1. Debugging SPU programs creates a new set of problems.

2. The SPU intrinsics documentation (see Resources) defines simplified vector type names starting with vec_.

3. However, with the SPU, the results are stored in a general-purpose register -- register 4 in this case.

4. Now, there are two compilers currently available for SPU programming, and, as one might expect, they excel in different areas.

5. When increasing hard segment content, the interaction between SPU moleculars is intensified whereas the miscibility of the blends in decreased consequently.

6. The preferred value size on the SPU is a 32-bit word, but others are supported, including bytes, halfwords, and doublewords.

7. SPU processes can be scheduled by the kernel, and all users can create them without interfering with each other.

8. THE SPU ABI, like the PPU ABI, uses registers to pass values to functions.

9. The only byte-oriented arithmetic function on the SPU is absdb, "absolute difference of bytes," which gives the absolute value of the difference between two operands.

10. This is critical, as the SPU can only load exactly 16 bytes at a time, aligned to exactly a 16-byte boundary.

11. The SPU has a read channel for receiving a single data word from the mailbox and two write channels for sending data words (more on this below).

12. Instead, the SPU can access any 128-bit word in the local store at L1 cache speed.

13. The SPU instruction clz (count leading zeroes, called spu_cntlz in the C language intrinsics) is perfect for this.

13. is a sentence dictionary, on which you can find good sentences for a large number of words.

14. The two transmission steps do not involve the SPU at all, but only the MFC (which is part of the larger SPE).

15. Branch hinting is necessary on the SPU because mispredicted branches come at a high cost.

16. Since all registers on the SPU are 16-bytes long, this will load a full 16-byte quadword into the register, even though you are only really concerned with the first 4 bytes of it.

17. To use an SPU from a process, the user needs to have write permission to the mount point of the spufs and choose an unused name for the new SPU context.

18. The SPU queues a DMA GET to pull a portion of the problem data set from main memory to a buffer.

19. Now, the integer multiply instructions on the SPU are somewhat problematic, especially signed multiplication (using the mpy instruction).

20. When the SPU code finishes or hits a critical error condition, it stops executing and the host process returns from the ioctl call.

21. Most importantly, if each SPU is represented by a single character device, it becomes hard for an application to find an SPU that is not yet used by another.

22. In the future, we are planning to change this so that more logical than physical SPU contexts can be present and have the kernel switch between them.

23. All specific intrinsics take the form si_assemblyinstructionname where assemblyinstructionname is the name of the assembly language instruction as defined in the SPU Assembly Language Specification.

24. When the PPE writes a data word to that address, the SPU can read from its corresponding mailbox read channels.

25. In addition, by default, every branch encountered by the SPU is assumed to be not taken, including unconditional branches.

26. To understand this cryptic-looking sequence, again keep in mind that the SPU only does loads and stores a quadword at a time, on quadword-aligned addresses.

27. Research about automatic turning control for agricultural vehicle was carried out based on KUBATO SPU - 60 transplanter.

28. The link register is only special by convention -- the SPU assembly language allows you to set the link in any register you choose.

29. Nickel oxide thin films were deposited by de reactive magnetron spu tring.

30. By writing to DMA channels, the SPE can initiate a memory transfer, which is executed in parallel to both the SPU code execution and the PPE control flow.