|
Boost : |
From: Achilleas Margaritis (axilmar_at_[hidden])
Date: 2007-09-20 05:55:17
Could you run it with optimizations?
Larry Evans wrote:
> On 09/19/07 17:15, Achilleas Margaritis wrote:
> [snip]
>> Draft version 0.8 contains a makefile for gcc under prj/gcc directory. I
>> compiled the example with gcc from OpenSuse 10.2. I left the executable
>> and object files (for 80x86) in the zip file so I hope some other people
>> can run it in case there is a problem.
>>
>> What impressed me is how fast the benchmark was compared to Microsoft's
>> compiler. The malloc routine of gcc must be very good.
>>
>> Larry, what are you trying to run the program on? is it a PowerPC
>> machine? if so, your version may crash due to different endianess
>> (perhaps because pointer addresses are used as bitfields?)...
>
> It's a compaq 4400 (bought 7/12/2002) so its an iX86, not PowerPC.
> Maybe I just didn't let it run long enough. So for (about 3-5min) I get:
>
> cd ~/prog_dev/boost-svn/ro/trunk/bin.v2/sandbox/axilmar/gcc-4.1/debug/
> ./main
> Garbage Collector Test
> Live storage will peak at 8194272 bytes.
>
> Stretching memory with a binary tree of depth 18
>
> Creating a long-lived binary tree of depth 16
> Creating a long-lived array of 500000 doubles
> Creating 33824 trees of depth 4
> Top down construction took 820.000000 msec
> Bottom up construction took 980.000000 msec
> Creating 8256 trees of depth 6
> Top down construction took 824.000000 msec
> Bottom up construction took 987.000000 msec
> Creating 2052 trees of depth 8
> Top down construction took 868.000000 msec
> Bottom up construction took 1390.000000 msec
> Creating 512 trees of depth 10
> Top down construction took 1359.000000 msec
> Bottom up construction took 60733.000000 msec
> Creating 128 trees of depth 12
> Top down construction took 921.000000 msec
> Bottom up construction took 1989.000000 msec
> Creating 32 trees of depth 14
> Top down construction took 1788.000000 msec
> Bottom up construction took 1738.000000 msec
> Creating 8 trees of depth 16
> Top down construction took 2475.000000 msec
> Bottom up construction took 3060.000000 msec
> Completed in 80657.000000 msec
> heap size = 0
>
> Compilation interrupt at Wed Sep 19 18:14:01
>
> _______________________________________________
> Unsubscribe & other changes: http://lists.boost.org/mailman/listinfo.cgi/boost
>
Boost list run by bdawes at acm.org, gregod at cs.rpi.edu, cpdaniel at pacbell.net, john at johnmaddock.co.uk