1. Survey of multicore architectures Marko Bertogna Scuola Superiore S.Anna, ReTiS Lab, Pisa, Italy

2. Summary CELL processor Reconfigurable devices Software-Hardware co-design Parallel programming problems data dependencies process synchronization memory barriers locking mechanisms Language extensions for parallel programming Real-time multiprocessor scheduling

3. Cell processor A Cell Processor

4. Cell History

5. Cell basic concepts

6. Cell synergy

7. Cell Chip

8. Cell features

9. Cell Processor Components

13. Synergistic Processor Element (SPE)

14. SPE

15. SPE details

16. Element Interconnect Bus (EIB)

17. EIB: Data topology

18. Example: 8 concurrent transactions

19. Theoretical peak operations

20. Cell BE performance

21. Why is Cell Processor so fast?

22. CELL software environment

23. System Level Simulator

24. SPE management library

25. CELL parallelism

26. Typical CELL sw development flow

27. ARM ’ s MPcore

28. PicoArray (by PicoChip)

29. PicoArray scaling

30. FPGA and Reconfigurable devices

31. Field Programmable Gate Arrays SRAM-based matrix of integrated elements whose interconnections can be programmed statically or even dynamically Basic block is Logic Element (LE) Chip capacities from 1k to 1000k LEs Each LE is typically composed by logic gates, LUTs, Flip-Flops and latches Need for optimized CAD or pre-binded design libraries

32. FPGA CSL organization: Basic Logic Element:

33. Altera ’ s Stratix IV basic block Adaptive Logic Module (ALM)

34. Flexibility vs efficiency

35. Reconfigurable devices advantages Efficiency AND Flexibility Time to market Easier upgrade Lower cost (on scale production) Reusable IP Customable interface

36. Reconfigurable devices parameters Block granularity Coarse grained: Functional Units, Processor Cores, Memory Tiles Fin grained: gate and register level Density Reconfiguration time Compile-Time Reconfiguration (CTR) Run-Time Reconfiguration (RTR) Partial or Total reprogramming

37. Triscend ’ s A7S chip

38. Example: multiplier on Altera ’ s Stratix IV

39. Typical FPGA software development environment FPGA optimized module library IO Editor Generate  file.h Bind (placement and route)  file.csl Config  file.cfg Download

40. Typical FPGA module library

41. Altera ’ s Nios II Nios II is a soft-core processor IP that can be downloaded into an Altera ’ s FPGA, obtaining the functionalities of a real RISC CPU Logic elements are programmed so as to behave like gates of classic ASIC processors Different Nios versions are available faster and with full functionalities  bigger size medium sized compact but slower and with limited functionalities

42. Nios II core

43. Selecting Nios II e/s/f

44. Example of a Nios II Processor system

45. Final global layout

46. Soft-core processors and FPGAs Possible to have multiple cores on a single chip Customizable hardware can be used to coordinate the various cores Build and test a whole multicore system in a faster time Detect and solve bottlenecks without needing to repeatedly return to the integration phase

47. Co-design problems with FPGAs A task may be executed by a (soft-core or ASIC) processor or may be entirely implemented in hardware on the reconfigurable logic “ Programming in Space ” versus “ Programming in Time ” Centralized vs Distributed computing Sequential vs Parallel programming Interconnect Network

48. What is a task in hardware? Software programming c=a+b; result=c/2; Hardware implementation a b c + shifter result Assembler expansion: ldr r0,a ldr r1,b add r0,r0,r1 mov r0,LSR r0 str r0,result 5 operations All in one clock cycle!

49. Conclusions FPGAs are interesting devices for multicore systems developers Valid benchmark upon which to compare classic serial programming methods and parallel computing approaches Allow reducing time-to-market for next- generation multicore systems Provide common platforms that can easily reproduce any architecture (given a proper VHDL/Verilog description)