x86_64的 - 装配 - 循环条件和乱序 [英] x86_64 - Assembly - loop conditions and out of order
问题描述
(我是这样的话,我会做我自己。的)
我的问题:
我倾向于避免间接/索引寻址为了方便模式。
I tend to avoid the indirect/index addressing modes for convenience.
作为替代,我经常使用即时,绝对或寄存器寻址。
As a replacement, I often use immediate, absolute or register addressing.
在code:
; %esi has the array address. Say we iterate a doubleword (4bytes) array.
; %ecx is the array elements count
(0x98767) myloop:
... ;do whatever with %esi
add $4, %esi
dec %ecx
jnz 0x98767;
在这里,我们有一个序列化的组合(DEC和JNZ)的prevent正确的乱序执行(依赖)。
Here, we have a serialized combo(dec and jnz) which prevent proper out of order execution (dependency).
有没有办法避免/打破DEP? (我不是一个组装专家)。
Is there a way to avoid that / break the dep? (I am not an assembly expert).
推荐答案
在优化英特尔处理器,始终把标记设置指令的条件跳转指令前右,这样他们就可以宏观融合成一条微在德codeRS。这对AMD的CPU没有显著恶化。你可能被一个CPU的不宏观保险丝比较和分支对缩短分支误predict罚款。在法正确predicted情况下,这是一个额外的运算以空间的重新排序缓冲器一个额外的周期。我不认为任何这些,不问分裂比较和分支指令。我认为,英特尔在额外的UOP吞吐量更显著。
When optimizing for Intel CPUs, always put the flag-setting instruction right before the conditional jump instruction, so they can macro-fuse into one uop in the decoders. It's not significantly worse for AMD CPUs. You might shorten the branch mispredict penalty by one for CPUs that don't macro-fuse compare-and-branch pairs. In the correctly-predicted case, it's one extra op taking space in the re-order buffer for one extra cycle. I don't think either of those justifies splitting up compare-and-branch instructions. I think the extra uop throughput on Intel is more significant.
AMD推土机/打桩机/压路机可以融合测试/ CMP
任何江铜
,但只有测试/ CMP
,没有任何ALU指令。所以,一定会把树枝进行比较。
AMD Bulldozer/Piledriver/Steamroller can fuse test/cmp
with any jcc
, but only test/cmp
, not any ALU instructions. So definitely put compares with branches.
瓦格纳雾的 microarch指南,表9.2(SandyBridge的用于/ IvyBridge的):
From Agner Fog's microarch guide, Table 9.2 (for Sandybridge / Ivybridge):
First | can pair with these | cannot pair with
instruction | (and the inverse) |
---------------------------------------------
cmp |jz, jc, jb, ja, jl, jg| js, jp, jo
add, sub |jz, jc, jb, ja, jl, jg| js, jp, jo
adc, sbb |none |
inc, dec |jz, jl, jg | jc, jb, ja, js, jp, jo
test | all |
and | all |
or, xor, not, neg | none |
shift, rotate | none |
Table 9.2. Instruction fusion
所以基本上, /减
可以宏观保险丝以江铜
只要条件仅依赖于由 /减
修改位。 (否则,他们没有宏观保险丝,你会得到插入合并标志(当你读到这样一个额外的UOP公司 EAX
写在人
),或者在更早的CPU,一个局部的标志搪塞。)
So basically, inc/dec
can macro-fuse with a jcc
as long as the condition only depends on bits that are modified by inc/dec
. (Otherwise, they don't macro-fuse, and you get an extra uop inserted to merge the flags (like when you read eax
after writing al
). Or on earlier CPUs, a partial-flags stall.)
酷睿2 / Nehalem的是宏观的融合能力较为有限,而酷睿2不能宏观保险丝,64位模式的。
Core2 / Nehalem was more limited in macro-fusion capability, and Core2 couldn't macro-fuse in 64bit mode at all.
阅读瓦格纳雾的优化汇编和C导游也一样,如果你还没有。他们充分必要的知识的。
Read Agner Fog's optimizing asm and C guides, too, if you haven't already. They're full of essential knowledge.
这篇关于x86_64的 - 装配 - 循环条件和乱序的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持IT屋!