Graphics Chip Comparison And Test Configuration
To make it easier to compare the performance of the different graphic chips and generations, we provide additional results for Nvidia’s GeForce 8, 9800 GTX, and GTX 260, and AMD’s Radeon 38x0 and 48x0. The GeForce 9600 GT and Radeon 4870 are tested with two different driver versions to make it easier to see the differences upon updating from ForceWare 175.16 to GeForce 177.92, or from Catalyst 8.6 to 8.8.
The Asus EN9600GT Silent with 512 MB runs at the Nvidia standard clock speeds, just like the reference 9600 GT with 1 GB. MSI slightly increases graphics processor (GPU) and shader speeds, while Palit and Sparkle increase GPU, shader, and graphics memory speeds.
| Card Manufacturer and Chip | Code name | Memory | GPU Speed | Shader | Memory Speed | SPs |
|---|---|---|---|---|---|---|
| GeForce GTX 260 | GT200 | 896 GDDR3 | 576 MHz | 4.0, 1242 MHz | 1998 MHz | 192 |
| GeForce 9800 GTX | G92 | 512 MB GDDR3 | 675 MHz | 4.0, 1688 MHz | 2200 MHz | 128 |
| GeForce 9600 GT SLI | G94 | 1024 MB GDDR3 | 650 MHz | 4.0, 1625 MHz | 1800 MHz | 64 |
| GeForce 9600 GT | G94 | 1024 MB GDDR3 | 650 MHz | 4.0, 1625 MHz | 1800 MHz | 64 |
| Asus GeForce 9600 GT | G94 | 512 MB GDDR3 | 650 MHz | 4.0, 1625 MHz | 1800 MHz | 64 |
| MSI GeForce 9600 GT | G94 | 1024 MB GDDR3 | 700 MHz | 4.0, 1680 MHz | 1800 MHz | 64 |
| Palit GeForce 9600 GT | G94 | 1024 MB GDDR3 | 700 MHz | 4.0, 1750 MHz | 2000 MHz | 64 |
| Sparkle GeForce 9600 GT | G94 | 512 MB GDDR3 | 700 MHz | 4.0, 1850 MHz | 2000 MHz | 64 |
| GeForce 8800 GTS | G92 | 512 MB GDDR3 | 650 MHz | 4.0, 1625 MHz | 1944 MHz | 128 |
| GeForce 8800 GT | G92 | 512 MB GDDR3 | 600 MHz | 4.0, 1500 MHz | 1800 MHz | 112 |
| GeForce 8800 GTX | G80 | 768 MB GDDR3 | 576 MHz | 4.0, 1350 MHz | 1800 MHz | 128 |
| GeForce 8800 GTS | G80 | 640 MB GDDR3 | 500 MHz | 4.0, 1188 MHz | 1600 MHz | 96 |
| GeForce 8800 GTS | G80 | 320 MB GDDR3 | 500 MHz | 4.0, 1188 MHz | 1600 MHz | 96 |
| Card Manufacturer and Chip | Memory Bus | Manufacturing Process | Transistors | Interface |
|---|---|---|---|---|
| GeForce GTX 260 | 448 Bit | 65 nm | 1400 MB | PCIe 2.0 |
| GeForce 9800 GTX | 256 Bit | 65 nm | 754 MB | PCIe 2.0 |
| GeForce 9600 GT SLI | 256 Bit | 65 nm | 505 MB | PCIe 2.0 |
| GeForce 9600 GT | 256 Bit | 65 nm | 505 MB | PCIe 2.0 |
| Asus GeForce 9600 GT | 256 Bit | 65 nm | 505 MB | PCIe 2.0 |
| MSI GeForce 9600 GT | 256 Bit | 65 nm | 505 MB | PCIe 2.0 |
| Palit GeForce 9600 GT | 256 Bit | 65 nm | 505 MB | PCIe 2.0 |
| Sparkle GeForce 9600 GT | 256 Bit | 65 nm | 505 MB | PCIe 2.0 |
| GeForce 8800 GTS | 256 Bit | 65 nm | 754 MB | PCIe 2.0 |
| GeForce 8800 GT | 256 Bit | 65 nm | 754 MB | PCIe 2.0 |
| GeForce 8800 GTX | 384 Bit | 90 nm | 681 MB | PCIe 1 |
| GeForce 8800 GTS | 320 Bit | 90 nm | 681 MB | PCIe 1 |
| GeForce 8800 GTS | 320 Bit | 90 nm | 681 MB | PCIe 1 |
| Card Manufacturer and Chip | Code name | Memory | GPU Speed | Shader | Memory Speed | SPs |
|---|---|---|---|---|---|---|
| Radeon HD 4870 | RV770 | 512 MB GDDR5 | 750 MHz | 4.1 | 3600 MHz | 800 |
| Radeon HD 4850 CF | RV770 | 512 MB GDDR3 | 625 MHz | 4.1 | 1986 MHz | 800 |
| Radeon HD 4850 | RV770 | 512 MB GDDR3 | 625 MHz | 4.1 | 1986 MHz | 800 |
| Radeon HD 3870 | RV670 | 512 MB GDDR4 | 775 MHz | 4.1 | 2252 MHz | 320 |
| Radeon HD 3850 | RV670 | 256 MB GDDR3 | 670 MHz | 4.1 | 1658 MHz | 320 |
| Card Manufacturer and Chip | Memory Bus | Manufacturing Process | Transistors | Interface |
| Radeon HD 4870 | 256 Bit | 55 nm | 965 MB | PCIe 2.0 |
| Radeon HD 4850 CF | 256 Bit | 55 nm | 965 MB | PCIe 2.0 |
| Radeon HD 4850 | 256 Bit | 55 nm | 965 MB | PCIe 2.0 |
| Radeon HD 3870 | 256 Bit | 55 nm | 666 MB | PCIe 2.0 |
| Radeon HD 3850 | 256 Bit | 55 nm | 666 MB | PCIe 2.0 |
Memory clock speed=DDR clock speed doubled; physical clock speed is one half
DDR5 clock speed quadrupled; physical clock speed is one quarter
SPs=Stream-Processors, P and V=Pixel shader and Vertex shader
TC=Turbo Cache
HM=Hyper Memory
OC=overclocked (clock speed higher than standard)
SLI=Parallel mode with 2 Nvidia Cards
3SLI=Parallel mode with 3 Nvidia graphics chips
4SLI=Parallel mode with 4 Nvidia graphics chips
CF=CrossFire Parallel mode with 2 AMD cards
3CF=CrossFire Parallel mode with 3 AMD graphics chips
4CF=CrossFire Parallel mode with 4 AMD graphics chips
R680=2xRV670
Shader 2.0=DirectX 9.0; 3.0=DirectX 9.0c; 4.0=DirectX 10; Shader 4.1=DirectX 10.1
| CPU | Intel Core 2 Extreme X6800 @ 2.93 GHz (11x266 MHz), Socket 775, 1.28 V, 65 nm, 4 MB L2 Cache |
| FSB | 1066 MHz (4x266 MHz) |
| Motherboard | Asus P5E3 Deluxe, PCIe 2.0 2x16, ICH9R |
| Chip set | Intel X38 |
| Memory | 2x 1 GB Ballistix (Crucial Technology) 1.5 V DDR3 1066 7-7-7-20 (2x533 MHz) |
| Audio | Intel High Definition Audio |
| LAN | Intel 1000 Pro |
| Hard Drives | Western Digital WD5000AAKS 500 GB, S-ATA, 16 MB Cache Hitachi 120 GB, S-ATA, 8 MB Cache |
| DVD | Gigabyte GO-D1600C |
| Power Supply | CoolerMaster RS-850-EMBA 850 W |
| Motherboard | Asus P5N-T Deluxe, PCIe 2.0 2x16 |
| Chip set | Nvidia nForce 780i SLI |
| Memory | 2x1 GB, A-Data Technology 1.8 Volt, DDR2 800 5-5-5-18 (2x400 MHz) |
| Audio | ADI 1988B SoundMax |
| LAN | Marvell 88E1116 Gigabit Ethernet |
| Graphic | AMD Catalyst 8.6 and 8.8 Nvidia ForceWare 175.16, GTX 260 ForceWare 177.39, 9600 GT ForceWare 175.16 and GeForce 177.92 |
| Operating System | Windows Vista Enterprise SP1 |
| DirectX | 10 und 10.1 |
| Chip Set Driver | X38 Intel 8.3.1.1009 780i Nvidia nForce 9.64 |
Latest Graphics Cards News
- 20/05 – Qualcomm Hires Former AMD CTO Demers
- 18/05 – Nvidia Responds to GeForce 600 Series V-Sync Stuttering Issue
- 18/05 – Behold: Here Are The First Unreal Engine 4 Screens
- 17/05 – Nvidia Debuts GK110-based 7.1 Billion Transistor Super GPU
- 17/05 – GE Announces Kepler Graphics Card for Military and Aviation
Latest Graphics Cards reviews
- 18/05 – Best Gaming CPUs For The Money: May 2012
- 10/05 – Best Graphics Cards For The Money: May 2012
- 10/05 – GeForce GTX 670 2 GB Review: Is It Already Time To Forget GTX...
- 09/05 – Video Teaser: Radeon HD 7800 Series Remains A Solid Value
- 08/05 – Benchmarking AMD's 768-Shader Pitcairn: Not For Public...
"Under permanent load we measured temperatures of up to 103 °C"
Not what you would call fit for purpose as a GPU, unless is also marked as a space heater!.
Why don't we have any ATI 4670 ? reviews or comparisons or benchmarks ? Who is interested in the Green cards anymore ? Especially when the conclusion is, buy another model green card. Seriously is this site sponsered by Nvidia ?
where's the GTX280 and the 9800GX2???
Blimey, I'm surprised my 8800GT compares so well with that list (SM2.0
of 5457, SM3.0 of 5704, overall score 11762 (CPU limits the overall
scores as it's only an AMD 6000+). toms must be using a pretty naffy
8800GT to only get an SM3.0 of 4984 (oh yeah, just stock clocks -
who the heck buys that these days?), especially given the X6800 being
used is 25% faster than mine. Speaking of which, if one is going to
bother testing with games like Crysis, why only use a dual-core? Surely
it makes sense to use a good quad-core so that one can be sure higher
resolution tests are not limited by CPU issues?
Overall, just more proof that the naming scheme for the 9xxx series was
crazy. Why does NVIDIA keep releasing so many different overlapping
variants with names that make no sense? The number of different names
is laughable.
Re other cards like the GTX280: maybe they haven't included more since
one can always infer other comparisons based on the various VGA charts.
The only thing I wish they'd stop doing is using MS FSX which is really
badly written (suffers terrible slowdown without the full PCIe speed
as it reloads textures constantly).
Also, has anyone ever done an analysis of exactly what Crysis is doing?
Sites are so fond of using it as if it's the ultimate benchmark because
it hammers gfx cards so hard, but how do we know it's not just
inefficiently written instead? No way to tell. How many polys per frame
typically? Not seen this mentioned anywhere. I did send this question to
NVIDIA but nobody replied. I think I would have more respect for Crysis
performance results if I could be sure it was getting more out of the
cards compared to other games, but I have to say the movie demos I've
seen don't look that good compared to, say, Stalker Clear Sky which
is said to have over a million polys/frame (a rather rough measure to
be sure, but better than nothing).
Ian.
I was sold on this unit until I read that. I really don't understand why some RAM sinks couldn't be used. As a consumer I really don't want to be looking at the temps all the time wondering if the chips are going to overheat.