1. Larrabee Eric Jogerst Cortlandt Schoonover Francis Tan

2. Larrabee Intels new approach to a GPU Considered to be a hybrid between a multi- core CPU and a GPU Combines functions of a multi-core CPU with the functions of a GPU

3. Larrabee

4. FETCH Larrabee

5. Fetch Utilizes a hardware prefecther Supports four threads of execution – Separate register files for each thread – Switches threads in order to cover cases where the compiler is unable to schedule code without stalls or if the prefetcher has not received new instructions – Inactive thread data is written to the cores local L2 cache

6. PIPELINE ORGANIZATION Larrabee

7. Pipeline Pipeline derived from the dual-issue Pentium processor, which is 5-stages – Short, inexpensive execution pipeline Pairing rules for primary and secondary instruction pipes are deterministic – Allows compilers to perform offline analysis with a wide scope

8. Pipeline Pairing rules for primary and secondary instruction pipes are deterministic – Allows compilers to perform offline analysis with a wide scope All instructions can be issued on the primary pipeline – Minimizes the combinational problems for a compiler Secondary pipeline can execute a large x86 instruction set – Small and cheap – Power wasted by failing to dual-issue on every cycle is minimal

9. Pipeline Each core has own pipeline – Based upon the 5 stage Pentium – Dual issues instructions – In order execution Pipeline is shared between threads – Hardware can switch between threads that have instructions that have instructions ready to execute

10. Pipeline Designed software-rendering pipeline to minimize the number of locks and other synchronization events Graphics-rendering pipeline written with high- level languages and tools – Enables developers to add innovative rendering capabilities

11. SIMD ORGANIZATION Larrabee

12. Vector Processor Unit 16-wide vector processor unit (VPU) – executes integer, single-precision float, and double-precision float instructions – VPU and register are approximately one-third the area of the processor core Tradeoff – Increased computational density – Wider VPUs have higher utilization

13. Vector Processor Unit VPU instructions can be predicated by a mask register Mask controls which parts of a vector register or memory location are written and which are left untouched Advantages – Reduces branch misprediction penalties – Gives instruction scheduler greater freedom

14. Number of Cores Many-core processor – Planned to have 24 to 48 cores

15. Number of Cores

17. SYSTEM ON-CHIP COMPONENTS Larrabee

18. System On-Chip Components x86 computer cores - Dual issue, in order processors that support the x86 protocol with Larrabee extensions. Connected to ring network and high bandwidth connection to adjacent L2 Cache subset.

19. System On-Chip Components L2 Cache subsets – High bandwidth access to adjacent CPU – Connected directly to the ring network – Coherent cache, uses the ring network to check coherency when allocating new cache lines

20. System On-Chip Components Ring Network Nodes – Simple bi-directional routers with a 512 bit data path in each direction (1024 bit total bandwidth) – Organized in rings of 8-16 cores and other devices – Interconnected with other rings – All data moved between cores and fixed functional units passes through the ring network

21. System On-Chip Components Fixed function logic components – Provides rasterization, interpolation and other commonly needed functions – Directly connected to the ring network – Will be spread among the cores to provide lower latency and load balancing on the ring network

22. System On-Chip Components Memory & I/O interface – Provides and manages communication between the Ring Network and off chip devices. – Manages initial routing and tasking of cores

23. MEMORY HIERARCHY Larrabee

25. Memory Interface

26. ON-CHIP INTERCONNECT Larrabee

27. On-Chip Interconnect Ring interconnect bus Similar to the Sony Cell processor.

28. Ring Bus

29. Ring Bus Features Bi-directional 512 Bits in each direction Presumably running at core speed. Each element can take from one direction on odd CC and other direction on even CC.

30. Ring Bus Comparisons Compared to AMDs R600/RV670 bus, it is half the bit-width. The higher clock speed of Larrabees bus should make up for the difference in bandwidth.

31. Ring Bus Tradeoff Analysis

32. Pros: Straightforward, not complex Able to deliver high bandwidth Great performance if memory clients need high bandwidth. Cons: Waste of chip area if most applications dont need high memory bandwidth That area could be spent elsewhere to increase performance in a different way.

33. MULTITHREADING ORGANIZATION Larrabee

34. Multithreading Organization Superscalar In-Order Four Threads of execution Dual issue (with a vector processing unit)

35. Comparison to OO Execution # CPU cores:2 out-of-order10 in-order Instruction issue:4 per clock2 per clock VPU per core:4-wide SSE16-wide L2 cache size:4 MB Single-stream:4 per clock2 per clock Vector throughput: 8 per clock160 per clock

37. 8 per clock Larrabee Vector Processor

38. Scheduling Policy Software Controlled More flexible due to the software controlled scheduling than a typical GPU.

39. Software Controlled Scheduling Pros Flexible: can choose the scheduler to suit the application. Worst case wont be so bad. (As compared to a hardware encoded scheduling policy) Cons Overhead of scheduler takes a bite out of performance Programmer overhead of selecting the correct scheduler.

40. Criticism NVIDIA – like a GPU from 2006 – Unrealistic performance projections – Motivated by interest to retain market share

41. Possible Market Dreamworks Animation Xbox / Playstation Scientific research

42. Questions?