[Wien] MKL 10 linking

awronka@uni.lodz.pl awronka at uni.lodz.pl
Fri Dec 7 17:04:08 CET 2007


     Hello Andrey,

      I have performed a few quick benchmark runs to fccni example from
user manual (“runsp_lapw  –ce 0.0001 –NI” for 3000 k points) for
your default and my pure layered mkl10 linking models,  on my small
home computers,  and stated as follows:

1.  I can  compile all programs on “-O3  -xX” optimization level,  except
of lapw2 program, where  only “-O1 –xX”  passed, in both cases of
compilation,  and system parameter OMP_NUM_THREADS=2 passed on  pure
layered linking only.

2.  Times of execution I obtained , were a little shorter for my pure
layered linking model. Exactly,  it was 51 sec. for my and 1 min. 4 sec.
for your  linking settings,  on my 3.2 GHz Intel  Pentum  4, 1GB RAM (667
HHz) stationary computer  with  Centos 5 operating system (1 min/1 min. 10
sec. on my Dell laptop – T5600 Core 2 Duo, 1.83 GHz with slow 5600 rpm
hard disk and 2 GB RAM(667 MHz),  Suse 10.3).

I do not know, why that "-O3" optimization crash for lapw2 on my systems.
What about your benchmark results?

Greetings,
 Andrzej





More information about the Wien mailing list