EVGA GeForce GTX 480 SuperClocked+ vs NVIDIA GeForce GTX 660

Theoretical performance comparison

Real-world game, 3D graphics and compute performance is dependent on several GPU parameters, including texture fillrate, pixel fillrate, memory bandwidth, single- and double-precision performance. Below you will find why they are important, and which card has better characteristics.

Pixel fill rate (gigapixels/s)

40
32
24
16
8
0
 
 
34.9
 
20.7
 
 
Higher is better
Although it has slower graphics clock, the GeForce GTX 480 SuperClocked+ comes with considerably higher pixel fill rate, owing to many more ROPs (Raster Operations Pipelines). Better maximum pixel fill rate allows more pixels to be drawn on screen per second, and is an indication of better GPU performance, unless there are bottlenecks somewhere else.
  - EVGA GeForce GTX 480 SuperClocked+
  - NVIDIA GeForce GTX 660

Texture fill rate (gigatexels/s)

100
80
60
40
20
0
 
 
43.6
 
82.6
 
 
Higher is better
The GeForce GTX 660 has more TMUs (Texture Mapping Units) than the GeForce GTX 480 SuperClocked+. Furthermore, its graphics frequency is higher, consequently it has much higher texture fillrate. Better texture fill rate allows the graphics card to use more sophisticated 3D effects and/or map more textures to each texel, which improves games visual appearance.

Single Precision performance (GFLOPS)

3000
2400
1800
1200
600
0
 
 
1393
 
1983
 
 
Higher is better
Maximum Single Precision performance, measured in GFLOPS or billions of Floating Point Operations Per Second, indicates how good the graphics card is at running applications, that make an extensive use of single-precision floating point numbers. As a rule, the more stream processors or CUDA cores the graphics card has, and the the faster they run at, the higher Single Precision performance will be. The NVIDIA GeForce GTX 660 has an edge here. Higher single-precision performance number means the graphics card will perform better in general computing applications. Since stream processors or CUDA cores are also used as vertex and geometry shaders for 3D image generation, higher performance is also beneficial to games.

Memory bandwidth (GB/s)

300
240
180
120
60
0
 
 
182
 
144
 
 
Higher is better
Memory bandwidth parameter specifies how much memory (in Gigabytes) the graphics card can read from or write to dedicated memory per second. GPUs with higher memory bandwidth have better performance at high display resolutions, or when using large and detailed textures, and/or utilizing complex 3D effects and filters, like anti-aliasing. The bandwidth depends on memory type, speed, and memory interface width. In this case, the EVGA GeForce GTX 480 SuperClocked+ graphics card offers wider memory bus. As such, it has higher memory bandwidth.
  - EVGA GeForce GTX 480 SuperClocked+
  - NVIDIA GeForce GTX 660

Specs comparison

All rows with different specifications or features are highlighted.

General information

Market segmentDesktop
ManufacturerEVGANVIDIA
ModelGeForce GTX 480 SuperClocked+GeForce GTX 660
Part number015-P3-1485-AR, 015-P3-1485-ER, 015-P3-1485-KE, 015-P3-1485-KR, 015-P3-1485-R1, 015-P3-1485-RX 
Based onNVIDIA GeForce GTX 480N/A

Architecture / Interface

Die name  
Architecture  
Fabrication process  
Bus interface  

Cores / shaders

CUDA cores  
ROPs  
Pixel fill rate  
Texture units  
Texture fill rate  
Single Precision performance  

Clocks / Memory

Base clock 980 MHz
Graphics clock726 MHz 
Processor clock1451 MHz 
Boost clock  
Memory size1536 MB2048 MB
Memory typeGDDR5
Memory clock  
Memory interface width  
Memory bandwidth  

Other features

Maximum SLI options 
Maximum power  

Better values / features are marked with green color, and worse values are in red color.


Detailed specifications:

Compare graphics cards

Type in full or partial GPU manufacturer, model name and/or part number.

More comparisons