Re: [Valgrind-users] Valgrind 3.6.0 on ppc doesn't detect any "Invalid write" errors

2011-03-02 Thread Bart Van Assche
2011/3/1 Piotr AdaszyƄski > > [ ... ] > Could you tell me why results from ppc target are different ? What > could I do wrong ? Strange. Does the output of "make -s regtest" on your setup match that of the nightly PPC build (available in the valgrind-developers mailing list archives) ? Bart. --

Re: [Valgrind-users] dump-instrs problems

2011-03-02 Thread Josef Weidendorfer
On Monday 28 February 2011, Elie Shaccour wrote: > consider the following abstract code: > jne .L2 > add > sub > > .L2: > add > sub > > If the jump is taken 4 times and not taken once,in counting the number of > times each asm executed I get the following: > 5 > 1 > 1 > 1 > 1 > 4 > 4 > > is ther

Re: [Valgrind-users] fwrite and fread (cachegrind)

2011-03-02 Thread Josef Weidendorfer
On Monday 28 February 2011, Wan Mohd Fairuz Wan Ismail wrote: > Do cachegrind count misses function calls provoked by fwrite or fread? Not sure I understand that question, but any Valgrind tool only works on user level code. So if your program triggers lots of kernel work, this can not be seen by