Overclock.net › Forums › Industry News › Hardware News › [Official] AMD Bulldozer Reviews Thread
New Posts  All Forums:Forum Nav:

[Official] AMD Bulldozer Reviews Thread - Page 106

post #1051 of 2308
Quote:
Originally Posted by rubicsphere View Post
Were there any non-GPU limited high end dual card setup benchmarks?
I'm also interested in this. I remember I saw a revew witch showed thuban putting up impressive MIN fps in multicard setups.

I might be mistaken
post #1052 of 2308
Quote:
Originally Posted by Behemoth777 View Post
Maybe more optimization with programs and such, but processors don't improve in performance like video cards do when they get a bios/driver update.
Try and remember: this is such a radical departure from every x86 CPU ever produced, that it's entirely possible that OS patches and re-structuring of schedulers and/or BIOS fixes may actually fix a lot of what we're seeing as bad performance. Hell, if anyone reads the Anand review, the last page pretty much sums it up -- AMD says Windows 7's scheduler cannot allocate threads appropriately. So you may say, "Well, why didn't they make something more appropriate for the times?" And I would say that making small architectural changes are no longer "looking forward". BD is a huge gamble, and the payoff is not going to be immediate.

That being said, I would like to see how the FX would do in some Linux benches -- wishful thinking, and I'm not sure I'm up to spending 250 bucks to find out.
post #1053 of 2308
This just feels that amd released bulldozer for the sake of releasing it. Power and performance wise, it cannot compete with stars yet. They should've canned this beast until it can actually beat out the previous architecture, and release an 8 core stars based chip. Maybe piledriver can be to bulldozer what stars was to barcelona.
Edited by cky2k6 - 10/12/11 at 9:55am
Heisenberg
(16 items)
 
  
CPUMotherboardGraphicsRAM
Core i7 4930k Asus RIV BE HIS HD7970x3 4x4GB Corsair 2133 
Hard DriveHard DriveHard DriveCooling
Samsung 840 Evo 500GB 2 Crucial m4 256gb raid 0 4TB Hitachi EK rivbe monoblock + ek 7970fc 
OSMonitorKeyboardPower
Windows 8.1 Pro 27" LED Cinema + 27" Auria 2560x1440 Mionix Zibal 60 Corsair ax1200i 
CaseMouseAudioAudio
Case Labs TH10 Mionix Naos 5000 Asus Xonar d2x Teac ha-501 amp & hd650/dt880 600 ohm cans 
  hide details  
Reply
Heisenberg
(16 items)
 
  
CPUMotherboardGraphicsRAM
Core i7 4930k Asus RIV BE HIS HD7970x3 4x4GB Corsair 2133 
Hard DriveHard DriveHard DriveCooling
Samsung 840 Evo 500GB 2 Crucial m4 256gb raid 0 4TB Hitachi EK rivbe monoblock + ek 7970fc 
OSMonitorKeyboardPower
Windows 8.1 Pro 27" LED Cinema + 27" Auria 2560x1440 Mionix Zibal 60 Corsair ax1200i 
CaseMouseAudioAudio
Case Labs TH10 Mionix Naos 5000 Asus Xonar d2x Teac ha-501 amp & hd650/dt880 600 ohm cans 
  hide details  
Reply
post #1054 of 2308
Quote:
Originally Posted by sub50hz View Post
Try and remember: this is such a radical departure from every x86 CPU ever produced, that it's entirely possible that OS patches and re-structuring of schedulers and/or BIOS fixes may actually fix a lot of what we're seeing as bad performance. Hell, if anyone reads the Anand review, the last page pretty much sums it up -- AMD says Windows 7's scheduler cannot allocate threads appropriately.
What did they use to test Bulldozer on during development then? How would they be able to know what BD's performance would be like on Windows 7 if it currently doesn't work properly? And how were they getting those 1337 benches that showed BD neck and neck with the 980X? That sounds like a bunch of evasive BS on AMD's part if you ask me.
post #1055 of 2308
Quote:
Originally Posted by Papas View Post
now this is a serious question. since when has any cpu beat another cpu(with 2x's as many cores) in a multi threaded task? i have never seen a test where a dual core beat a quad in something that used all the cores. To me, in my honest opinion, it seems like bulldozer is not being fully utilized. not that its underpower. If it was underpowered, it would be loosing in all tests, not just some of them. it seems like some of the test are more optimized than others.

Trying to explain myself better. in a bunch of tests it scores worse than the 2500k, then in some others it scores better than a 2600k, how is that possible unless the testing is not using the full power of the cores? Ohh, BTW, im not talking about single threaded performance. im talking about multi threaded where it looses to the 2500k and then somehow wins in others against the 2600k.
It would have been nice if AMD would have let some of the benchmark makers play with Bulldozer before now. Then this could have been mitigated some. As it stands right now...this is very possible. We might have to wait for a few days for some new version of benches to be made. Though I don't see massive improvemnt coming. From the looks of it there might actually be bottle necks INSIDE the cpu its self, though. When these bottle necks don't matter...then it does OK. When they do matter it does horrible.

This is what we get with AMD's hush-hush nonsense.

Arg...I hate to say it, but I think some more time is need to know for sure. Though my guess is that any benchmark software not fully utilizing Bulldozer based CPUs will have a new version out by this weekend.

If AMD releases a special driver fix for Catalyst to make it perform better I think I might have go down to AMD corporate and start slapping people...they've had plenty of time to make Catalyst make good use of Bulldozer.
Edited by Vagrant Storm - 10/12/11 at 9:58am
My System
(16 items)
 
  
CPUMotherboardGraphicsGraphics
2600K @ 4.7GHz Asus P8P67 B3 GTX 580 EVGA Hydro Copper 2 GTX 580 EVGA  
RAMHard DriveOptical DriveOS
4x4GB G.Skill Ripjaws bunch of 'em Blu-Ray For movies Windows 8.1 
MonitorMonitorKeyboardPower
24.4" Hans G HH251 X2 Yamakasi DS270  Blah 1000watt Super Flower 
CaseMouseMouse PadAudio
Built into Desk Microsoft SideWinder X8 Comfy one... Creative Extreme Gamer 
  hide details  
Reply
My System
(16 items)
 
  
CPUMotherboardGraphicsGraphics
2600K @ 4.7GHz Asus P8P67 B3 GTX 580 EVGA Hydro Copper 2 GTX 580 EVGA  
RAMHard DriveOptical DriveOS
4x4GB G.Skill Ripjaws bunch of 'em Blu-Ray For movies Windows 8.1 
MonitorMonitorKeyboardPower
24.4" Hans G HH251 X2 Yamakasi DS270  Blah 1000watt Super Flower 
CaseMouseMouse PadAudio
Built into Desk Microsoft SideWinder X8 Comfy one... Creative Extreme Gamer 
  hide details  
Reply
post #1056 of 2308
Quote:
Originally Posted by Malcolm View Post
What did they use to test Bulldozer on during development then? How would they be able to know what BD's performance would be like on Windows 7 if it currently doesn't work properly? And how were they getting those 1337 benches that showed BD neck and neck with the 980X? That sounds like a bunch of evasive BS on AMD's part if you ask me.
It's very possible that AMD has worked with/is currently working with MS to see if it's something that can be rolled out with a hotfix. Rather than calling bullcrap, try and be a little more objective.
post #1057 of 2308
I remeber when first speculation where 50% increase performance with 33% increase core count. Now its 25% less performance with 33% increased core count and we were complaining that 50% increase was not so much considering the extra 2 core.
Ishimura
(21 items)
 
Silent Knight
(13 items)
 
 
CPUMotherboardGraphicsRAM
Intel Core i7 3770K @ 4.6GHz ASRock Z77E-ITX eVGA GTX 1080 Ti Hybrid AMD Radeon R9 16GB DDR3-2400MHz  
Hard DriveHard DriveCoolingCooling
SanDisk Ultra II 960GB Toshiba X300 5TB Corsair H100i GTX eVGA Hybrid Water Cooler  
CoolingOSMonitorKeyboard
4x GentleTyphoon AP-15 Windows 10 Pro 64-Bit Philips Brilliance BDM4065UC 4K Razer BlackWidow Chroma  
PowerCaseMouseMouse Pad
eVGA SuperNOVA 750 G3 Define Nano S Logitech G502 Proteus Core PECHAM Gaming Mouse Pad XX-Large 
AudioAudioAudioAudio
Audioengine D1 DAC Mackie CR Series CR3 Audio-Technica ATH-M50 Sennheiser HD 598 
Audio
Sony XB950BT 
CPUMotherboardGraphicsRAM
AMD Phenom II X4 955 @ 4.2GHz ASUS M4A79XTD EVO AMD Radeon HD 7970 3GB @ 1200/1500 2x 4GB G.SKILL Ripjaws X DDR3-1600 
Hard DriveHard DriveHard DriveCooling
OCZ Agility 3 60GB WD Caviar Green 1.5TB 2 x Seagate Barracuda 2TB XSPC Raystorm 
CoolingCoolingOSPower
EK-FC7970 XSPC RS360 Windows 10 Pro 64-Bit Corsair TX750 
Case
NZXT Switch 810  
  hide details  
Reply
Ishimura
(21 items)
 
Silent Knight
(13 items)
 
 
CPUMotherboardGraphicsRAM
Intel Core i7 3770K @ 4.6GHz ASRock Z77E-ITX eVGA GTX 1080 Ti Hybrid AMD Radeon R9 16GB DDR3-2400MHz  
Hard DriveHard DriveCoolingCooling
SanDisk Ultra II 960GB Toshiba X300 5TB Corsair H100i GTX eVGA Hybrid Water Cooler  
CoolingOSMonitorKeyboard
4x GentleTyphoon AP-15 Windows 10 Pro 64-Bit Philips Brilliance BDM4065UC 4K Razer BlackWidow Chroma  
PowerCaseMouseMouse Pad
eVGA SuperNOVA 750 G3 Define Nano S Logitech G502 Proteus Core PECHAM Gaming Mouse Pad XX-Large 
AudioAudioAudioAudio
Audioengine D1 DAC Mackie CR Series CR3 Audio-Technica ATH-M50 Sennheiser HD 598 
Audio
Sony XB950BT 
CPUMotherboardGraphicsRAM
AMD Phenom II X4 955 @ 4.2GHz ASUS M4A79XTD EVO AMD Radeon HD 7970 3GB @ 1200/1500 2x 4GB G.SKILL Ripjaws X DDR3-1600 
Hard DriveHard DriveHard DriveCooling
OCZ Agility 3 60GB WD Caviar Green 1.5TB 2 x Seagate Barracuda 2TB XSPC Raystorm 
CoolingCoolingOSPower
EK-FC7970 XSPC RS360 Windows 10 Pro 64-Bit Corsair TX750 
Case
NZXT Switch 810  
  hide details  
Reply
post #1058 of 2308
Quote:
Originally Posted by nagle3092 View Post
It does, I wonder if there is something up with the Crosshair boards they sent out.
That's exactly what I've been thinking.
Quote:
Originally Posted by Vagrant Storm View Post
Benchmarks are not valid until after release I thought? That is what I've read about 14,713 times on OCN the last few days. BF3 is in beta so you can't use it. Plus if you are over 40fps...3fps or so is the margin of error. Unless you can tell me that you get the same exact results every time you run a bench on your system. In every other hardware test it would universally accepted that those results were limited by some other piece of hardware since they are so similar.

And I say again...a beta version of a game could easily account for the results too...especially when the 2500k beat the 2600k by a few fps(though I bet it is more to do with an unstable OC). Plus under the law of statistics you have to throw out the best and throw out the worst. BF3 is probably the best right now as far as gaming goes. I am not even sure what to pick to throw out the worst...it could be one many.
Why can't I use BF3? Because it's beta? Seriously? That's about the silliest thing I've ever heard. You're comparing performance of the same program. Regardless of whether or not it's beta. That argument is invalid and its beta status is irrelevant.

And while you may try to minimize it as "just a few FPS", when you look at it, in percents, there's a much larger margin. I surely can tolerate margin of error, however, they said that they ran each test three times. Besides, we're not talking just "a few fps", we're talkin between 8 and 15. Don't try to minimize that Intel is not favored.

As for my results, while sure they're not identical every time, all of my results have been within 1% of each other. That's more about methodology and how the tests/BM's are run. It has to be consistent if you expect consistent results.

Quote:
Originally Posted by Papas View Post
now this is a serious question. since when has any cpu beat another cpu(with 2x's as many cores) in a multi threaded task? i have never seen a test where a dual core beat a quad in something that used all the cores. To me, in my honest opinion, it seems like bulldozer is not being fully utilized. not that its underpower. If it was underpowered, it would be loosing in all tests, not just some of them. it seems like some of the test are more optimized than others.

Trying to explain myself better. in a bunch of tests it scores worse than the 2500k, then in some others it scores better than a 2600k, how is that possible unless the testing is not using the full power of the cores? Ohh, BTW, im not talking about single threaded performance. im talking about multi threaded where it looses to the 2500k and then somehow wins in others against the 2600k.
Exactly. The results are so mixed, they almost make no damn sense.
Edited by BlackOmega - 10/12/11 at 10:02am
Black Box
(16 items)
 
  
CPUMotherboardGraphicsRAM
i7 3770k Asus P8Z77-Vpro Evga 780 Classified Crucial Ballistix 
Hard DriveHard DriveOptical DriveCooling
A-Data 128GB SSD Samsung Spinpoint F3 1TB Pioneer BDR-207DBK Corsair H80 
OSMonitorKeyboardPower
Win 7 pro 64 Hannspree 25" 1080p LCD 2ms Razer Lycosa PC Power & Cooling 760w 
CaseMouseMouse PadAudio
Corsair 550D MX 518 Allsop Creative XFi Xtreme music 
  hide details  
Reply
Black Box
(16 items)
 
  
CPUMotherboardGraphicsRAM
i7 3770k Asus P8Z77-Vpro Evga 780 Classified Crucial Ballistix 
Hard DriveHard DriveOptical DriveCooling
A-Data 128GB SSD Samsung Spinpoint F3 1TB Pioneer BDR-207DBK Corsair H80 
OSMonitorKeyboardPower
Win 7 pro 64 Hannspree 25" 1080p LCD 2ms Razer Lycosa PC Power & Cooling 760w 
CaseMouseMouse PadAudio
Corsair 550D MX 518 Allsop Creative XFi Xtreme music 
  hide details  
Reply
post #1059 of 2308
Quote:
Originally Posted by sub50hz View Post
It's very possible that AMD has worked with/is currently working with MS to see if it's something that can be rolled out with a hotfix. Rather than calling BS, try and be a little more objective.
BD has been in development for this long and they still haven't managed to get this mythical patch out yet?
    
CPUMotherboardGraphicsRAM
2x intel Xeon E5-2650 Supermicro MBD-X9DR3-F-O Onboard awesomeness 8 x 8GB Kingston DDR3 1333 ECC 
Hard DriveCoolingOSMonitor
4x WD Green 2TB in RAID 10 2x Coolermaster Hyper 212 EVOs Windows Server 2012 Datacenter 3x Dell Ultrasharp U2410s 
PowerCase
Corsair AX1200 Case Labs TX10-D 
  hide details  
Reply
    
CPUMotherboardGraphicsRAM
2x intel Xeon E5-2650 Supermicro MBD-X9DR3-F-O Onboard awesomeness 8 x 8GB Kingston DDR3 1333 ECC 
Hard DriveCoolingOSMonitor
4x WD Green 2TB in RAID 10 2x Coolermaster Hyper 212 EVOs Windows Server 2012 Datacenter 3x Dell Ultrasharp U2410s 
PowerCase
Corsair AX1200 Case Labs TX10-D 
  hide details  
Reply
post #1060 of 2308
Thanks for the reviews. Does anyone know if there are reviews with crossfire/sli gpus?? Just wondering about multi gpu stability with these cpu's
KOMAHDIR
(14 items)
 
  
CPUMotherboardGraphicsRAM
Intel I5-2500k  Asus p8z68-v/gen3 Sapphire AMD 290 8GB g-skill snipers @ 1866 9,10,10,28 
Hard DriveCoolingOSMonitor
256 Crucial M4 XSPC,Swiftech,EK windows 8.1 ViewSonic VX2370Smh-LED Black 23" 
PowerCase
Coolermaster 850W Silent Pro Coolermaster CM690 
  hide details  
Reply
KOMAHDIR
(14 items)
 
  
CPUMotherboardGraphicsRAM
Intel I5-2500k  Asus p8z68-v/gen3 Sapphire AMD 290 8GB g-skill snipers @ 1866 9,10,10,28 
Hard DriveCoolingOSMonitor
256 Crucial M4 XSPC,Swiftech,EK windows 8.1 ViewSonic VX2370Smh-LED Black 23" 
PowerCase
Coolermaster 850W Silent Pro Coolermaster CM690 
  hide details  
Reply
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: Hardware News
Overclock.net › Forums › Industry News › Hardware News › [Official] AMD Bulldozer Reviews Thread