A few years ago, in the Windows environment, I did some testing, by letting multiple instances of CPU computation intensive + memory access intensive + I/O access intensive application run. I developed 2 versions: One is running under multi-processing, another is running under multi-threading.
I found that the performance is much better for multi-processing. I read somewhere else (but I can't remember the site).
Which states that the reason is that under multi-threading, they are "fighting" for a single memory pipeline and I/O pipeline, which makes the performance worse compared to multi-processing
However, I can't find that article anymore. I was wondering, till today, whether the below still hold true?
In Windows, having the algorithm code run under multi-processing, there is a high chance that the performance will be better than multi-threading.
It depends on how much the various threads or processes (I'll be using the collective term "tasks" for both of them) need to communicate, especially by sharing memory: that's easy, cheap and fast for threads, but not at all for processes, so, if a lot of it is going on, I bet processes' performance is not going to beat threads'.
Also, processes (esp. on Windows) are "heavier" to get started, so if a lot of "task starts" occur, again threads can easily beat processes in terms of performance.
Next, you can have CPUs with "hyperthreading", which can run (at least) two threads on a core very rapidly -- but, not processes (since the "hyperthreaded" threads cannot be using distinct address spaces) -- yet another case in which threads can win performance-wise.
If none of these considerations apply, then the race should be no better than a tie, anyway.
I'm not sure what the quote even means. It's very close to nonsense.
The primary thing that in-proc threads share is virtual memory address space.
I found this is true as well. but I think it has something to do with the scheduling. because if you run it long enough, the multi-processes is just as fast as multi-threads. that number is about 10 seconds. if the algorithm needs to be run for 10 seconds. the multi-processes is as fast as multi-thread. but if it only needs to be run for less than 1 second. multi-processes is much,much faster than multi-thread.
来源：https://stackoverflow.com/questions/3376562/performance-difference-for-multi-thread-and-multi-process