我已经阅读了所有的答案(超过30个)，并没有找到一个简单的原因:如果你读过并练习过Intel®64和IA-32架构优化参考手册，汇编程序比C更快，所以汇编程序可能更慢的原因是编写这种慢汇编程序的人没有阅读优化手册。

In the good old days of Intel 80286, each instruction was executed at a fixed count of CPU cycles. Still, since Pentium Pro, released in 1995, Intel processors became superscalar, utilizing Complex Pipelining: Out-of-Order Execution & Register Renaming. Before that, on Pentium, produced in 1993, there were U and V pipelines. Therefore, Pentium introduced dual pipelines that could execute two simple instructions at one clock cycle if they didn't depend on one another. However, this was nothing compared with the Out-of-Order Execution & Register Renaming that appeared in Pentium Pro. This approach introduced in Pentium Pro is practically the same nowadays on most recent Intel processors.

Let me explain the Out-of-Order Execution in a few words. The fastest code is where instructions do not depend on previous results, e.g., you should always clear whole registers (by movzx) to remove dependency from previous values of the registers you are working with, so they may be renamed internally by the CPU to allow instruction execute in parallel or in a different order. Or, on some processors, false dependency may exist that may also slow things down, like false dependency on Pentium 4 for inc/dec, so you may wish to use add eax, 1 instead or inc eax to remove dependency on the previous state of the flags.

如果时间允许，您可以阅读更多无序执行和注册重命名。因特网上有大量的信息。

There are also many other essential issues like branch prediction, number of load and store units, number of gates that execute micro-ops, memory cache coherence protocols, etc., but the crucial thing to consider is the Out-of-Order Execution. Most people are simply not aware of the Out-of-Order Execution. Therefore, they write their assembly programs like for 80286, expecting their instructions will take a fixed time to execute regardless of the context. At the same time, C compilers are aware of the Out-of-Order Execution and generate the code correctly. That's why the code of such uninformed people is slower, but if you become knowledgeable, your code will be faster.

除了乱序执行之外，还有很多优化技巧和技巧。请阅读上面提到的优化手册:-)

However, assembly language has its own drawbacks when it comes to optimization. According to Peter Cordes (see the comment below), some of the optimizations compilers do would be unmaintainable for large code-bases in hand-written assembly. For example, suppose you write in assembly. In that case, you need to completely change an inline function (an assembly macro) when it inlines into a function that calls it with some arguments being constants. At the same time, a C compiler makes its job a lot simpler—and inlining the same code in different ways into different call sites. There is a limit to what you can do with assembly macros. So to get the same benefit, you'd have to manually optimize the same logic in each place to match the constants and available registers you have.

长波克，只有一个限制时间。当你没有足够的资源来优化每一个代码的变化，并花时间分配寄存器，优化一些溢出和诸如此类的事情时，编译器每次都会赢。对代码进行修改、重新编译和度量。如有必要重复。

此外，你可以在高水平方面做很多事情。此外，检查生成的程序集可能会给人一种代码是垃圾的印象，但实际上它的运行速度比您想象的要快。例子:

Int y = data[i]; //在这里做一些事情。 call_function (y,…);

编译器将读取数据，将其推入堆栈(溢出)，然后从堆栈读取并作为参数传递。听起来屎?它实际上可能是非常有效的延迟补偿，并导致更快的运行时。

//优化版本 call_function(数据[我],…);//毕竟不是那么优化。

优化版本的想法是，我们降低了寄存器压力，避免溢出。但事实上，“垃圾”版本更快!

看看汇编代码，只看指令，然后得出结论:指令越多，速度越慢，这将是一个错误的判断。

这里需要注意的是:许多组装专家认为他们知道很多，但知道的很少。规则也会随着架构的变化而变化。例如，x86代码并不存在总是最快的银弹。如今，最好还是按照经验法则行事:

记忆很慢 缓存速度快 尽量更好地使用缓存 你多久会错过一次?你有延迟补偿策略吗? 对于一个cache miss，你可以执行10-100个ALU/FPU/SSE指令 应用程序架构很重要。 . .但是当问题不在架构上时，它就没有帮助了

此外，过于相信编译器会神奇地将考虑不周到的C/ c++代码转换为“理论上最优”的代码是一厢情愿的想法。如果你关心这个低级别的“性能”，你必须知道你使用的编译器和工具链。

C/ c++中的编译器通常不太擅长重新排序子表达式，因为对于初学者来说，函数有副作用。函数式语言没有受到这个警告的影响，但它不太适合当前的生态系统。有一些编译器选项可以允许宽松的精确规则，允许编译器/链接器/代码生成器改变操作的顺序。

这个话题有点死路一条;对于大多数人来说，这是无关紧要的，而剩下的人，他们已经知道自己在做什么了。

这一切都归结为:“理解你在做什么”，这与知道你在做什么有点不同。

在Amiga上，CPU和图形/音频芯片会为了访问特定区域的RAM(具体来说是前2MB的RAM)而争斗。因此，当你只有2MB RAM(或更少)时，显示复杂的图形加上播放声音会杀死CPU的性能。

在汇编程序中，你可以巧妙地交错你的代码，使CPU只在图形/音频芯片内部繁忙时(即当总线空闲时)才尝试访问RAM。因此，通过重新排序指令，巧妙地使用CPU缓存，总线定时，你可以实现一些使用任何高级语言都不可能实现的效果，因为你必须为每个命令定时，甚至在这里或那里插入nop，以使不同的芯片不受彼此的雷达影响。

这也是为什么CPU的NOP (No Operation -什么都不做)指令实际上可以让你的整个应用程序运行得更快的另一个原因。

当然，这种技术取决于特定的硬件设置。这就是为什么许多Amiga游戏无法适应更快的cpu的主要原因:指令的计时错误。

Actually you can build large scale programs in a large model mode segaments may be restricted to 64kb code but you can write many segaments, people give the argument against ASM as it is an old language and we don't need to preserve memory anymore, If that were the case why would we be packing our PC's with memory, the only Flaw I can find with ASM is that it is more or less Processor based so most programs written for the intel architecture Most likely would not run on An AMD Architecture. As for C being faster than ASM there is no language faster than ASM and ASM can do many thing's C and other HLL's can not do at processor level. ASM is a difficult language to learn but once you learn it no HLL can translate it better than you. If you could only see some of the things HLL's Do to you code, and understand what it is doing, you would wonder why More people don't use ASM and why assembers are no longer being updated ( For general public use anyway). So no C is not faster than ASM. Even experiences C++ programmers still use and write code Chunks in ASM added to there C++ code for speed. Other Languages Also that some people think are obsolete or possibly no good is a myth at times for instance Photoshop is written in Pascal/ASM 1st release of souce has been submitted to the technical history museum, and paintshop pro is written still written in Python,TCL and ASM ... a common denominator of these to "Fast and Great image processors is ASM, although photoshop may have Upgraded to delphi now it is still pascal. and any speed problems are comming from pascal but this is because we like the way programs look and not what they do now days. I would like to make a Photoshop Clone in pure ASM which I have been working on and its comming along rather well. not code,interpret,arange,rewwrite,etc.... Just code and go process complete.

在运行时创建机器代码怎么样?

我的兄弟曾经(大约在2000年)通过在运行时生成代码实现了一个非常快速的实时光线跟踪器。我不记得细节了，但有一些主模块是通过对象循环的，然后它准备和执行一些特定于每个对象的机器代码。

然而，随着时间的推移，这种方法被新的图形硬件淘汰，变得毫无用处。

今天，我认为大数据(数百万条记录)上的一些操作，如数据透视表、钻孔、实时计算等，都可以用这种方法进行优化。问题是:这样的努力值得吗?

我曾经和一个人一起工作过，他说“如果编译器笨到不能弄清楚你要做什么，并且不能优化它，那么你的编译器就坏了，是时候换一个新的了”。我确信在某些情况下汇编程序会打败你的C代码，但是如果你发现自己经常使用汇编程序来“赢得”编译器，那么你的编译器就完蛋了。

对于编写试图强制查询计划器执行操作的“优化”SQL也是如此。如果您发现自己重新安排查询以让计划器执行您想要的操作，那么您的查询计划器就完蛋了——请更换一个新的计划器。