGAS στο οποίο συμπεριλαμβάνει και τους επιταχυντές υλικού. Έτσι (i) η πρόσβαση στους επιταχυντές μπορεί να γίνει απευθείας από οποιονδήποτε επεξεργαστή στο σύστημα και (ii) οι επιταχυντές μπορούν να έχουν πρόσβαση σε οποιαδήποτε θέση μνήμης στο σύστημα. Με τον τρόπο αυτό, η προτεινόμενη αρχιτεκτονική προσφέρει ένα ενοποιημένο περιβάλλον όπου όλοι οι επαναδιαμορφώσιμοι πόροι μπορούν να χρησιμοποιηθούν απρόσκοπτα από οποιοδήποτε επεξεργαστή/λειτουργικό σύστημα. H αρχιτεκτονική UNILOGIC αξιολογήθηκε σε ένα πρωτότυπο που φιλοξενεί συνολικά 64 Zynq MPSoCs και 1 Terabyte μνήμης. H αρχιτεκτονική UNILOGIC προσφέρει επιδόσεις που κυμαίνονται από 3 έως 400 φορές ταχύτερες και 46 έως 370 φορές πιο αποδοτικές ενεργειακά σε σχέση με συστήματα που χρησιμοποιούν CPUs, ενώ υπερβαίνουν τις GPU από 6 έως 20 φορές από πλευράς απαιτούμενου χρόνου επίλυσης, και από 8 έως 20 φορές από πλευράς απαιτούμενης ενέργειας για τη λύση.

show abstract

A platform for FPGA virtualization in clouds and data centers

Cited by 8 publications

References 4 publications

Virtualizing and Scheduling FPGA Resources in Cloud Computing Datacenters

Virtualizing and Scheduling FPGA Resources in Cloud Computing Datacenters

Cloud-Based FPGA Custom Computing Machines for Streaming Applications

UniLogic (unified logic)

Contact Info

Product

Resources

About