درحال بارگذاري...
ارسال به دوستان
 فهرست مطالب
 فهرست نقدها
  1. NURA: A framework for supporting non-uniform resource accesses in gpus
NURA: A framework for supporting non-uniform resource accesses in gpus
6 مرتبه مشاهده شده

NURA: A framework for supporting non-uniform resource accesses in gpus

Darabi, S.

  1. DOI:10.1145/3508036
  2. Main Entry: Darabi, S.
  3. Title:NURA: A framework for supporting non-uniform resource accesses in gpus.
  4. Publisher:Association for Computing Machinery, 2022.
  5. Abstract:Multi-application execution in Graphics Processing Units (GPUs), a promising way to utilize GPU resources, is still challenging. Some pieces of prior work (e.g., spatial multitasking) have limited opportunity to improve resource utilization, while other works, e.g., simultaneous multi-kernel, provide fine-grained resource sharing at the price of unfair execution. This paper proposes a new multi-application paradigm for GPUs, called NURA, that provides high potential to improve resource utilization and ensures fairness and Quality-of-Service (QoS). The key idea is that each streaming multiprocessor (SM) executes Cooperative Thread Arrays (CTAs) belong to only one application (similar to the spatial multi-tasking) and shares its unused resources with the SMs running other applications demanding more resources. NURA handles resource sharing process mainly using a software approach to provide simplicity, low hardware cost, and flexibility. We also perform some hardware modifications as an architectural support for our software-based proposal. We conservatively analyze the hardware cost of our proposal, and observe less than 1.07% area overhead with respect to the whole GPU die. Our experimental results over various mixes of GPU workloads show that NURA improves GPU system throughput by 26% compared to state-of-the-art spatial multi-tasking, on average, while meeting the QoS target. In terms of fairness, NURA has almost similar results to spatial multitasking, while it outperforms simultaneous multi-kernel by an average of 76%. © 2022 ACM
  6. Notes:Sharif Repository
  7. Subject:Cloud computing.
  8. Subject:Gpu.
  9. Subject:Multitasking.
  10. Subject:Quality of services.
  11. Subject:Streaming multiprocessor.
  12. Subject:System throughput.
  13. Subject:Computer graphics.
  14. Subject:Graphics processing unit.
  15. Subject:Multiprocessing systems.
  16. Subject:Program processors.
  17. Subject:Quality of service.
  18. Subject:Cloud-computing.
  19. Subject:Gpu.
  20. Subject:Graphics processing.
  21. Subject:Multi-application.
  22. Subject:Multi-kernel.
  23. Subject:Processing units.
  24. Subject:Quality-of-service.
  25. Subject:Resources utilizations.
  26. Subject:Streaming multiprocessors.
  27. Subject:System throughput.
  28. Subject:Multitasking.
  29. Added Entry:Mahani, N.
  30. Added Entry:Baxishi, H.
  31. Added Entry:Yousefzadeh Asl Miandoab, E.
  32. Added Entry:Sadrosadati, M.
  33. Added Entry:Sarbazi Azad, H.
  34. Added Entry:Sharif University of Technology.
  35. Source: Proceedings of the ACM on Measurement and Analysis of Computing Systems ; Volume 6, Issue 1 , 2022 ; 24761249 (ISSN)
  36. Web Site:https://dl.acm.org/doi/10.1145/3508036

 فهرست نقدها