Offload Annotations - Bringing Heterogeneous Computing to Existing Libraries and Workloads

Offload Annotations - Bringing Heterogeneous Computing to Existing Libraries and Workloads

USENIX via YouTube Direct link

Conclusion

20 of 20

20 of 20

Conclusion

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

Offload Annotations - Bringing Heterogeneous Computing to Existing Libraries and Workloads

Automatically move to the next video in the Classroom when playback concludes

  1. 1 Intro
  2. 2 Background: Hardware Commoditization
  3. 3 Background: CPUs vs. GPUs
  4. 4 Background: Data Science on the CPU
  5. 5 Trend: Data Science on the GPU
  6. 6 Trend: CPU Libraries vs. GPU Libraries
  7. 7 Goals
  8. 8 Annotator - Function Annotations
  9. 9 Step 1: Annotator - Allocation Annotations
  10. 10 Step 1: Annotator - Offload Split Type
  11. 11 End User
  12. 12 Step 3: Runtime - Offloading API
  13. 13 Step 3: Runtime - Splitting API
  14. 14 Step 3: Runtime - Scheduling Heuristics (optional)
  15. 15 Integration Experience
  16. 16 Evaluation: Summary
  17. 17 In-Depth Evaluation: Allocations
  18. 18 In-Depth Evaluation: Heuristics
  19. 19 In-Depth Evaluation: Splitting/Paging Datasets
  20. 20 Conclusion

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.