Overclock.net › Forums › Industry News › Software News › [TH] Windows 8: Does AMD's Bulldozer Architecture Benefit?
New Posts  All Forums:Forum Nav:

[TH] Windows 8: Does AMD's Bulldozer Architecture Benefit?

post #1 of 41
Thread Starter 
Quote:
Shortly after AMD's Bulldozer architecture launched, AMD had us anticipating a couple of hotfixes that were supposed to improve FX-8150's performance. But Windows 8 was the ultimate goal. Now that the operating system is out, does it help FX-8150?
Quote:
It was a bummer, then, when AMD told us not to expect much from Windows 8 when it introduced FX-8350. But of course we wanted to go back and run benchmarks to follow up on our Bulldozer-based coverage. Can Microsoft's latest help make up some of the performance we were expecting to see back when FX-8150 launched, or are any possible operating system-related benefits already baked in?



Source.


The short answer is: at a 1% global difference, not really. The results from the different benchmarks are all over the place, sometimes there is almost no difference between the three, sometimes the unpatched Windows 7 wins, sometimes it's the patched Windows 7 that wins and sometimes it's Windows 8 that wins.

Windows 8 wins both audio transcoding tests, the first by 4 and 3 seconds compared to the patched Windows 7 and the unpatched Windows 7, the second by 5 and 6 seconds compared to the patched Windows 7 and the unpatched Windows 7.

However, if, for example, you're using Visual Studio 2010, the FX-8150 takes 20 seconds more to compile Chrome on Windows 8 than on the patched Windows 7 and 22 seconds more than on the unpatched Windows 7.

If you're using Adobe After Effects CS6, the unpatched Windows 7 wins by 6 and 5 seconds compared to the patched Windows 7 and Windows 8 respectively.

The only notable case where Windows 8 wins is in Dirt Showdown, where the unpatched Windows 7 comes second and the patched Windows 7 comes last, but that is with Medium detail settings with no AA. In the Ultra quality settings with 8x MSAA, they all perform the same.

In my opinion the supposed added efficiency of scheduling related threads to the same module which is supposed to be done in Windows 8 is negated by the fact that there are less resources available to each thread in the same module. Likewise, scheduling two related threads to different modules gives them more resources, but then they take longer to communicate with each other, so in many cases it ends up as a toss-up.
Edited by tpi2007 - 10/31/12 at 4:16am
 
Metro 2033 review
Metro 2033
CPUMotherboardGraphicsRAM
Core i7-3820 Asus Sabertooth X79 Gigabyte GTX 480 16 GB Corsair DDR3 1866 Mhz Dominator 
Hard DriveOptical DriveCoolingOS
Intel SSD 320 120GB + WD Caviar Black 1TB + 500GB Sony Optiarc DVD-RW Corsair A70, Noiseblocker M12-P + AC Accelero X... Windows 7 Home Premium 64-bit 
MonitorKeyboardPowerCase
LG Flatron L204WT Logitech wireless Corsair AX750 Professional Modular 80 Plus Gold Cooler Master HAF 912 Plus 
Mouse
Logitech optical wireless 
  hide details  
Reply
 
Metro 2033 review
Metro 2033
CPUMotherboardGraphicsRAM
Core i7-3820 Asus Sabertooth X79 Gigabyte GTX 480 16 GB Corsair DDR3 1866 Mhz Dominator 
Hard DriveOptical DriveCoolingOS
Intel SSD 320 120GB + WD Caviar Black 1TB + 500GB Sony Optiarc DVD-RW Corsair A70, Noiseblocker M12-P + AC Accelero X... Windows 7 Home Premium 64-bit 
MonitorKeyboardPowerCase
LG Flatron L204WT Logitech wireless Corsair AX750 Professional Modular 80 Plus Gold Cooler Master HAF 912 Plus 
Mouse
Logitech optical wireless 
  hide details  
Reply
post #2 of 41
Why would it.
Money
(13 items)
 
Z575
(9 items)
 
Oppo Find 5
(6 items)
 
CPUMotherboardGraphicsRAM
FX-8320 @ 4.7Ghz 1.5v Gigabyte 970A-UD3 XFX 7970 @ 1.1Ghz 8GB Team 1600 7-9-7-24 
Hard DriveHard DriveCoolingOS
Crucial M4 64GB Samsung F3 500GB Corsair H100 Windows 7 x86_64 
MonitorKeyboardPowerCase
NEC E222W HPE 87 w/ Browns + Ducky PBT caps Seasonic 850W Chenming Dragon 
Mouse
Deathadder 3.5G 
CPUMotherboardGraphicsRAM
AMD A6-3420M @ 2.2Ghz 1.1v Lenovo Torpedo A55 6720g2 6GB Elpida 1333 CL9 
Hard DriveOSMouseAudio
Samsung 840 250GB Ubuntu 12.04 x86_64 Abyssus 3.5G Plantronics Gamecom 777 
CPUGraphicsRAMHard Drive
1.5Ghz Snapdragon S4 Pro Quad Adreno 320 2GB 533Mhz LPDDR2 16GB flash 
OSMonitor
Jelly Bean 4.1.1 5" 1080p IPS 
  hide details  
Reply
Money
(13 items)
 
Z575
(9 items)
 
Oppo Find 5
(6 items)
 
CPUMotherboardGraphicsRAM
FX-8320 @ 4.7Ghz 1.5v Gigabyte 970A-UD3 XFX 7970 @ 1.1Ghz 8GB Team 1600 7-9-7-24 
Hard DriveHard DriveCoolingOS
Crucial M4 64GB Samsung F3 500GB Corsair H100 Windows 7 x86_64 
MonitorKeyboardPowerCase
NEC E222W HPE 87 w/ Browns + Ducky PBT caps Seasonic 850W Chenming Dragon 
Mouse
Deathadder 3.5G 
CPUMotherboardGraphicsRAM
AMD A6-3420M @ 2.2Ghz 1.1v Lenovo Torpedo A55 6720g2 6GB Elpida 1333 CL9 
Hard DriveOSMouseAudio
Samsung 840 250GB Ubuntu 12.04 x86_64 Abyssus 3.5G Plantronics Gamecom 777 
CPUGraphicsRAMHard Drive
1.5Ghz Snapdragon S4 Pro Quad Adreno 320 2GB 533Mhz LPDDR2 16GB flash 
OSMonitor
Jelly Bean 4.1.1 5" 1080p IPS 
  hide details  
Reply
post #3 of 41
Thread Starter 
Quote:
Originally Posted by S.M. View Post

Why would it.

Because AMD and Microsoft had said so, the author of the article briefly talks about it in the article, and you can always read the review of the FX-8150 with the Windows 7 patches. The better thread scheduler in Windows 8 was supposed to better understand Bulldozer's architecture and do what I said in the last paragraph of the OP, and gives us better all-round (at least we hoped) results.
Edited by tpi2007 - 10/31/12 at 4:32am
 
Metro 2033 review
Metro 2033
CPUMotherboardGraphicsRAM
Core i7-3820 Asus Sabertooth X79 Gigabyte GTX 480 16 GB Corsair DDR3 1866 Mhz Dominator 
Hard DriveOptical DriveCoolingOS
Intel SSD 320 120GB + WD Caviar Black 1TB + 500GB Sony Optiarc DVD-RW Corsair A70, Noiseblocker M12-P + AC Accelero X... Windows 7 Home Premium 64-bit 
MonitorKeyboardPowerCase
LG Flatron L204WT Logitech wireless Corsair AX750 Professional Modular 80 Plus Gold Cooler Master HAF 912 Plus 
Mouse
Logitech optical wireless 
  hide details  
Reply
 
Metro 2033 review
Metro 2033
CPUMotherboardGraphicsRAM
Core i7-3820 Asus Sabertooth X79 Gigabyte GTX 480 16 GB Corsair DDR3 1866 Mhz Dominator 
Hard DriveOptical DriveCoolingOS
Intel SSD 320 120GB + WD Caviar Black 1TB + 500GB Sony Optiarc DVD-RW Corsair A70, Noiseblocker M12-P + AC Accelero X... Windows 7 Home Premium 64-bit 
MonitorKeyboardPowerCase
LG Flatron L204WT Logitech wireless Corsair AX750 Professional Modular 80 Plus Gold Cooler Master HAF 912 Plus 
Mouse
Logitech optical wireless 
  hide details  
Reply
post #4 of 41
Figured this would be the case.
 
Another Quad Core
(13 items)
 
 
CPUMotherboardGraphicsRAM
Intel i5-760 @ 3.82 GHz ASUS P7P55D-E Gigabyte Radeon HD 7870 OC 8GB G.SKILL Ripjaws DDR3-1600 
Hard DriveOptical DriveCoolingOS
60GB Agility 3 + 1TB Caviar Black LG Blu-Ray Burner Cooler Master Hyper 212 Plus Win 7 Pro x64 w/SP1 + Ubuntu 12.04 
MonitorKeyboardPowerCase
LG IPS226 Logitech G110 Enermax Revolution 85+ 1250W Silverstone KL-03 (Silver) 
MouseOther
Logitech G400 Corsair HS1 Headset 
CPUMotherboardGraphicsRAM
C2Q Q8200 2.33GHZ 1.05vCore ASRock P45XE XFX Radeon 4670 1GB 4GB OCZ Platinum DDR2-1000 
Hard DriveOptical DriveOSMonitor
1TB Seagate Barracuda 16x LG DVD-RW Windows 7 x64, Ubuntu 10.10 x64 BenQ 18.5 wide LED 
KeyboardPowerCaseMouse
Gigabyte wireless BFG 450 watt Coolermaster Elite 330 Gigabyte wireless optical 
  hide details  
Reply
 
Another Quad Core
(13 items)
 
 
CPUMotherboardGraphicsRAM
Intel i5-760 @ 3.82 GHz ASUS P7P55D-E Gigabyte Radeon HD 7870 OC 8GB G.SKILL Ripjaws DDR3-1600 
Hard DriveOptical DriveCoolingOS
60GB Agility 3 + 1TB Caviar Black LG Blu-Ray Burner Cooler Master Hyper 212 Plus Win 7 Pro x64 w/SP1 + Ubuntu 12.04 
MonitorKeyboardPowerCase
LG IPS226 Logitech G110 Enermax Revolution 85+ 1250W Silverstone KL-03 (Silver) 
MouseOther
Logitech G400 Corsair HS1 Headset 
CPUMotherboardGraphicsRAM
C2Q Q8200 2.33GHZ 1.05vCore ASRock P45XE XFX Radeon 4670 1GB 4GB OCZ Platinum DDR2-1000 
Hard DriveOptical DriveOSMonitor
1TB Seagate Barracuda 16x LG DVD-RW Windows 7 x64, Ubuntu 10.10 x64 BenQ 18.5 wide LED 
KeyboardPowerCaseMouse
Gigabyte wireless BFG 450 watt Coolermaster Elite 330 Gigabyte wireless optical 
  hide details  
Reply
post #5 of 41
We all knew this would be the case. But doesn't Windows 8 make better use of hardware acceleration.. so that could kind of make up for it I suppose?
Main Rig.
(14 items)
 
Battlefield 2 review.
Battlefield 2 PC Game EA
 
CPUMotherboardGraphicsRAM
Bulldozer FX4100 Gigabyte GA-M68MT-S2 MSI 7770 Kingston Hyper X | 2 x 2 GB 
Hard DriveOptical DriveCoolingOS
WD 2 TB  LiteON DVD/CD R-W Drive AMD Standard cooler Windows 7 Ultimate 
MonitorKeyboardPowerCase
32' Luxor Full HD TV Microsoft comfort curce Antec 450 Watt OcUK Value case 
MouseAudio
Microsoft wireless mouse Logitech speakers & Bass 
  hide details  
Reply
Main Rig.
(14 items)
 
Battlefield 2 review.
Battlefield 2 PC Game EA
 
CPUMotherboardGraphicsRAM
Bulldozer FX4100 Gigabyte GA-M68MT-S2 MSI 7770 Kingston Hyper X | 2 x 2 GB 
Hard DriveOptical DriveCoolingOS
WD 2 TB  LiteON DVD/CD R-W Drive AMD Standard cooler Windows 7 Ultimate 
MonitorKeyboardPowerCase
32' Luxor Full HD TV Microsoft comfort curce Antec 450 Watt OcUK Value case 
MouseAudio
Microsoft wireless mouse Logitech speakers & Bass 
  hide details  
Reply
post #6 of 41
A different waiter is not going to make a person eat faster. He can only more efficiently serve the restaurant.
Money
(13 items)
 
Z575
(9 items)
 
Oppo Find 5
(6 items)
 
CPUMotherboardGraphicsRAM
FX-8320 @ 4.7Ghz 1.5v Gigabyte 970A-UD3 XFX 7970 @ 1.1Ghz 8GB Team 1600 7-9-7-24 
Hard DriveHard DriveCoolingOS
Crucial M4 64GB Samsung F3 500GB Corsair H100 Windows 7 x86_64 
MonitorKeyboardPowerCase
NEC E222W HPE 87 w/ Browns + Ducky PBT caps Seasonic 850W Chenming Dragon 
Mouse
Deathadder 3.5G 
CPUMotherboardGraphicsRAM
AMD A6-3420M @ 2.2Ghz 1.1v Lenovo Torpedo A55 6720g2 6GB Elpida 1333 CL9 
Hard DriveOSMouseAudio
Samsung 840 250GB Ubuntu 12.04 x86_64 Abyssus 3.5G Plantronics Gamecom 777 
CPUGraphicsRAMHard Drive
1.5Ghz Snapdragon S4 Pro Quad Adreno 320 2GB 533Mhz LPDDR2 16GB flash 
OSMonitor
Jelly Bean 4.1.1 5" 1080p IPS 
  hide details  
Reply
Money
(13 items)
 
Z575
(9 items)
 
Oppo Find 5
(6 items)
 
CPUMotherboardGraphicsRAM
FX-8320 @ 4.7Ghz 1.5v Gigabyte 970A-UD3 XFX 7970 @ 1.1Ghz 8GB Team 1600 7-9-7-24 
Hard DriveHard DriveCoolingOS
Crucial M4 64GB Samsung F3 500GB Corsair H100 Windows 7 x86_64 
MonitorKeyboardPowerCase
NEC E222W HPE 87 w/ Browns + Ducky PBT caps Seasonic 850W Chenming Dragon 
Mouse
Deathadder 3.5G 
CPUMotherboardGraphicsRAM
AMD A6-3420M @ 2.2Ghz 1.1v Lenovo Torpedo A55 6720g2 6GB Elpida 1333 CL9 
Hard DriveOSMouseAudio
Samsung 840 250GB Ubuntu 12.04 x86_64 Abyssus 3.5G Plantronics Gamecom 777 
CPUGraphicsRAMHard Drive
1.5Ghz Snapdragon S4 Pro Quad Adreno 320 2GB 533Mhz LPDDR2 16GB flash 
OSMonitor
Jelly Bean 4.1.1 5" 1080p IPS 
  hide details  
Reply
post #7 of 41
Dissapointing, yet not at all surprising. If AMD couldn't keep up with the promises and hype they made on Bulldozer, why would they be able to keep up with any other lie?
post #8 of 41
My question is why did they test with an old 8150? The test should have been done using an 8350. Or perhaps both if they really wanted to test a bulldozer. But the 8350 should certainly not have been ignored.
The results they achieved are interesting, but not entirely relevant considering they are not testing using the current architecture. There's a good chance that piledriver with its optimizations would respond differently to the same tests.
Death Star
(20 items)
 
Darksaber
(11 items)
 
 
CPUMotherboardGraphicsRAM
Athlon II x2 245 Asus M3A78 Radeon HD6570 1GB Mushkin Silverline 2GB DDR2  
Hard DriveOptical DriveOSMonitor
OCZ Vertex 2 120GB Samsung Blu-Ray Windows 7 Samsung 46" DLP 
PowerCaseOther
Silverstone Strider Essentials 400W Silverstone Milo ML03B Hauppage WinTV 1250 
  hide details  
Reply
Death Star
(20 items)
 
Darksaber
(11 items)
 
 
CPUMotherboardGraphicsRAM
Athlon II x2 245 Asus M3A78 Radeon HD6570 1GB Mushkin Silverline 2GB DDR2  
Hard DriveOptical DriveOSMonitor
OCZ Vertex 2 120GB Samsung Blu-Ray Windows 7 Samsung 46" DLP 
PowerCaseOther
Silverstone Strider Essentials 400W Silverstone Milo ML03B Hauppage WinTV 1250 
  hide details  
Reply
post #9 of 41
So much for it's the software's fault because it doesn't understand FX chips architecture.. rolleyes.gif
post #10 of 41
Quote:
Originally Posted by wedge View Post

My question is why did they test with an old 8150? The test should have been done using an 8350. Or perhaps both if they really wanted to test a bulldozer. But the 8350 should certainly not have been ignored.
The results they achieved are interesting, but not entirely relevant considering they are not testing using the current architecture. There's a good chance that piledriver with its optimizations would respond differently to the same tests.
Because when the FX-8150 came out, AMD pointed finger at Windows for not utilizing their obscure architecture efficiently enough. Statements where said about hotfixes improving performance, and that Windows 8 would run the Bulldozer better. The FX-8150 isn't FX-8350, and the FX-8350 wasn't the processor these statements were made for.
New Posts  All Forums:Forum Nav:
  Return Home
  Back to Forum: Software News
Overclock.net › Forums › Industry News › Software News › [TH] Windows 8: Does AMD's Bulldozer Architecture Benefit?