在这个网站上已经有很多性能问题了,但是在我看来,几乎所有的问题都是非常具体的,而且相当狭窄。几乎所有人都重复了避免过早优化的建议。
我们假设:
代码已经正常工作了
所选择的算法对于问题的环境已经是最优的
对代码进行了测量,并隔离了有问题的例程
所有优化的尝试也将被衡量,以确保它们不会使事情变得更糟
我在这里寻找的是策略和技巧,在一个关键算法中,当没有其他事情可做,但无论如何都要挤出最后百分之几。
理想情况下,尽量让答案与语言无关,并在适用的情况下指出所建议的策略的任何缺点。
我将添加一个带有我自己最初建议的回复,并期待Stack Overflow社区能想到的任何其他东西。
在带有模板的语言(c++ /D)中,您可以尝试通过模板参数传播常量值。你甚至可以用开关来处理小的非常值集合。
Foo(i, j); // i always in 0-4.
就变成了
switch(i)
{
case 0: Foo<0>(j); break;
case 1: Foo<1>(j); break;
case 2: Foo<2>(j); break;
case 3: Foo<3>(j); break;
case 4: Foo<4>(j); break;
}
缺点是缓存压力,因此这只会在深度或长期运行的调用树中获得,其中值在持续时间内是恒定的。
我大半辈子都在这里度过。大致的方法是运行你的分析器并记录它:
Cache misses. Data cache is the #1 source of stalls in most programs. Improve cache hit rate by reorganizing offending data structures to have better locality; pack structures and numerical types down to eliminate wasted bytes (and therefore wasted cache fetches); prefetch data wherever possible to reduce stalls.
Load-hit-stores. Compiler assumptions about pointer aliasing, and cases where data is moved between disconnected register sets via memory, can cause a certain pathological behavior that causes the entire CPU pipeline to clear on a load op. Find places where floats, vectors, and ints are being cast to one another and eliminate them. Use __restrict liberally to promise the compiler about aliasing.
Microcoded operations. Most processors have some operations that cannot be pipelined, but instead run a tiny subroutine stored in ROM. Examples on the PowerPC are integer multiply, divide, and shift-by-variable-amount. The problem is that the entire pipeline stops dead while this operation is executing. Try to eliminate use of these operations or at least break them down into their constituent pipelined ops so you can get the benefit of superscalar dispatch on whatever the rest of your program is doing.
Branch mispredicts. These too empty the pipeline. Find cases where the CPU is spending a lot of time refilling the pipe after a branch, and use branch hinting if available to get it to predict correctly more often. Or better yet, replace branches with conditional-moves wherever possible, especially after floating point operations because their pipe is usually deeper and reading the condition flags after fcmp can cause a stall.
Sequential floating-point ops. Make these SIMD.
我还喜欢做一件事:
将编译器设置为输出程序集清单,并查看它为代码中的热点函数发出了什么。所有那些聪明的优化,“一个好的编译器应该能够自动为你做”?实际的编译器可能不会执行这些操作。我见过GCC发出真正的WTF代码。