Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
- 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 a chocolate > firewall. I am sure they're usually very good, but on this occasion > their tech support staff were uninformed & told me about DIMMs when I > had clearly stated that I required memory for a Vaio C1 Picturebook > (and given the model number). > > Stroller. > And they can do nothing for a Dell 8250 with Rambus! 512MB -> 1GB is my plan. Tom Veldhouse -- [EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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-factor sub-notebook might be argued to be prohibitively expensive, at $160 or so for 64meg... Have you looked up your machine on the Crucial.com memory configurator page? YES! I can't imagine paying $160 for 512MB or even 1GB sticks of DDR, much less for 64MB of anything. You might luck out, and Crucial offers your type "proprietary"... Crucial were, in this particular case, about as much use as a chocolate firewall. I am sure they're usually very good, but on this occasion their tech support staff were uninformed & told me about DIMMs when I had clearly stated that I required memory for a Vaio C1 Picturebook (and given the model number). Stroller. -- [EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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 vulnerable to "use this and its
faster" and then its compared to something else and is found to be
slower on the numbers.
Unfortunately it has to come down to "if you haven't measured/compared
it, then it didn't happen." if you are going to recommend it to someone
else.
BillK
On Thu, 2003-10-23 at 12:48, Norberto Bensa wrote:
> 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, everyone can test on their own if -Os if faster or slower than -O2.
> But what I can say for sure is: on a P3 box, -O3 is NOT faster than -O{s,2}
>
> Regards,
> Norberto
--
[EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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, everyone can test on their own if -Os if faster or slower than -O2.
But what I can say for sure is: on a P3 box, -O3 is NOT faster than -O{s,2}
Regards,
Norberto
pgp0.pgp
Description: signature
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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, Hall Stevenson wrote: > At 1w1:59 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 use, let us know if > your system is truly noticeably faster. My money says you won't notice > the difference. The compiled files will be bigger, but probably not > faster (to a human). 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 "-Os was by *FAR* the slowest" that suggested the difference might be noticeable. 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 prohibitively expensive, at $160 or so for 64meg. I think I'll probably have to bite the bullet, but I think that on this machine performance may be more noticeable than on most. Unfortunately compilations take far longer also. At present I am more interested in getting compilation to support prelinking, which I'm finding quite a confusing process, but since I have made several big recompiles in the last few days it would be nice to know that I'm using the optimal flags. Stroller. -- [EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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 -- [EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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 as bad as this, but it is impossible to try every combination. Other flags can vary depending on the application used for testing, cpu etc. This is part of a project I am doing and more detail will be available when finished (some of the runs shown here are not representative of previous runs - consistency with the small differences some flags make is a problem on an in-use system over long time spans). Note that a graph like this takes ~10 hours to run, and many more to test and set up. It has been done using a perl driver script to manage the process. Note that I am on a dialup, so accessing the png may be a bit slow. BillK On Thu, 2003-10-23 at 05:05, Stroller wrote: > 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. > > > > When you do figure out which is the "best" flag to use, let us know if > > your system is truly noticeably faster. My money says you won't notice > > the difference. The compiled files will be bigger, but probably not > > faster (to a human). > > 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 > "-Os was by *FAR* the slowest" that suggested the difference might be > noticeable. > > 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 prohibitively expensive, > at $160 or so for 64meg. I think I'll probably have to bite the bullet, > but I think that on this machine performance may be more noticeable > than on most. Unfortunately compilations take far longer also. At > present I am more interested in getting compilation to support > prelinking, which I'm finding quite a confusing process, but since I > have made several big recompiles in the last few days it would be nice > to know that I'm using the optimal flags. > > Stroller. > > > -- > [EMAIL PROTECTED] mailing list -- William Kenworthy <[EMAIL PROTECTED]> -- [EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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 prohibitively expensive, > at $160 or so for 64meg. I think I'll probably have to bite the bullet, > but I think that on this machine performance may be more noticeable > than on most. Unfortunately compilations take far longer also. At > present I am more interested in getting compilation to support > prelinking, which I'm finding quite a confusing process, but since I > have made several big recompiles in the last few days it would be nice > to know that I'm using the optimal flags. > > Stroller. Have you looked up your machine on the Crucial.com memory configurator page? I can't imagine paying $160 for 512MB or even 1GB sticks of DDR, much less for 64MB of anything. You might luck out, and Crucial offers your type "proprietary" memory drastically cheaper- I have done so in the past with these types of boxes. Robert Crawford -- [EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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 No, That should be -O3 to -O2 , -O3 will make very very large files, and not as much improvement. -O2 or -Os is very much depending on the application. For a Desktop, I'd use -Os .. For media related libraries and prorams. -O2. //Spider -- begin .signature This is a .signature virus! Please copy me into your .signature! See Microsoft KB Article Q265230 for more information. end pgp0.pgp Description: PGP signature
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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. When you do figure out which is the "best" flag to use, let us know if your system is truly noticeably faster. My money says you won't notice the difference. The compiled files will be bigger, but probably not faster (to a human). 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 "-Os was by *FAR* the slowest" that suggested the difference might be noticeable. 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 prohibitively expensive, at $160 or so for 64meg. I think I'll probably have to bite the bullet, but I think that on this machine performance may be more noticeable than on most. Unfortunately compilations take far longer also. At present I am more interested in getting compilation to support prelinking, which I'm finding quite a confusing process, but since I have made several big recompiles in the last few days it would be nice to know that I'm using the optimal flags. Stroller. -- [EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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 use, let us know if your system is truly noticeably faster. My money says you won't notice the difference. The compiled files will be bigger, but probably not faster (to a human). Hall -- [EMAIL PROTECTED] mailing list
RE: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
>-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 like a definitive answer here, and don't have the time >for multiple recompilations myself. > >Stroller. > http://www.google.com/search?hl=en&ie=UTF-8&oe=UTF-8&q=speed+%22-Os%22+%22-O 2%22&btnG=Google+Search I've been thinking about doing the same thing you are for a little while. Basically from what I've seen in 2.95 Os was a little faster than O2 in alot of cases. In 3.2 this isn't true, but in 3.3 it swings back so that using Os could pick up some speed. I'm going to wait until 3.3 is stable until I do a mass recompile again. -- [EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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 is back to its better running time (two or three seconds to load all the records in memory). Yup. That's why I'm recompiling my whole system with -Os (even gcc, glibc, kernel, etc.) 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 like a definitive answer here, and don't have the time for multiple recompilations myself. Stroller. -- [EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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 best (dramatically so on > > > something like a > > > > 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 is back to its better running > > time (two or three seconds to load all the records in memory). > > Yup. That's why I'm recompiling my whole system with -Os (even gcc, glibc, > kernel, etc.) > > Regards, > Norberto -- [EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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 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 is back to its better running > time (two or three seconds to load all the records in memory). Yup. That's why I'm recompiling my whole system with -Os (even gcc, glibc, kernel, etc.) Regards, Norberto pgp0.pgp Description: signature
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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 to be application dependent. Makes sense when you read what man gcc says. BillK On Wed, 2003-10-22 at 03:49, [EMAIL PROTECTED] wrote: > 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 mentioned on the list show a > > small incremental advantage, except for -falign-functions=4 which also > > slows things down. Making this 32 gives a small advantage though. -- [EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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 dynamicly loaded libs that are pulled in ... Also, it seems that one set of flags may be faster on one application, but may have a different effect on another. BillK On Wed, 2003-10-22 at 09:56, 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 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 is back to its better running > time (two or three seconds to load all the records in memory). > > It would be interesting to actually develop a whole suite of tests to > see when O3 is faster (if ever) and when O2 is faster. Based on this > one (completely un-scientific :) test, I'd have to say that the C++ > standard library is best compiled with O2. > > For what it's worth, I did some benchmarking on my new drive as well, > and it's performing as good or better than the old drive. > > Thanks for all the feedback! If anyone else happens to do similar > testing or benchmarking of compiler optimizations, I'd be interested in > reading about them. > > Thanks again, > Matt > > > > -- > [EMAIL PROTECTED] mailing list -- [EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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 mentioned on the list show a > small incremental advantage, except for -falign-functions=4 which also > slows things down. Making this 32 gives a small advantage though. -- [EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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 compiled with O2, so I just re-merged my gentoo gcc using O2. I recompiled my program, and now it is back to its better running time (two or three seconds to load all the records in memory). It would be interesting to actually develop a whole suite of tests to see when O3 is faster (if ever) and when O2 is faster. Based on this one (completely un-scientific :) test, I'd have to say that the C++ standard library is best compiled with O2. For what it's worth, I did some benchmarking on my new drive as well, and it's performing as good or better than the old drive. Thanks for all the feedback! If anyone else happens to do similar testing or benchmarking of compiler optimizations, I'd be interested in reading about them. Thanks again, Matt -- [EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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) 3.3.1 20030927 (Gentoo Linux 3.3.1-r5, propolice) From my experience: gcc 3.3 is faster than 3.2. O3 is worse than O2/Os. Glück Auf Volker -- Conclusions In a straight-up fight, the Empire squashes the Federation like a bug. Even with its numerical advantage removed, the Empire would still squash the Federation like a bug. Accept it. -Michael Wong -- [EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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 so far, -O3 always decreases performance - O2 is best (dramatically so on something like a celery). Most of the other options you see mentioned on the list show a small incremental advantage, except for -falign-functions=4 which also slows things down. Making this 32 gives a small advantage though. As well as your program, you may need to optimise any dynamic libs that it relies on, as well as system services. Testing has also shown that something as simple as running an application in a frame-buffer, as against an xterm can slow an application that writes to the screen by ~10% (X is faster!) What does "ldd mybinary" show?, and what were the original flags in make.conf? Did you recompile the whole OS after changing make.conf? There are so many variables, including kernel options that comparing one distro to another is fraught with difficulty, and gentoo is at a disadvantage here as most users do not have the knowledge to pick the best options, whilst debian et al are conservative, but set up by very experianced people. BillK On Wed, 2003-10-22 at 03:56, 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 did on under my debian unstable installation. > > I basically wrote a CSV file reader in C++. The implementation uses a > vector of vectors (one vector per row for each field, and a vector for > every row). In other words: > > std::vector< std::vector< std::string > > data; > > Anyway, my data file has roughly 50,000 records. 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. (Run times don't change > appreciably between subsequent runs, so I don't think caching is the > issue here.) > > 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)). > > I haven't changed any compile settings from one system to the other. > Just for kicks, I tried using the optimising options I'm using for > Gentoo in my /etc/make.conf: "-O3 -march=athlon-xp -pipe". That knocked > a couple seconds off the load time, but the Debian-compiled version is > still much faster. > > 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) > > Looks like Debian's is a bit newer. I don't follow gcc development > really---have their been drastic improvements in a minor revision? > > Tonight I plan to setup grub to boot the old system to do some more > investigating. > > Thanks for any comments or thoughts! > Matt > > > > -- > [EMAIL PROTECTED] mailing list -- William Kenworthy <[EMAIL PROTECTED]> -- [EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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) > > Looks like Debian's is a bit newer. I don't follow gcc development > really---have their been drastic improvements in a minor revision? > Thats not a minor. thats about as major as its been previous years.. I think they had a 20% speedup in just plain compile times, and solidified the "athlon-xp" to actually be xp instead of athlon + sse. ACCEPT_KEYWORDS="~x86" emerge -vp gcc, Give it a whirl (if you dare) to get gcc 3.3 on Gentoo as well, then you at least come to the point of the same generation of compilers, might work better then ;) I also hope you checked so hdparm reports the same thing between debian and Gentoo. //Spider -- begin .signature This is a .signature virus! Please copy me into your .signature! See Microsoft KB Article Q265230 for more information. end pgp0.pgp Description: PGP signature
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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 kernels wossisname interactivity (IE: perceived performance on desktop apps) over actual straight-line performance. Have you tried running `/etc/init.d/hdparm start` & repeating your tests..? Stroller. -- [EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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 a vector of vectors (one vector per row for each field, and a vector for every row). In other words: std::vector< std::vector< std::string > > data; Anyway, my data file has roughly 50,000 records. 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. (Run times don't change appreciably between subsequent runs, so I don't think caching is the issue here.) 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)). I haven't changed any compile settings from one system to the other. Just for kicks, I tried using the optimising options I'm using for Gentoo in my /etc/make.conf: "-O3 -march=athlon-xp -pipe". That knocked a couple seconds off the load time, but the Debian-compiled version is still much faster. 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) Why don't you upgrade to 3.3.1-r4 (its currently ~x86 but it works well) or something similar on Gentoo and compile the program. Then you will know for sure. -- Andrew Gaffney -- [EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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 100% certain the new drive is actually performing as expected. Rick Kitty5 NewMedia http://Kitty5.com POV-Ray News & Resources http://Povray.co.uk TEL : +44 (01270) 501101 - ICQ : 15776037 PGP Public Key http://pgpkeys.mit.edu:11371/pks/lookup?op=get&search=0x231E1CEA -- [EMAIL PROTECTED] mailing list
Re: [gentoo-user] slightly OT: c++ performance: gentoo vs. debian
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 did on under my debian unstable installation. > > I basically wrote a CSV file reader in C++. The implementation uses a > vector of vectors (one vector per row for each field, and a vector for > every row). In other words: > > std::vector< std::vector< std::string > > data; > > Anyway, my data file has roughly 50,000 records. 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. (Run times don't change > appreciably between subsequent runs, so I don't think caching is the > issue here.) > > 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)). > > I haven't changed any compile settings from one system to the other. > Just for kicks, I tried using the optimising options I'm using for > Gentoo in my /etc/make.conf: "-O3 -march=athlon-xp -pipe". That knocked > a couple seconds off the load time, but the Debian-compiled version is > still much faster. > > 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) > > Looks like Debian's is a bit newer. I don't follow gcc development > really---have their been drastic improvements in a minor revision? > > Tonight I plan to setup grub to boot the old system to do some more > investigating. > > Thanks for any comments or thoughts! > Matt > > > > -- > [EMAIL PROTECTED] mailing list -- Regards, Redeeman () ascii ribbon campaign - against html e-mail /\- against microsoft attachments -- [EMAIL PROTECTED] mailing list
