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 |
|||||
| |||||
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 |
|||||
| |||||
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 |
|||||
| |||||
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 |
|||||
| |||||
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 segment | Desktop | |
Manufacturer | EVGA | NVIDIA |
Model | GeForce GTX 480 SuperClocked+ | GeForce GTX 660 |
Part number | 015-P3-1485- | |
Based on | NVIDIA GeForce GTX 480 | N/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 clock | 726 MHz | |
Processor clock | 1451 MHz | |
Boost clock | ||
Memory size | 1536 MB | 2048 MB |
Memory type | GDDR5 | |
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:
- EVGA GeForce GTX 480 SuperClocked+ (015-P3-1485-AR, 015-P3-1485-ER, 015-P3-1485-KE, 015-P3-1485-KR, 015-P3-1485-R1, 015-P3-1485-RX)
- NVIDIA GeForce GTX 660
Compare graphics cards
More comparisons
Compare EVGA GeForce GTX 480 SuperClocked+:
Compare NVIDIA GeForce GTX 660: