Hello,
The xml feature is really neat. Thanks for the new command line options in
3.5.0.
When --time-stamp=yes is chosen, the xml file has timestamps
for the start and finish of the process and not for individual errors.
In very long running programs time stamp for non-leak errors
is the key to
Thanks for helping me John, here's the output
Sections from .o file:
There are 19 section headers, starting at offset 0x378b0:
Section Headers:
[Nr] Name TypeAddr OffSize ES Flg Lk
Inf Al
[ 0] NULL 00 00 00
Hi --
I'm using helgrind from 3.5.0 on OPENMP code.
I have a lazily malloc'd pthread mutex in a static global
variable that helgrind detects.
I'd like to disable the warning somehow in code, not
with a suppression, so that I can look at more interesting
errors.
So far I've failed to be able to
On Thu, Aug 27, 2009 at 5:30 AM, Zhao Qin wrote:
>
> I would like to evaluate translation overhead from application memory to
> shadow memory only. In another word, no overhead for checking and
> propagation.
> Is there any simple way to do it, e.g. an switch to turn on and off for it?
Nothing qui
Hi:
I would like to evaluate translation overhead from application memory to
shadow memory only. In another word, no overhead for checking and
propagation.
Is there any simple way to do it, e.g. an switch to turn on and off for it?
Best Regards
Qin
On Monday 24 August 2009, Ken wrote:
> I used callgrind to profile a storage engine of mysql and got this out put.
Can you add a bug report for your problem?
It is probably related to bug 177956, but I am not sure (the latter is about
switching on/off instrumentation).
Next important question: Any
> When intel compiler is used with profiler guided optimization,
> two new sections called "text.hot" and "text.unlikely" are
> created by the compiler. This is on Linux x86 32 bit.
Please show the relevant data from
readelf --sections foo.o
readelf --segments my_app
for an ET_REL object
Hello,
When intel compiler is used with profiler guided optimization,
two new sections called "text.hot" and "text.unlikely" are
created by the compiler. This is on Linux x86 32 bit.
The symbols in these sections are not read by Valgrind
and this causes many frames in memcheck error stack traces
