Re: [Bug-apl] More performance results

2014-04-17 Thread Juergen Sauermann
Hi Elias, just do something like this: *for ((i=1; $i<80; ++i)); do** ** ./Parallel $i** ** ./Parallel_OMP $i** **done* That wil create a number of files ending in .omp and .man. In the previous version there was a fault, corrected in the attached version. /// Jürgen On 04/17/2014 04:41 AM,

Re: [Bug-apl] More performance results

2014-04-16 Thread Elias Mårtenson
I'll be happy to run the benchmark. Can you give me the details on how to actually run it? Regards, Elias On 17 April 2014 01:56, Juergen Sauermann wrote: > Hi, > > I have created a benchmark program that measures the startup (fork) and > finish (join) > times of OMP. It also compares them with

[Bug-apl] More performance results

2014-04-16 Thread Juergen Sauermann
Hi, I have created a benchmark program that measures the startup (fork) and finish (join) times of OMP. It also compares them with a hand-crafted fork/join. The manual implementation uses a O(log(P)) algorithm for forking and joining compared to apparently an assumed O(P) algorithm in OMP. It