1、The SPU actually loads two instructions at a time from a doubleword-aligned boundary.
SPU實(shí)際上會(huì)從一個(gè)雙字對(duì)齊的邊界開(kāi)始一次加載兩條指令。

2、Here are some of the more common SPU intrinsics.
下面是比較常見(jiàn)的一些SPUintrinsic(類(lèi)型沒(méi)有給出，這是因?yàn)?/a>它們大多為多態(tài))。

3、Debugging SPU programs creates a new set of problems.
調(diào)試s PU程序會(huì)出現(xiàn)一些新的問(wèn)題。

4、The SPU processes buffer #1.
SPU處理一號(hào)緩沖區(qū)。

5、Also, exceptions resulting from executed code aren't reported to the SPU itself.
而且，執(zhí)行代碼產(chǎn)生的異常結(jié)果也不會(huì)向SPU進(jìn)行匯報(bào)。

6、The SPU waits for the buffer to fill up.
SPU等待緩沖區(qū)被填充。

7、Instead, the SPU can access any 128-bit word in the local store at L1 cache speed.
相反，SPU可以以L1緩存的速度來(lái)訪問(wèn)本地存儲(chǔ)器中的任何128位的字。

8、The SPU has no special registers.
SPU沒(méi)有特殊的寄存器。

9、The SPU processes buffer #2.
SPU處理二號(hào)緩沖區(qū)。

10、The SPU waits for buffer #2 to finish filling.
SPU等待二號(hào)緩沖區(qū)被填充。

11、Often this is called by the SPU code itself.
通常這是由SPU代碼本身調(diào)用的。

12、The SPU has no real hardware support for branch hinting.
SPU對(duì)于分支提示并沒(méi)有沒(méi)有實(shí)際硬件支持。

13、The SPU queues a DMA PUT to transmit the buffer back to main memory.
SPU對(duì)DMA PUT進(jìn)行排隊(duì)，從而將緩沖區(qū)傳輸回主內(nèi)存。

14、It turns out that several SPU instructions deal with only one of the register's values.
幾個(gè)SPU指令只能處理這些寄存器值中的一個(gè)。

15、Remember that the SPU registers are 128 bits wide, but our value is only 32 bits long.
SPU寄存器均為128位寬，但我們的值只有32位長(zhǎng)。

16、A signal might need to be delivered to a thread that is executing SPU code.
我們可能需要將信號(hào)發(fā)送給正在執(zhí)行SPU代碼的線程。

17、Every directory in spufs refers to a logical spu context.
spufs中的每個(gè)目錄都是指一個(gè)邏輯的spu上下文。

18、Branch hinting is necessary on the SPU because mispredicted branches come at a high cost.
分支提示之所以在SPU是必需的是因?yàn)轭A(yù)測(cè)錯(cuò)誤的分支可能會(huì)帶來(lái)高耗費(fèi)。

19、An SPU resembles a cross between a simple CPU design and a digital signal processor.
SPU就像是簡(jiǎn)單的CPU設(shè)計(jì)與數(shù)字信號(hào)處理器之間的交叉。

20、The SPU queues a DMA GET to pull a portion of the problem data set from main memory to a buffer.
SPU對(duì)DMA GET進(jìn)行排隊(duì)，從而將涉及的數(shù)據(jù)集的一部分從主內(nèi)存?zhèn)鬏數(shù)揭粋€(gè)緩沖區(qū)。

21、The two transmission steps do not involve the SPU at all, but only the MFC.
兩個(gè)傳輸步驟根本沒(méi)有涉及SPU，只涉及MFC(這是比較大的SPE的一部分)。

22、The SPU waits for the buffer to finish being transmitted.
SPU等待緩沖區(qū)完成傳輸。

23、starts execution of SPU code.
開(kāi)始執(zhí)行SPU代碼。

24、SPU code is compiled separately from the PPC code and gets loaded at run time.
SPU代碼與PPC代碼分開(kāi)進(jìn)行編譯，并在運(yùn)行時(shí)進(jìn)行加載。

SPU翻譯

【計(jì)】 標(biāo)量處理部件, 系統(tǒng)劃分部件, 系統(tǒng)處理部件 詳情