[CPMD-list] NCACHE size

Kozin, I (Igor) I.Kozin at dl.ac.uk
Fri Aug 27 13:14:06 CEST 2004


> I made some tests on my opteron machine, and cpmd link to atlas is 
> approx. 1.5 more efficient than
> cpmd link to acml, so that's right, with cpmd the first thing to do is 
> to find an optimized blas/lapack lib
> for your cpu, and then after you should play with the ncache value.
> Many thanks to the guys who made atlas, (even if the mkl is more 
> efficient with the itanium2 ).

The difference I see on our Opteron 244 (wat32 benchmark) is about 2%:
Axel's pre-built Atlas for Opterons is slightly quicker than Gnu ACML 2.0.
Does it mean Atlas _has_ to be locally tuned?

> >PB> >btw: the best way to optimize the fft is use it as little as 
> >PB> >possible (e.g. by using the REAL SPACE WFN KEEP keyword, provided
> >PB> >there is enough memory on your machine).

Apologies for diverting the topic further...
Just tried REAL SPACE WFN KEEP and got 
  MEMORY| MEMORY REQUIRED:   274776194  WORDS
 PROGRAM STOPS IN SUBROUTINE MEMORY| TOO BIG VALUE

memory.F: 82-91
#if !defined(MALLOC8)
C     Check if 8 * LEN is in the range of integer.
      IF(IRAT.EQ.2) THEN
C       Integer=integer*4 : 2^31=2147483648, 2^28=268435456
        IF(LEN.GT.2**28) THEN
          WRITE(*,*) ' MEMORY| MEMORY REQUIRED:',LEN,' WORDS'
          CALL STOPGM('MEMORY','TOO BIG VALUE')
        ENDIF
      ENDIF
#endif

As far as I can see I can do nothing about IRAT. Can I use MALLOC8?
I remember Axel advised for POINTER8 but against using MALLOC8 a while
ago...

Igor



More information about the CPMD-list mailing list