Performance degrades for more than 2 threads on Xeon X5355

I am writing an application using boost threads and using boost barriers to synchronize the threads. I have two machines to test the application.

Machine 1 is a core2 duo (T8300) cpu machine (windows XP professional - 4GB RAM) where I am getting following performance figures :

Number of threads :1 , TPS :21

Number of threads :2 , TPS :35 (66 % improvement)

further increase in number of threads decreases the TPS but that is 开发者_如何转开发understandable as the machine has only two cores.

Machine 2 is a 2 quad core ( Xeon X5355) cpu machine (windows 2003 server with 4GB RAM) and has 8 effective cores.

Number of threads :1 , TPS :21

Number of threads :2 , TPS :27 (28 % improvement)

Number of threads :4 , TPS :25

Number of threads :8 , TPS :24

As you can see, performance is degrading after 2 threads (though it has 8 cores). If the program has some bottle neck , then for 2 thread also it should have degraded.

Any idea? , Explanations ? , Does the OS has some role in performance ? - It seems like the Core2duo (2.4GHz) scales better than Xeon X5355 (2.66GHz) though it has better clock speed.

Thank you

-Zoolii

---

I'd be very surprised if this isn't memory page access related. Have you tried forcing the Xein box down to four or two CPUs and rerun you tests?

---

You really need to do more analysis. E.g. how much contention is there? How many times do the cores block on flushing cache for the memory barriers?

---

Unless the sole difference between the two machines is the CPU you really have no way of knowing. Subtle interactions between bus speeds, memory, disk I/O (if relevant), network I/O (if relevant), 32 bit vs 64 bit (if relevant), device drivers and the OS could all contribute to this.

One thing you might check is System Properties | Advanced | Performance Settings | Advanced and ensure that the "Processor scheduling" on both machines is the same; at least it will remove one difference.