SlackwareThis Forum is for the discussion of Slackware Linux.
Notices
Welcome to LinuxQuestions.org, a friendly and active Linux Community.
You are currently viewing LQ as a guest. By joining our community you will have the ability to post topics, receive our newsletter, use the advanced search, subscribe to threads and access many other special features. Registration is quick, simple and absolutely free. Join our community today!
Note that registered members see fewer ads, and ContentLink is completely disabled once you log in.
If you have any problems with the registration process or your account login, please contact us. If you need to reset your password, click here.
Having a problem logging in? Please visit this page to clear all LQ-related cookies.
Get a virtual cloud desktop with the Linux distro that you want in less than five minutes with Shells! With over 10 pre-installed distros to choose from, the worry-free installation life is here! Whether you are a digital nomad or just looking for flexibility, Shells can put your Linux machine on the device that you want to use.
Exclusive for LQ members, get up to 45% off per month. Click here for more info.
6 cores with hyper threading would be seen by the kernel as 12 cores. My i7 920 is seen as 8.
Yers, that doesnt make it a real 12 core (or 8 core in your case) CPU. 12 threads, 6 cores is reality.
Since its possible to get the real core count, having a misleading core count isnt very good work IMO.
Quote:
Originally Posted by 273
These two are my point though. I'd expect the motherboard may have some impact and I would assume the RAM configuration could have a major impact. If it's the same machine then it's inaccurate reporting (like the 12 cores thing) and if it's different machines then the whole test is invalid. Either way they've proven themselves untrustworthy.
It shouldnt be a different motherboard according to the insert. Even if it was a different motherboard, there are only X79 and X79 based C600 chipsets for LGA 2011 CPUs.
I'd doubt that anyone has pulled 2 x 4GB sticks and replaced them with a single 8GB stick.
As for the sound chip, I'm 100% sure that is reporting. I've got a realtek ALC888 sound chip, and dpending on where you look it will report as ALC888, HDA Codec Realtek, Intel HD Audio, or HDA (High Definition Audio) AMD/ATI South Bridge.
**** List of CAPTURE Hardware Devices ****
card 0: SB [HDA ATI SB], device 0: ALC888 Analog [ALC888 Analog]
Subdevices: 1/1
Subdevice #0: subdevice #0
card 0: SB [HDA ATI SB], device 1: ALC888 Digital [ALC888 Digital]
Subdevices: 1/1
Subdevice #0: subdevice #0
card 0: SB [HDA ATI SB], device 2: ALC888 Analog [ALC888 Analog]
Subdevices: 1/1
Subdevice #0: subdevice #0
cat /proc/asound/cards
Quote:
0 [SB ]: HDA-Intel - HDA ATI SB
HDA ATI SB at 0xfe024000 irq 16
Thats just from debian, I know I've seen other linxu distros give different results again.
*edit- Intel DX79SI does have a ALC892 sound chip. Even though its not listed on the intel site, its 'Intel High Definition Audio (Intel HD Audio) subsystem' there-
There is already a post in the discussion thread on the phoronix forums asking about it ("Looking at the image of system specifications it is at least two different systems (e.g. different sound cards?", page 3, post #26)-
IMO the differences are from 'bad use of a tool'. I wouldnt be so lazy as to get the benchmarking software to post a list of the hardware at all. If I did, and there was differences in the listed hardware, I'd make 100% sure that I was including a hard 'we did' or 'we didnt use the same hardware' (and BIOS settings) in the article.
If a tester is really untrustworthy, its easy to skew figures without changing hardware, just tweak a few BIOS settings.
If theres a sin there, its trusting software designed by the user ("Written by Michael Larabel"). Follow the name link and you get this-
Quote:
Michael Larabel is also the lead developer of the Phoronix Test Suite.
So the lead dev is the guy using the software that has listed the hardware. If he thought there was a issue, it would be fixed, or in the porcess of being fixed.
There is already a post in the discussion thread on the phoronix forums asking about it ("Looking at the image of system specifications it is at least two different systems (e.g. different sound cards?", page 3, post #26)-
Maybe rather than going round and round on the 'its different hardware', 'no its not' discussion, someone should go to the phoronix forums, point out the issues and uncertainties in the hardware list?
Surely its better to bring up issues with a full list of 'problems', where the authour will see them, in the community that has created the testing software? Even if its not 'better', its polite. If we dont give feedback to devs, in a place where they are likely to see it, how are they to know that we have problems with the software they have created.
Last edited by cascade9; 08-03-2012 at 07:20 AM.
Reason: addion, minor change
Ben Hutchings has announced the release of the 3.2.25 (diffs) stable kernel. It not only has the usual pile of important fixes, but also has a large set of backported fixes for memory management performance issues, courtesy of Mel Gorman.
Regardless how stable Slackware-current is, and how close 14.0.-beta will be to 14.0,
it is simply wrong to chose 14.0-beta and not 13.37. But Phoronix is famous for its odd benchmark tests.
While I generally agree with most of what has been said here about Phoronix benchmarks, I think, that if they had used 13.37, they'd be criticised for comparing an almost outdated release with an older kernal against new releases with new kernels, with obviously better optimisations, of the other distros, But if they are serious, they'll repeat the test with 14 release.
Is it possible, that Xfce was a limiting factor? As has been said, on Slackware recent releases of KDE are quite snappy, and, what may come as a surprise for many people, faster than Xfce. As far as I can tell, KDE was slower up to 4.5.5, but after that caught up with and finally passed by Xfce.
Don't get me wrong: Xfce is quite fast, and hasn't gotten any slower than it was, as far as I can tell, just KDE has become so much faster. It's finally back up to the speed I knew from KDE 3.5!
gargamel
EDIT: My statements are not based on stop-watch experiments or serious benchmarks, but just on "user experience", and may therefore be subjective in nature. However, I can assure you, that I use KDE and Xfce on exactly the same hardware.
While I generally agree with most of what has been said here about Phoronix benchmarks, I think, that if they had used 13.37, they'd be criticised for comparing an almost outdated release with an older kernal against new releases with new kernels, with obviously better optimisations, of the other distros, But if they are serious, they'll repeat the test with 14 release.
Is it possible, that Xfce was a limiting factor? As has been said, on Slackware recent releases of KDE are quite snappy, and, what may come as a surprise for many people, faster than Xfce. As far as I can tell, KDE was slower up to 4.5.5, but after that caught up with and finally passed by Xfce.
Don't get me wrong: Xfce is quite fast, and hasn't gotten any slower than it was, as far as I can tell, just KDE has become so much faster. It's finally back up to the speed I knew from KDE 3.5!
gargamel
EDIT: My statements are not based on stop-watch experiments or serious benchmarks, but just on "user experience", and may therefore be subjective in nature. However, I can assure you, that I use KDE and Xfce on exactly the same hardware.
I don't generally use XFCE since I go straight to fluxbox if I need to run something other than KDE, but with the 4.10 upgrade I logged in to see what it was about. I felt the same way, that KDE felt much quicker than XFCE. As is stated in the quote, I have no numbers to back up that statement, just my personal experience.
What aspect do you feel is sluggish? Startup, window operations, or something else? I'm using thunar from 4.10 in my dwm setup and even with the nouveau driver it's snappiness incarnate.
What aspect do you feel is sluggish? Startup, window operations, or something else? I'm using thunar from 4.10 in my dwm setup and even with the nouveau driver it's snappiness incarnate.
The time it takes just to open a program or draw a window are the two things I can say for certain, just because I did not spend much time in it. If it's not faster than KDE there really isn't any reason for me to spend much time with it. I use the Nvidia proprietary driver, but I run KDE with desktop effects enabled, mostly transparency, and it still opens, draws and renders everything faster that I can tell. I'm not limited in anyway by hardware, so on a different machine I might see very different results, but on this machine (the only one running current) KDE feels much faster. It's as close to instant as I can think of with the exception of fluxbox which may actually do things before I tell it too! LMAO.
The time it takes just to open a program or draw a window are the two things I can say for certain, LMAO.
Something's not right then.
Using my super scientific counting device , from the time I click on the icon to launch Xfce-terminal until it is displayed I make it to one m - I don't even get the entire first syllable of Mississippi out. Which happens to be the same speed as Fluxbox.
This is on an AMD x6 with 8GiB ram, 7200rpm SATA drive, and Nvidia GTS450. It's also the same with a core2duo laptop, 2GiB ram, intel GPU, and 5400RPM SATA drive. My dellmini 9 that runs Slackware from a 4GiB SD card also launches the GTK apps at near instant speeds (of course this does not include Firefox/Seamonkey).
I'd take a look and make sure that something is not dangling in the background chewing on CPU and/or or disk I/O.
Using my super scientific counting device , from the time I click on the icon to launch Xfce-terminal until it is displayed I make it to one m - I don't even get the entire first syllable of Mississippi out. Which happens to be the same speed as Fluxbox.
This is on an AMD x6 with 8GiB ram, 7200rpm SATA drive, and Nvidia GTS450. It's also the same with a core2duo laptop, 2GiB ram, intel GPU, and 5400RPM SATA drive. My dellmini 9 that runs Slackware from a 4GiB SD card also launches the GTK apps at near instant speeds (of course this does not include Firefox/Seamonkey).
I'd take a look and make sure that something is not dangling in the background chewing on CPU and/or or disk I/O.
Is it the same for non XFCE programs? Google Chrome, VLC, Firefox, etc? You may very well be right, that something isn't right, I've been backing up config files from the beta and plan on doing a clean install of 14 once it becomes final even though this was a clean install of -current about two weeks ago. I know something about KDE's file indexing was absolutely DESTROYING performance until it was disabled. There may be something similar with XFCE that I'm unaware of at this point.
Gedit, Brasero, Gthumb, SpaceFm, mkvmerge GUI, audacious, Abiword .... almost all GTK apps are instant.
For the heavier programs,
From a cold start, Seamonkey takes 2 almost 3 seconds to launch. Google Chrome takes under 2 seconds, Chromium is slightly faster on launch than Google Chrome, those three are instant for a warm start. Even Gimp launches in under 2 seconds.
Don't use VLC, but UMplayer starts instantly.
Last edited by disturbed1; 08-03-2012 at 09:35 PM.
While I generally agree with most of what has been said here about Phoronix benchmarks, I think, that if they had used 13.37, they'd be criticised for comparing an almost outdated release with an older kernal against new releases with new kernels, with obviously better optimisations, of the other distros,
Except that CentOS 6.2 was in the comparison, so they weren't considering kernel versions when making choices. But it still a sloppy comparison, maybe even so more.
What aspect do you feel is sluggish? Startup, window operations, or something else? I'm using thunar from 4.10 in my dwm setup and even with the nouveau driver it's snappiness incarnate.
There is *nothing* sluggisch in Xfce. It *is* damn' fast. Alas, recent KDE is *feels* even faster. Really, KDE 4.8.4 is up to a speed not known in years in KDE!
One thing is or feels still faster in Xfce, though. Despite the noticeable and significant improvements in Dolphin, Thunar is still a bit (!) faster, when I open directories with several thousands of files (RAW images from my digital camera). But Dolphin is now quite close, except for the largest of directories, and it is finally stable (had few crashes in the past with it, but none with KDE 4.8.4).
I don't really see what there is to worry about to be honest....I use Slackware because I love Slackware and I'm not really too concerned about what it benchmarks at in anyone's test.
Don't know about benchmarks and the such... I think Slackware 14 will be a _stellar_ release (I'm waiting for the finished product). KDE has really come along, (4.8.4 is a _huge_ improvement over 4.5.5 which was decent enough) and Xfce 4.10 will make a great candidate for my old MacBook Pro.
LinuxQuestions.org is looking for people interested in writing
Editorials, Articles, Reviews, and more. If you'd like to contribute
content, let us know.