Hi ! I had a similar kind of a problem using the profiler... I found out that, when I single step for a single cycle assembly instruction, the profiler clock used to increment by 6 ! I think u could use the Statics manager of BIOS to get the right clock Cycles.... All the best, nikhil --- simha j <> wrote: > hi, > > i am using ccs2 for 621x. > I was Profiling a 'for loop' of my c-code which > loops > for count 0, few equations in it. > For this case I got clock050. > > but when i made count =1 (i.e., only one iteration), > I am getting clock = 550. > > so for count 0, clock becomes 550*200 which is > not > correct. > > where i am going wrong???? > > looking forward to your replies. > > bye > > _____________________________________ > Note: If you do a simple "reply" with your email > client, only the author of this message will receive > your answer. You need to do a "reply all" if you > want your answer to be distributed to the entire > group. > > _____________________________________ > About this discussion group: > > To Join: Send an email to > To Post: Send an email to > > To Leave: Send an email to > Archives: http://www.yahoogroups.com/group/c6x > > Other Groups: http://www.dsprelated.com > ">http://docs.yahoo.com/info/terms/ __________________________________________________

simha j wrote: > hi, > > i am using ccs2 for 621x. > I was Profiling a 'for loop' of my c-code which loops > for count 0, few equations in it. > For this case I got clock050. > > but when i made count =1 (i.e., only one iteration), > I am getting clock = 550. > > so for count 0, clock becomes 550*200 which is not > correct. > > where i am going wrong???? > > looking forward to your replies. > > bye What this sounds like, is that when you are running one iteration of the loop you are not using the software pipelined loop because of insufficient number of iterations. This why the cycle counts for a single iteration seem high. You need a certain minimum number of iterations to get the loop primed and busy. In fact it can be seen that your steady state performance is 75 cycles per iteration as opposed to 550, which is a 7x improvement in performance. This is what software pipeling buys you, and in which case the saying "the more the meerier" is aptly true. Regards Jagadeesh Sankaran

hi, i am using ccs2 for 621x. I was Profiling a 'for loop' of my c-code which loops for count 0, few equations in it. For this case I got clock050. but when i made count =1 (i.e., only one iteration), I am getting clock = 550. so for count 0, clock becomes 550*200 which is not correct. where i am going wrong???? looking forward to your replies. bye