Page 2 of 3 FirstFirst
1
2
3
LastLast
  1. #21
    Quote Originally Posted by ita View Post
    This can't be accurate. I7 2600k is much better than I5 2500k yet it gives a lower result?
    It's two things:

    1) i5-2500K and i7-2600K gives same performance in games because Hyperthreading is worthless for games, and
    2) Margin of error between test runs. 2% is not statistically relevant anywhere, 5% difference comes still easy between two runs of same test in games that do not have pre-recorded benchmark demo.

    You can see another funny thing with Hyperthreading when comparing i5-760 and i7-920, where the 760 is actually better. That's because games do not like HT at all, and can sometimes actually lose speed because of it even though both CPUs run at same speed.

    Also one other thing worth extra attention in the chart is the performance of AMD x4 970 vs x6 1090T. Both of those are pulling roughly the same numbers, because again cores do not matter for games one bit. Because the x4 is much cheaper than x6, it's also better choice for a gaming computer, there are no ifs and buts about it.

    edit:

    Third thing worth noting is how high i3-2100 is actually in the chart, especially compared to AMD CPUs. Even though it has only two cores, games do not need more, and the raw clock speed combined with two generations newer technology makes it better performer than either x4 970 or x6 1090T, and it's also cheaper, driving the last nail in the coffin of AMDs being better in price or price/performance for gamers.
    Last edited by vesseblah; 2011-07-07 at 07:50 AM.
    Never going to log into this garbage forum again as long as calling obvious troll obvious troll is the easiest way to get banned.
    Trolling should be.

  2. #22
    High Overlord Repeant's Avatar
    10+ Year Old Account
    Join Date
    Mar 2011
    Location
    Canada
    Posts
    112
    As said multiple times Sandy bridge is pretty much running the show when it comes to CPU's I'm waiting for Bulldozer before I buy another Computer though, that aside my personal preference still lies in with AMD. Now ARM on the other hand has focused mainly on mobile devices Iphones,PSP(2)Vita ect, So they are fairly unknown in the Computer market when compared to AMD or Intel however they are pretty much the best at what they do. However this may change as Microsoft has announced Windows 8 will support ARM processors (possibly 7/vista), meaning that Microsoft will be supporting a chip with a new and streamlined architecture which makes it much more efficient then most current gen CPU's.

    So lots to look forward to

  3. #23
    ARM processors are meant for low power mobile devices, but regardless of Win8 support for it, those will not be viable alternative for gaming computers for many years to come. Low power optimized hardware simply will not run high performance applications properly. ARM Win8 is meant for tablets, not desktop computers.
    Never going to log into this garbage forum again as long as calling obvious troll obvious troll is the easiest way to get banned.
    Trolling should be.

  4. #24
    High Overlord Repeant's Avatar
    10+ Year Old Account
    Join Date
    Mar 2011
    Location
    Canada
    Posts
    112
    True enough that ARM deals in almost exclusively small devices, and Windows 8 is aimed to be a mobile device OS even though it is compatible with a normal system. However ARM already produces Chips that already push 2GH with multiple-cores and that is for smaller devices such as a phone which given the size is a lot of power. So yes 2GHz isn't amazing in comparison to a desktop but that doesn't mean that ARM won't try to expand into the desktop market.

    It may take a couple years but I don't think it would be to hard to improve the performance of their CPU's even if they have to design a new line. Overclocked CPU's with a push of a button seems to be the new standard. And CPU's like the I5-2500k have benched in above 4.5 GHz(3.3GHz normal), so the fact remains just from overclocking you can gain quite a large increase.

    So I'm still excited for the possibility of a full blow ARM CPU for a desktop

  5. #25
    Didn't ARM show a CPU running a W8 tablet at computex?
    Also Intel is looking to produce Atom-CPU's for tablets, not very succesful so far though. Their CPU's run way too hot, to a degree that you barely can hold the tablet.

  6. #26
    While I've always been an ATI/AMD fan, there's no denying that Intel just have better performance currently.

    Thanks to Elyaan for the great sig!

  7. #27
    Quote Originally Posted by Crowe View Post
    Intel has a market share of over 82% of the CPU market with AMD somewhere around 10% and ARM around 8%.

    Intel has a lot more resources to invest into CPU development and have been pushing CPU progress hard in the fast few years. Intel can afford to release a new and more efficient CPU architecture every two years while AMDs CPU design is only just getting it's first major overhaul in 6 years with the Bulldozer architecture.

    Considering the disparities between the two companies it's surprising that AMD has managed to keep up for so long. But with their aging chip architecture they're no match for Intels Sandy Bridge CPUs. Even as an AMD supporter I cannot deny the dominance of Intel in the current situation.

    However, things should change a little once Bulldozers hit the market. It probably won't steamroll Sandy Bridges but should at least be able to keep up. AMD also has an advantage over Intel in that it purchased ATI a couple of years ago giving it access to GPU technology. Since then AMD has been trying to unify CPUs and GPUs on a single APU chip. Their current Llano APUs and the coming Trinity APUs are the first fruits of that labor and gives AMD an edge in the budget market.

    Overall though the only way AMD can keep up with Intel is by keeping their prices low and trying to be as innovative as possible.

    Because, while Intel is undoubtedly No. 1 in the Desktop segment, that segment only makes up a small share of the total CPU market. Intels Atom CPU for Netbooks isn't all that great, ARM is dominating the hand-held market and AMDs Llano brings DX 11 power to Notebooks at a low price.
    The market shares you're referencing are their revenue share, not their actual market share.

    http://www.pcr-online.biz/news/36574...dy-Bridge-woes

    No one really knows how many AMD processors are in use vs Intel. Their current foothold in notebooks is doing quite well. No one can say AMD doesn't do mobile right, especially with those new integrated graphics controllers coming out that rival 8500 GTs.
    i7-4770k - GTX 780 Ti - 16GB DDR3 Ripjaws - (2) HyperX 120s / Vertex 3 120
    ASRock Extreme3 - Sennheiser Momentums - Xonar DG - EVGA Supernova 650G - Corsair H80i

    build pics

  8. #28
    Quote Originally Posted by Bendder View Post
    Bulldozer will change the way the field looks when it finally gets released. I'm not saying it's gonna be the king of all CPU's but I am waiting to see where it comes into the picture before I do any upgrades of my CPU/Mobo.

    Currently I have an i7 860 (4 core + HT) running at 3.6Ghz. That is MORE than enough for whatever I want to do with WoW or any other game I currently play.
    Bulldozer won't change anything except some apps that can actually use the 8 cores properly. Most likely even current Sandys still wipe the floor with it gaming wise.

  9. #29
    Quote Originally Posted by Hinaaja View Post
    Bulldozer won't change anything except some apps that can actually use the 8 cores properly. Most likely even current Sandys still wipe the floor with it gaming wise.
    Yeah, I'm sure you know all the inside info on benchmarks and stuff that we all somehow missed.

    Also, it's 16 cores (8 "modules", 2 cores per) with the equivalent of Intel's turboboost built in.
    Last edited by glo; 2011-07-07 at 11:22 AM.
    i7-4770k - GTX 780 Ti - 16GB DDR3 Ripjaws - (2) HyperX 120s / Vertex 3 120
    ASRock Extreme3 - Sennheiser Momentums - Xonar DG - EVGA Supernova 650G - Corsair H80i

    build pics

  10. #30
    Quote Originally Posted by ita View Post
    This can't be accurate. I7 2600k is much better than I5 2500k yet it gives a lower result?
    Considering wow doesn't use Hyper threading, and then giving the scenario, yes it could yield equal or lesser results even when clocked .1ghz higher. That said, it could have just been a small hiccup during that test that caused it to show up as slightly lower.

  11. #31
    Deleted
    I bought a phenom II 965 BE about 2 years ago and i bought a 6970 and i have 150 fps on WoW in 10 mans and 250fps constant on COD black ops. Honestly if you want to buy something buy what you like and who you wish to support and then buy a decent VGA. My firend bought an i7 and a 480gtx, i still get better gaming performance. I wouldn't buy an Intel product for only 10-20 fps. Cpus do not offer that huge difference in performance unless its for a specific task. You want to compress 10gb files and you are not bothered to wait 2 more minutes?? then buy an i7, if you dont care to wait 2 minutes and love AMD for being stubborn mules then buy a Bulldozer when they come out.

  12. #32
    Quote Originally Posted by Alan1187 View Post
    Considering wow doesn't use Hyper threading, and then giving the scenario, yes it could yield equal or lesser results even when clocked .1ghz higher. That said, it could have just been a small hiccup during that test that caused it to show up as slightly lower.
    Correct. If you look at the thread involving the processAffinityMask testing, on post #22 some analytical work was done with HT and WoW. HT actually doesn't play well with WoW at all.

  13. #33
    Field Marshal Walthor's Avatar
    15+ Year Old Account
    Join Date
    Jan 2009
    Location
    The Netherlands
    Posts
    85
    Quote Originally Posted by vesseblah View Post
    You can see another funny thing with Hyperthreading when comparing i5-760 and i7-920, where the 760 is actually better. That's because games do not like HT at all, and can sometimes actually lose speed because of it even though both CPUs run at same speed.
    Would that be 'fixed' if you would force wow to run only on the actual physical cores and not the 4 extra HT cores?
    Quote Originally Posted by Boubouille View Post
    Needed the bandwidth for porn.
    Quote Originally Posted by Izhara View Post
    It's an invisible exploding mushroom. Jesus, man, mushrooms haven't done anything that awesome since Super Mario Brothers.

  14. #34
    Herald of the Titans Saithes's Avatar
    10+ Year Old Account
    Join Date
    Feb 2011
    Location
    Mun
    Posts
    2,719
    When I disable Hyperthreading I notice no performance boosts
    Intel Core i7 5820K @ 4.2GHz | Asus X99 Deluxe Motherboard | 16GB Crucial DDR4 2133 | MSI GTX 980 4G GAMING | Corsair HX750 Gold | 500GB Samsung 840 EVO

  15. #35
    Deleted
    I've always used AMD before, but with the newest build coming in few days I'm going to roll with i7-2600k.

  16. #36
    Quote Originally Posted by vesseblah View Post
    The discussion pretty much ends here...



    For the $50 price difference (in cpu+mobo) you get massive performance boost. AMD will give you decent computer at $400-500 price point if you need to fit monitor + all other fluff in the price, but if you have more to spend, Intel based system will always be superior in price/performance ratio from $500 to $50000 for gaming use.
    Extremely vague test with extremely vague details. This is by no means an accurate measurement/comparison of processors.

    I like Intel processors, but my $120 brand new 1075T@4GHZ likes to giggle @ Intel.~But I will say, when I go and build a hardcore gaming rig, I'm going Intel.

    There's a thread on the forum that shows you how to set your WoW to run on multiple cores, so my performance is off the charts

  17. #37
    Herald of the Titans Sephiracle's Avatar
    10+ Year Old Account
    Join Date
    Aug 2010
    Location
    Colorado
    Posts
    2,729
    Quote Originally Posted by Fidelity32 View Post
    Extremely vague test with extremely vague details. This is by no means an accurate measurement/comparison of processors.

    I like Intel processors, but my $120 brand new 1075T@4GHZ likes to giggle @ Intel.~But I will say, when I go and build a hardcore gaming rig, I'm going Intel.

    There's a thread on the forum that shows you how to set your WoW to run on multiple cores, so my performance is off the charts
    The only variable in those tests is the CPU, so I'm not sure why the results would classify as 'vague'
    LoL: Kr1sys
    WoW:'06 - '11 '14-?' : Krisys - Blood/Frost DK | Sephiracle - Arms/Prot Warrior | Sephyx - Shadow/Disc Priest | Petergriffin - Huntard


  18. #38
    Scarab Lord Wries's Avatar
    10+ Year Old Account
    Join Date
    Jul 2009
    Location
    Stockholm, Sweden
    Posts
    4,127
    Quote Originally Posted by glo View Post
    Also, it's 16 cores (8 "modules", 2 cores per) with the equivalent of Intel's turboboost built in.
    Nope. 4 modules with a total of 4 FP units and 8 integer units. Will show up like an 8-core processor in windows.

    ---------- Post added 2011-07-07 at 06:10 PM ----------

    Quote Originally Posted by Fidelity32 View Post
    Extremely vague test with extremely vague details. This is by no means an accurate measurement/comparison of processors.

    I like Intel processors, but my $120 brand new 1075T@4GHZ likes to giggle @ Intel.~But I will say, when I go and build a hardcore gaming rig, I'm going Intel.

    There's a thread on the forum that shows you how to set your WoW to run on multiple cores, so my performance is off the charts
    You can't set up wow to effectively use a lot of cores. Multithreaded optimisation needs to be done on programmer-level. The game has a lot of threads but only two of them are actually CPU heavy. Allowing the rest of them to run on the other cores (which they do by default anyway) won't make much of a difference.

    But YES. That chart IS creepy. I recall they bench WoW by doing a /timetest (taxi flying) over a cataclysm zone (empty of inhabitants during /timetest) and recording the FPS with fraps. Now while it's a reliable way of making sure all CPUs are treated equally, they still don't really tell us how the CPU's respond to raiding and/or many players in crowded areas. It would be nice of blizzard to make a synthetic benchmark of some kind for this (a raid simulation or the like), though that isn't likely to happen.

    So all we have is that creepy chart.
    Last edited by Wries; 2011-07-07 at 06:11 PM.

  19. #39
    Quote Originally Posted by Wries View Post
    Nope. 4 modules with a total of 4 FP units and 8 integer units. Will show up like an 8-core processor in windows.
    Uh, "nope"!

    16 core and 32 core versions are being developed, chief.

    http://www.theinquirer.net/inquirer/...lldozer-server
    i7-4770k - GTX 780 Ti - 16GB DDR3 Ripjaws - (2) HyperX 120s / Vertex 3 120
    ASRock Extreme3 - Sennheiser Momentums - Xonar DG - EVGA Supernova 650G - Corsair H80i

    build pics

  20. #40
    Scarab Lord Wries's Avatar
    10+ Year Old Account
    Join Date
    Jul 2009
    Location
    Stockholm, Sweden
    Posts
    4,127
    Quote Originally Posted by glo View Post
    Uh, "nope"!

    16 core and 32 core versions are being developed, chief.

    http://www.theinquirer.net/inquirer/...lldozer-server
    The AMD FX top-model for this coming generation for home consumer use will be 8 core. That there are server-oriented (low clockspeed) CPUs being developed isn't something interesting (nor surprising) for our line of use, now is it?

Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts
  •