Mail Archives: djgpp/2001/03/07/18:06:39
On 7 Mar 2001 21:07:59 GMT, Hans-Bernhard Broeker
<broeker AT physik DOT rwth-aachen DOT de> wrote:
>Damon Casale <damon AT wrong DOT redshift DOT com> wrote:
>> Hi, it's me again. I'm trying to get gprof to profile my compression
>> program correctly, and it's driving me batty. -_-
>
>> Here's the first few lines of (relevant) output:
>
>> Flat profile:
>
>> Each sample counts as 0.0555556 seconds.
>> % cumulative self self total
>> time seconds seconds calls Ts/call Ts/call name
>> 100.00 424.17 424.17 __dpmi_int
>
>See the FAQ. In a nutshell: either you've hit a gprof bug, or your
>program is completely bottlenecked by I/O operations.
Hmm. Apparently, I already have DJGPP v2.03. So that can't be the
problem.
I know that other functions in my code take time. I can turn off
compression, for instance, and make it go faster. (There are over
200,000,000 calls to longest_match, one of the compression functions,
which gprof says takes no time at all. That's completely untrue.)
I'm beginning to suspect that interrupts might have gotten turned off
somehow, or something like that. I'll let everyone know...
Damon Casale, damon AT WRONG DOT redshift DOT com (remove the obvious)
S(E)TI not found. There's no intelligent life here.
- Raw text -