Collecting SBUs now

Adam Trilling agt10 at columbia.edu
Thu May 30 12:00:10 PDT 2002


On Thu, 30 May 2002, Ian Molton wrote:

> Thats not quite true.
>
> I find -j4 is moticably quicker on my UNI-processor box.
>
> doing a 1-process make leaves the box doing only about 50-75% work -
> lots of gaps with little load.

i agree.  i did some kernel hacking on a dual-processor box for a class
last semester and make -j 4 took about 15 seconds less than make -j 2 to
compile the kernel (about 105 seconds vs about 90 seconds).  i think with
more processes than processors, the processors will still have work to do
while they're waiting on disk accesses, hence the speedup.


Adam Trilling
agt10 at columbia.edu


char m[9999],*n[99],*r=m,*p=m+5000,**s=n,d,c;main(){for(read(0,r,4000);c=*r;
r++)c-']'||(d>1||(r=*p?*s:(--s,r)),!d||d--),c-'['||d++||(*++s=r),d||(*p+=c==
'+',*p-=c=='-',p+=c=='>',p-=c=='<',c-'.'||write(2,p,1),c-','||read(2,p,1));}

-- 
Unsubscribe: send email to listar at linuxfromscratch.org
and put 'unsubscribe lfs-dev' in the subject header of the message



More information about the lfs-dev mailing list