Jump to content
HWBOT Community Forums

Strunkenbold

Crew
 View Profile  See their activity

  • Posts

    2209

  • Joined

  • Last visited

  • Days Won

    39

 Content Type 

Posts posted by Strunkenbold

    Big Mess in Intel GMA Sections

    in Submission & member moderation

    Posted

    I will investigate but afaik the HD 2000/3000/4000 mobile is the exact same as the desktop version.

     

    IIRC the HD3000 in the desktop variant has more options to change clock speed. Just like a free multi. The mobile chips remain at 650Mhz and lower. So actually this should qualify for an extra HD3000 mobile section, although this may be just a limitation by the mobile chipsets.

    HWBOT R5 Bugs/Features 2.0 - Report bugs or request new HWBOT features here

    in HWBOT Rev.5

    Posted

    - You can already search for benchmarks by socket: http://hwbot.org/search/submissions => socket is available under processor and videocard

     

    What I wanted to say is, it would be more comfortable to have this implemented in the rankings. Like this:

     

    Family: All | Intel | s478 | Pentium 4 | Pentium 4 3,0Ghz Prescott

     

    Also search has some bugs:

    -click on a result opens a new tab (which is correct) but also opens the result in the search tab (which is twice)

    -searching for socket a gives no results (because s462 also exists)

    -best am2 submission is a Phenom X2 555BE (??)

    -searching for s478 mixes results with Socket P

     

    and most annoying: It actually doesnt give you the best results! Look s2011 for instance

    HWBOT R5 Bugs/Features 2.0 - Report bugs or request new HWBOT features here

    in HWBOT Rev.5

    Posted

    - The UCBench SSE2 'boost' is known - it's quite reproducable, a bit like CL in 3DM01.

     

    If you look closer to the result I posted, you see that the top score is done with 64k threads and non-sse. How is that to explain?

    Also the "trick" with many threads is unexplainable. From wprime we know that creating that many threads on a single core cpu costs very much time. Why are the scores in UCBench getting better then? Tweaking ram or cpu for better results also dont make sense, cause you can just rerun the bench and hope for some fancy result popping up. (which will usually do and you beat much better configs)

    HWBOT R5 Bugs/Features 2.0 - Report bugs or request new HWBOT features here

    in HWBOT Rev.5

    Posted · Edited by Strunkenbold

    Bugs:

    -Phenom achievement doesnt work

    -socket 1156 pentiums and xeons doesnt count for the 1156 achievements

    -some arrandale mobile cpu's are listed as socket 1156, should be 989

    -clicking on cpu core in hardware browser results in a 404

     

    Features:

    -possibility to sort cpu benchmark results by socket, to find out which is the fastest of s478 for instance

    edit:

    -remove ucbench from hwbot as calculations seems to be buggy

    -results are more coincidence as everything else, good example here (sse2 is slower than non-sse), many threads makes better results- there is no plausible explanation for this

    Big Mess in Intel GMA Sections

    in Submission & member moderation

    Posted

    The situation in the GMA 950 mobile section is even more complicated.

     

    There are lots of results with Intel Atom processors that have his own category. The name of this category seems to be also wrong as atom uses 945GSE and it seems that GPU-Z is reporting things incorrectly. To make things even more interesting there are also results with 64bit memory interface (non atom) resulting of single channel ram (because these devices have just one ram slot).

     

    Also I dont understand the cryptic naming pattern. Wouldnt it be easier to make just 3 categorys like that:

    Intel GMA 950 (desktop)

    Intel GMA 950 (mobile)

    Intel GMA 950 (mobile) 64bit

    Big Mess in Intel GMA Sections

    in Submission & member moderation

    Posted

    From time to time Ive been looking through these and I see lots of results in the wrong category's .

    In the GMA HD (Clarkdale) section do people continuously posting results with sandybridge cpus and even some results with arrandale cpus.

    The same for GMA HD mobile (Arrandale). People seems to dont know that there is no mobile sandy bridge section. As even the mobile one's are like the desktop HD2000 & HD3000 gpu's.

    Ive been already reporting some of these but there are many and I hope that a result moderator can go through all of these.

    Clarification in PCMark'05 about Tweaks // Tricks allowed

    in Benchmark software

    Posted

    Actually we're bugging the test with running it with Vista/7 as there was no Aero when pcmark05 was developed and than we trick it again by running Internet Explorer 7,8,9. In both cases calculation gets done which was not intended by the devs. While this maybe excused by the technical advance during the years, allowing registry tweaks cant be the way to go. It simply leads to no rendering in transp windows and IE of rendering blank white pages as the same like video compression calcs something that is less demanding than audio compression.

    Dont get it, why dont we just drop this bench? Only thing we do here is restrict "super tweaks" but we're still not run the bench like it was intended. And I fear this isnt even possible today.

×
×
  • Create New...