AMD is laying the foundation for its Socket AM3+, Bulldozer-based Zambezi processors with the 990FX chipset, functionally identical to 890FX. The big news is that motherboard vendors are licensing SLI again, and we want to compare performance to Intel.
Hardware And Benchmark Setup
Swipe to scroll horizontally
Test Hardware
Processors
AMD Phenom II X4 980 Black Edition (Deneb) 3.7 GHz (18.5 * 200 MHz), Socket AM3, 4 GT/s HyperTransport, 6 MB Shared L3, Power-savings enabled, 125 W
Asus Sabertooth 990FX (Socket AM3+) 990FX/SB950, BIOS 0138
Row 3 - Cell 0
Asus P8Z68-V Pro (LGA 1155) Z68 Express PCH, BIOS 0401
Memory
Crucial 8 GB (2 x 4 GB) DDR3-1333, MT16JTF51264AZ-1G4D1 @ 9-9-9-24 and 1.65 V
Hard Drive
Intel SSDSC2MH250A2 250 GB SATA 6Gb/s
Graphics
Nvidia GeForce GTX 570 in SLICustom GeForce 270.77 Driver
Power Supply
Cooler Master UCP-1000 W
Swipe to scroll horizontally
Games
Lost Planet 2
Highest Quality Settings, No AA / No AF, 4x MSAA or 32x CSAA / 16x AF, vsync off, 1680x1050 / 1920x1080 / 2560x1600, DirectX 11, Steam version, Test A
Just Cause 2
Highest Quality Settings, No AA / 2x AF, 8x AA / 16x AF, vsync off, 1680x1050 / 1920x1080 / 2560x1600, Bokeh filter and GPU water disabled (for Nvidia cards), Concrete Jungle Benchmark
Metro 2033
High Quality Settings, AAA / 4x AF, 4x MSAA / 16x AF, 1680x1050 / 1920x1080 / 2560x1600, Built-in Benchmark, Depth of Field filter enabled, Steam version
F1 2010
Ultra High Settings, No AA / No AF, 8x AA / No AF, 1680x1050 / 1920x1080 / 2560x1600, Steam version, Custom benchmark script, DX11 Rendering
Aliens Vs. Predator Benchmark
High Quality Settings, SSAO, No AA / 16xAF, Ultra Quality Settings, 4x MSAA / No AF, vsync off, 1680x1050 / 1920x1080 / 2560x1600
Battlefield: Bad Company 2
Custom (Highest) Quality Settings, No AA / No AF, 8x MSAA / 16xAF, 1680x1050 / 1920x1080 / 2560x1600, opening cinematic, 145 second sequence, FRAPS
3DMark 11
Performance Default
World of Warcraft: Cataclysm
Ultra Quality Settings, No AA / 16x AF, 8x AA / 16x AF, From Crushblow to The Krazzworks, 1680x1050 / 1920x1080 / 2560x1600, FRAPS, DirectX 9 Rendering
Stay On the Cutting Edge: Get the Tom's Hardware Newsletter
Get Tom's Hardware's best news and in-depth reviews, straight to your inbox.
Tom's, what the hell is this? "At the end of the day, it's the graphics cards which are the bottleneck."
Did you go about benchmarking graphics cards, or was this a motherboard/cpu comparison? I'm tired of hearing this excuse all the time. We know you have a pair of 6990s and 590s in your shop. Get rid of that stupid bottleneck and DO IT RIGHT!
Thanks for the review, but at lower resolutions we all know that the CPU differences will become clear. So you just proved that if a game is taxing on the GPUs, both solutions are equal and when the graphics card ain't being taxed, CPU differences become apparent... Ok, thanks for proving what we already know once more (not being sarcastic here >_
Uhm... that last comment of mine was cut in half with the missing char of that face... I guess that's an escape char; oh well.
What is missing said something like:
...here "face"), but you said you wanted to test AMD's SLI on their 990FX vs Intel's SLI. So, IMO, you need less graphics horse power: like 2 GTS250's or 2 GTX460's or 2 GTX560's (not ti's) to tax the graphics subsystem and really show the differences. Maybe up the resolution also to really show if there is a difference between AMD's or Intel's SLI.