- Original Message -
From: "Stroller" <[EMAIL PROTECTED]>
To: <[EMAIL PROTECTED]>
Sent: Thursday, October 23, 2003 7:46 AM
Subject: Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
> Crucial were, in this particular case, about as much use as
On Oct 22, 2003, at 7:11 pm, flacycads wrote:
On Wednesday 22 October 2003 9:05 pm, Stroller wrote:
On Oct 22, 2003, at 5:43 pm, Hall Stevenson wrote:
As I posted within the last week, the laptop with which I am concerned
is a PII 400 with only 64meg of RAM. More RAM for this proprietary
form-fac
This whole trying to benchmark a user machine is fraught with difficulty
- things like preempt make it even more difficult.
For me, its tasks that can run for days where shaving a few hours off
the run time is useful, but not everyone does that. Unfortunately,
gentoo as a distro is particularly v
Bill Kenworthy wrote:
> For the reason that it is just a feeling: have you measured it, or is it
> imagination?
It feels faster and that's enough for me. You can't measure every day use in a
reliable way: there're just too many variables. So, if it feels faster, it IS
faster.
Of course, everyon
with only 64mb of memory you might be better of making gcc generate the smallest possible code, that way more will fit in memory so you dont have to swap as much, swapping a lot will definetly slow your system down.
On Wed, 2003-10-22 at 14:05, Stroller wrote:
On Oct 22, 2003, at 5:43 pm, Hal
For the reason that it is just a feeling: have you measured it, or is it
imagination?
BillK
On Wed, 2003-10-22 at 23:27, Norberto Bensa wrote:
> Bill Kenworthy wrote:
> > Ah, -Os was by *FAR* the slowest!
> >
>
> Really? Then why do I *feel* my box faster than ever before?
>
> Norberto
--
[EM
Bill Kenworthy wrote:
> Ah, -Os was by *FAR* the slowest!
>
Really? Then why do I *feel* my box faster than ever before?
Norberto
pgp0.pgp
Description: signature
see http://wdk.dyndns.org/flags.png.
Guess which one is -Os, 5th is -O3. Far right is:
"-Wno-deprecated -O2 -pipe -Wall -funroll-loops -fprefetch-loop-arrays
-finline-limit=1200 -falign-functions=32"
10 runs per flag combination, spikes are because its on a server in use.
-Os is consistently
On Wednesday 22 October 2003 9:05 pm, Stroller wrote:
> On Oct 22, 2003, at 5:43 pm, Hall Stevenson wrote:
> As I posted within the last week, the laptop with which I am concerned
> is a PII 400 with only 64meg of RAM. More RAM for this proprietary
> form-factor sub-notebook might be argued to be
begin quote
On Wed, 22 Oct 2003 22:05:01 +0100
Stroller <[EMAIL PROTECTED]> wrote:
>
> It was the previous posters' contention that -O2 would not be
> noticeably faster than -Os, but would produce larger binaries & take
> far longer to compile. It was Mr Kenworthy's emphasis in the statement
On Oct 22, 2003, at 5:43 pm, Hall Stevenson wrote:
At 11:59 AM 10/22/2003, you wrote:
Arg! I'm in the middle of recompiling my WHOLE kdelibs using -Os at
the advice of another poster here.
I really would like a definitive answer here, and don't have the time
for multiple recompilations myself.
W
At 11:59 AM 10/22/2003, you wrote:
Arg! I'm in the middle of recompiling my WHOLE kdelibs using -Os at the
advice of another poster here.
I really would like a definitive answer here, and don't have the time for
multiple recompilations myself.
When you do figure out which is the "best" flag to us
>-Original Message-
>From: Stroller [mailto:[EMAIL PROTECTED]
>Sent: Wednesday, October 22, 2003 10:59 AM
>To: [EMAIL PROTECTED]
>> Ah, -Os was by *FAR* the slowest!
>
>Arg! I'm in the middle of recompiling my WHOLE kdelibs using
>-Os at the
>advice of another poster here.
>I really would
On Oct 22, 2003, at 6:02 am, Bill Kenworthy wrote:
On Wed, 2003-10-22 at 12:46, Norberto Bensa wrote:
Matt Garman wrote:
Indeed, in this case, O2 is faster than O3. I assumed Debian's gcc
package was compiled with O2, so I just re-merged my gentoo gcc using
O2. I recompiled my program, and now it
Ah, -Os was by *FAR* the slowest!
BillK
On Wed, 2003-10-22 at 12:46, Norberto Bensa wrote:
> Matt Garman wrote:
> > On Wed, Oct 22, 2003 at 07:08:39AM +0800, William Kenworthy wrote:
> > > On all the machines (athlon t-bird, p4) I have tried so far, -O3
> > > always decreases performance - O2 is
Matt Garman wrote:
> On Wed, Oct 22, 2003 at 07:08:39AM +0800, William Kenworthy wrote:
> > On all the machines (athlon t-bird, p4) I have tried so far, -O3
> > always decreases performance - O2 is best (dramatically so on
> > something like a
>
> Indeed, in this case, O2 is faster than O3. I assu
I dont have the figures in front of me, but reliably 4 and 8 create a
slowdown, 16 is about even, whilst 32 gives a slight gain. This is on
an athlon-tbird 1.4g. On a p4, no flag, and 4 were the similar - havent
got as far as the rest yet. As well as being processor dependent, I
would expect it
Biggest problem I am coming across is time. For "zip", I have 23 CFLAG
combinations, run 10 tests for each. That makes 23 emerges, and 230
timings to take. Can take nearly 24 hours to complete and the machine
is unusable (unless you dont mind noise in the timings).
And that doesnt include dynam
If you could please clarify for me, your saying compiling with -falign-functions=32
gives you gains?
> On all the machines (athlon t-bird, p4) I have tried so far, -O3 always
> decreases performance - O2 is best (dramatically so on something like a
> celery). Most of the other options you see me
On Wed, Oct 22, 2003 at 07:08:39AM +0800, William Kenworthy wrote:
> On all the machines (athlon t-bird, p4) I have tried so far, -O3
> always decreases performance - O2 is best (dramatically so on
> something like a
Indeed, in this case, O2 is faster than O3. I assumed Debian's gcc
package was c
Hi,
On Tuesday 21 October 2003 19:56, Matt Garman wrote:
> For what it's worth, the Debian system used:
>
> g++ (GCC) 3.3.2 20030908 (Debian prerelease)
>
> And the Gentoo system is using:
>
> g++ (GCC) 3.2.3 20030422 (Gentoo Linux 1.4 3.2.3-r2, propolice)
I am using:
gcc --version
gcc (GCC) 3.3
Ive been doing quite a lot of this stuff lately. Make a small script
that contains all the make options you are considering and compile and
time the program looking for the best combination. Takes forever, and
is specific to that application.
On all the machines (athlon t-bird, p4) I have tried
begin quote
On Tue, 21 Oct 2003 14:56:40 -0500
Matt Garman <[EMAIL PROTECTED]> wrote:
>
> For what it's worth, the Debian system used:
>
> g++ (GCC) 3.3.2 20030908 (Debian prerelease)
>
> And the Gentoo system is using:
>
> g++ (GCC) 3.2.3 20030422 (Gentoo Linux 1.4 3.2.3-r2, propolice)
>
>
On Oct 21, 2003, at 8:56 pm, Matt Garman wrote:
...Under the Debian
system, it took, on average, two or three seconds to load this data
into
memory. However, under the Gentoo system, it takes eight or nine
seconds on average to load the data.
What kernel are you using..? The Gentoo-sources kerne
Matt Garman wrote:
I just got a new hard disk and installed gentoo on it. I've got a c++
development project that I was working on that runs noticeably slower on
my gentoo box than it did on under my debian unstable installation.
I basically wrote a CSV file reader in C++. The implementation uses
Matt Garman wrote:
> That's a pretty dramatic change, in my opinion. No hardware on my
> system has changed (except the new disk, which I have verified is not
> the source of the slowdown (it's a 10k SCSI drive, should be faster if
> anything)).
If execution time appears unaffected I would make 1
not much to say dude, it should by no way be possibly slower than debian
:-)
On Tue, 2003-10-21 at 21:56, Matt Garman wrote:
> I just got a new hard disk and installed gentoo on it. I've got a c++
> development project that I was working on that runs noticeably slower on
> my gentoo box than it d
I just got a new hard disk and installed gentoo on it. I've got a c++
development project that I was working on that runs noticeably slower on
my gentoo box than it did on under my debian unstable installation.
I basically wrote a CSV file reader in C++. The implementation uses a
vector of vect
28 matches
Mail list logo