# Operating System Support for Accelerators as First-Class Compute Elements in Heterogeneous Systems

DevFeed: [Operating System Support for Accelerators as First-Class Compute Elements in Heterogeneous Systems](<https://devfeed.tech/articles/operating-system-support-for-accelerators-as-first-class-compute-elements-in-heterogeneous-systems-101602.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.33380>)

Author: Mohammad Shahidzadeh, Lesley Shannon

Published: 2026-10-27T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>)

Topics: [systems](<https://devfeed.tech/topics/systems.md>), [Linux Kernel](<https://devfeed.tech/topics/linux-kernel.md>), [fpga](<https://devfeed.tech/topics/fpga.md>), [Distributed Systems & Parallel Computing](<https://devfeed.tech/topics/distributed-systems-parallel-computing.md>), [High-Performance Computing](<https://devfeed.tech/topics/high-performance-computing.md>)

Tags: [accelerators](<https://devfeed.tech/tags/accelerators.md>), [communication](<https://devfeed.tech/tags/communication.md>), [cpus](<https://devfeed.tech/tags/cpus.md>), [cs-ar](<https://devfeed.tech/tags/cs-ar.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-os](<https://devfeed.tech/tags/cs-os.md>), [efficiency](<https://devfeed.tech/tags/efficiency.md>), [energy-efficiency](<https://devfeed.tech/tags/energy-efficiency.md>), [fpga](<https://devfeed.tech/tags/fpga.md>), [framework](<https://devfeed.tech/tags/framework.md>), [heterogeneous-systems](<https://devfeed.tech/tags/heterogeneous-systems.md>), [improvements](<https://devfeed.tech/tags/improvements.md>), [interrupt](<https://devfeed.tech/tags/interrupt.md>), [linux](<https://devfeed.tech/tags/linux.md>), [memory](<https://devfeed.tech/tags/memory.md>), [operating-system](<https://devfeed.tech/tags/operating-system.md>), [performance](<https://devfeed.tech/tags/performance.md>), [scheduler](<https://devfeed.tech/tags/scheduler.md>), [scheduling](<https://devfeed.tech/tags/scheduling.md>), [support](<https://devfeed.tech/tags/support.md>)

## AI overview

The abstract identifies software overheads from treating hardware accelerators (HAs) as peripheral devices--communication, invocation, interrupt handling, and scheduling--as a barrier to their performance gains. MEERKAT, an FPGA-based framework for configurable multicore systems, lets researchers move Linux support from software to hardware to study these costs. Proposed mitigations include virtual-memory-aware communication for accessing application data, a lightweight invocation interface, dynamic polling or interrupt selection through Interrupt Policy Adaptation, and a scheduler that distributes work across CPUs and HA instances. Experiments report up to 260x faster communication and 2-6x wall-clock performance improvements over conventional schedulers. The abstract also says performance depends on operating-system overhead, available resources, and scheduling, as well as accelerator speed.

## Source excerpt

arXiv:2610.33380v1 Announce Type: cross Abstract: Heterogeneous systems-on-chip (SoCs) increasingly rely on domain-specific hardware accelerators (HAs) to deliver performance and energy efficiency gains beyond what general-purpose processors can provide. However, operating systems (O/S), such as Linux, assume that processors are the Compute Elements (CEs) and HAs are peripheral devices rather than specialized CEs. As a result, HA execution incurs substantial software (SW) overheads that reduce the effective benefits of hardware (HW) acceleration. This work demonstrates that significant inefficiencies arise from ``O/S peripheral device taxes'' (O/S taxes), including SW stack-accelerator communication, invocation, interrupt handling, and scheduling. We built MEERKAT, a Field-Programmable Gate Array (FPGA)-based framework for configurable multicore systems that include HAs; it allows the user to migrate Linux O/S support from SW to HW and identify, study, and quantify the impact. Here we study four major sources of O/S tax and introduce techniques to mitigate them. These include a virtual-memory-aware (VMA) communication method that enables efficient HA access to application data, a lightweight HA invocation interface, Interrupt Policy Adaptation (IPA) for dynamic polling and interrupt selection, and an HA-aware scheduler that dynamically distributes work across Central Processing Units (CPUs) and multiple HA instances. Experimental results demonstrate up to $260\times$ faster communication and $2$--$6\times$ performance improvements in wall-clock time over conventional schedulers. Furthermore, our study reveals that overall system performance depends not only on HA speed, but also on O/S overheads, resource availability, and scheduling decisions. These findings highlight the importance of treating HAs as first-class computational resources and motivate a more accelerator-centric O/S design for future heterogeneous systems.