Compare any two graphics cards:
Radeon HD 4870 512MB vs Radeon HD 4890 1GB
Intro
The Radeon HD 4870 512MB has a core clock frequency of 750 MHz and a GDDR5 memory speed of 900 MHz. It also uses a 256-bit memory bus, and uses a 55 nm design. It is made up of 800(160x5) SPUs, 40 Texture Address Units, and 16 Raster Operation Units.
Compare all of that to the Radeon HD 4890 1GB, which features a clock frequency of 1000 MHz and a GDDR5 memory frequency of 975 MHz. It also features a 256-bit memory bus, and uses a 55 nm design. It features 800(160x5) SPUs, 40 TAUs, and 16 Raster Operation Units.
Power Usage and Theoretical Benchmarks
Power Consumption (Max TDP)
| Radeon HD 4870 512MB |
|
150 Watts |
| Radeon HD 4890 1GB |
|
190 Watts |
| |
Difference: 40 Watts (27%)
|
|
Memory Bandwidth
Performance-wise, the Radeon HD 4890 1GB should theoretically be a bit superior to the Radeon HD 4870 512MB in general. (explain)
| Radeon HD 4890 1GB |
|
124800 MB/sec |
| Radeon HD 4870 512MB |
|
115200 MB/sec |
| |
Difference: 9600 (8%)
|
|
Texel Rate
The Radeon HD 4890 1GB should be quite a bit (more or less 33%) more effective at texture filtering than the Radeon HD 4870 512MB. (
explain)
| Radeon HD 4890 1GB |
|
40000 Mtexels/sec |
| Radeon HD 4870 512MB |
|
30000 Mtexels/sec |
| |
Difference: 10000 (33%)
|
|
Pixel Rate
The Radeon HD 4890 1GB should be a lot (approximately 33%) better at FSAA than the Radeon HD 4870 512MB, and should be capable of handling higher resolutions more effectively. (
explain)
| Radeon HD 4890 1GB |
|
16000 Mpixels/sec |
| Radeon HD 4870 512MB |
|
12000 Mpixels/sec |
| |
Difference: 4000 (33%)
|
|
Please note that the above 'benchmarks' are all just theoretical - the results were calculated based on the card's specifications, and real-world performance may (and probably will) vary at least a bit.
Price Comparison
Please note that the price comparisons are based on search keywords, and might not be the exact same card listed on this page. We have no control over the accuracy of their search results.
Radeon HD 4870 512MB
Amazon.com
Other US-based stores
Amazon.co.uk
Amazon.de
Amazon.fr
|
Radeon HD 4890 1GB
Amazon.com
Other US-based stores
Amazon.co.uk
Amazon.de
Amazon.fr
|
Specifications
| Model
| Radeon HD 4870 512MB |
Radeon HD 4890 1GB |
| Manufacturer
| ATi |
ATi |
| Year
| Jun 25, 2008 |
Apr 2, 2009 |
| Code Name
| RV770 XT |
RV790 XT |
| Fab Process
| 55 nm |
55 nm |
| Bus
| PCIe 2.0 x16 |
PCIe 2.0 x16 |
| Memory
| 512 MB |
1024 MB |
| Core Speed
| 750 MHz |
1000 MHz |
| Shader Speed
| N/A MHz |
(N/A) MHz |
| Memory Speed
| 900 MHz |
975 MHz |
| Unified Shaders
| 800(160x5) |
800(160x5) |
| Texture Mapping Units
| 40 |
40 |
| Render Output Units
| 16 |
16 |
| Bus Type
| GDDR5 |
GDDR5 |
| Bus Width
| 256-bit |
256-bit |
| DirectX Version
| DirectX 10.1 |
DirectX 10.1 |
| OpenGL Version
| OpenGL 3.0 |
OpenGL 3.0 |
| Power (Max TDP)
| 150 watts |
190 watts |
| Shader Model
| 4.1 |
4.1 |
| Bandwidth
| 115200 MB/sec |
124800 MB/sec |
| Texel Rate
| 30000 Mtexels/sec |
40000 Mtexels/sec |
| Pixel Rate
| 12000 Mpixels/sec |
16000 Mpixels/sec |
Memory Bandwidth: Bandwidth is the max amount of information (in units of MB per second) that can be transported over the external memory interface in one second. It is calculated by multiplying the card's bus width by the speed of its memory. In the case of DDR memory, it should be multiplied by 2 once again. If DDR5, multiply by 4 instead.
The higher the card's memory bandwidth, the faster the card will be in general. It especially helps with anti-aliasing, HDR and higher screen resolutions.
Texel Rate: Texel rate is the maximum texture map elements (texels) that are processed per second. This number is worked out by multiplying the total amount of texture units by the core clock speed of the chip. The higher the texel rate, the better the card will be at texture filtering (anisotropic filtering - AF). It is measured in millions of texels processed in one second.
Pixel Rate: Pixel rate is the maximum amount of pixels that the graphics card could possibly record to the local memory in a second - measured in millions of pixels per second. The figure is calculated by multiplying the number of ROPs by the clock speed of the card. ROPs (Raster Operations Pipelines - aka Render Output Units) are responsible for outputting the pixels (image) to the screen.
The actual pixel rate also depends on lots of other factors, most notably the memory bandwidth of the card - the lower the memory bandwidth is, the lower the ability to reach the max fill rate.
Comments
Be the first to leave a comment!