Lynx

Tork, Maroun; Maudlej, Lina; Silberstein, Mark

doi:10.1145/3373376.3378528

Cited by 48 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We believe that the status quo is equivalent to writing software without semantic interfaces. With accelerators expected to become ubiquitous in the near future [44,61], this status quo must change.…”

Section: Example #3: Compilers For Acceleratorsmentioning

confidence: 99%

The Case for Performance Interfaces for Hardware Accelerators

Iyer

Argyraki

et al. 2023

Proceedings of the 19th Workshop on Hot Topics in Operating Systems

View full text Add to dashboard Cite

While systems designers are increasingly turning to hardware accelerators for performance gains, realizing these gains is painstaking and error-prone. It can take several person-months to determine if a given accelerator is a good fit for a given piece of code, and accelerators that cost millions of dollars to build can slow down the very systems they were designed to accelerate.We argue that hardware accelerators must come with performance interfaces-interfaces that provide usable information about the accelerator's performance behavior just like semantic interfaces do for functionality-to facilitate their correct use. Since accelerators do not provide new functionality and are only useful if they improve system performance, performance interfaces are as integral to their correct use as semantic interfaces.

show abstract

Section: Example #3: Compilers For Acceleratorsmentioning

confidence: 99%

The Case for Performance Interfaces for Hardware Accelerators

Iyer

Argyraki

et al. 2023

Proceedings of the 19th Workshop on Hot Topics in Operating Systems

View full text Add to dashboard Cite

show abstract

“…Several prior works highlight the limitations of a centralized OS architecture in heterogeneous systems, such as lack of network and storage abstractions for GPUs [24,39,54]. Lynx [56] focused on a server architecture that uses SmartNICs to manage accelerators in acceleratorheavy servers. OmniX [53] and Helios [36] are acceleratorcentric OS architectures that enable decentralized application execution via peer-to-peer interaction among heterogeneous devices in a single server.…”

Section: Related Workmentioning

confidence: 99%

Slashing the disaggregation tax in heterogeneous data centers with FractOS

Vilanova

Maudlej

Bergman

et al. 2022

Proceedings of the Seventeenth European Conference on Computer Systems

Self Cite

View full text Add to dashboard Cite

Disaggregated heterogeneous data centers promise higher efficiency, lower total costs of ownership, and more flexibility for data-center operators. However, current software stacks can levy a high tax on application performance. Applications and OSes are designed for systems where local PCIe-connected devices are centrally managed by CPUs, but this centralization introduces unnecessary messages through the shared data-center network in a disaggregated system.We present FractOS, a distributed OS that is designed to minimize the network overheads of disaggregation in heterogeneous data centers. FractOS elevates devices to be firstclass citizens, enabling direct peer-to-peer data transfers and task invocations among them, without centralized application and OS control. FractOS achieves this through: (1) new abstractions to express distributed applications across services and disaggregated devices, (2) new mechanisms that enable devices to securely interact with each other and other data-center services, (3) a distributed and isolated OS layer that implements these abstractions and mechanisms, and can run on host CPUs and SmartNICs.Our prototype shows that FractOS accelerates real-world heterogeneous applications by 47%, while reducing their network traffic by 3×.

show abstract

Remote Programmability Model for SmartNICs in HPC Workloads

Horany,

Margolin

2022

OpenSHMEM and Related Technologies. OpenSHMEM in the Era of Exascale and Smart Networks

View full text Add to dashboard Cite

Lynx

Cited by 48 publications

References 7 publications

The Case for Performance Interfaces for Hardware Accelerators

The Case for Performance Interfaces for Hardware Accelerators

Slashing the disaggregation tax in heterogeneous data centers with FractOS

Remote Programmability Model for SmartNICs in HPC Workloads

Contact Info

Product

Resources

About