1 / 64

Modern processor design

Modern processor design. Engineering design. The dynamic-static interface (DSI). Conceptuall illustration of possible placement of DSI in ISA design. Performance simulation metods. Trace-driven simulation. Execution-driven simulation. Scalar pipeline machine.

stevepugh
Télécharger la présentation

Modern processor design

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Modern processor design

  2. Engineering design

  3. The dynamic-static interface (DSI)

  4. Conceptuall illustration of possible placement of DSI in ISA design

  5. Performance simulation metods Trace-driven simulation Execution-driven simulation

  6. Scalar pipeline machine

  7. Superpipelined machine of degree m=3

  8. Superpipelined MIPS R4000 8-stage pipeline

  9. Superscalar machine of degree n=3

  10. VLIW machine of degree n=3

  11. Pipeline example 4-stage 11-stage

  12. Two commercial instruction pipelines

  13. Activity of pipeline stages

  14. 6-stage instruction pipeline

  15. I-cache and D-cache

  16. Access to RF

  17. RAW, WAR, and WAW data dependencies

  18. WAW, WAR, and RAW hazards

  19. Forwarding paths

  20. Forwarding paths for ALU leading instructions

  21. Forwarding paths for Load leading instructions

  22. Impact on ALU, Load, and Branch penalties with increasing pipeline depth

  23. Mitigating the Branch penalty impact of deep pipelines

  24. Direct, associative, and set-associative caches

  25. Strategy of cache design

  26. Memory hierarchy

  27. Main memory and I/O

  28. DRAM accesses

  29. Virtual to physical address translation

  30. Processes switching

  31. Paging tables

  32. Direct cache

  33. Associative cache

  34. Set-associative cache

  35. Virtual to physical address translation

  36. Disk

  37. I/O device communication

  38. Stall cycle induced by backward propagation of stalling

  39. Machine parallelism

  40. Parallel pipeline of width s=3

  41. Parallel pipeline - examples 5-stage Pentium parallel pipeline s=2 5-stage i486

  42. Parallel pipeline with four execution pipes

  43. The Motorola 88110 superscalar microprocessor

  44. Interpipeline-stage buffers single-entry buffer multi-entry buffer multi-entry buffer with reordering

  45. Dynamic pipeline of width s=3

  46. 6-stage superscalar pipeline

  47. Instruction dispatching in superscalar pipeline

  48. Centralized reservation station

  49. Distributed reservation stations

  50. Dynamic pipeline with reservation stations and reorder buffer

More Related