AMD Radeon HD 6870 1600SP Edition vs NVIDIA GeForce GTX 460 OEM
Grafikprozessor
| GPU Name | Cypress | GF104 |
|---|---|---|
| GPU Variante | Cypress XT (215-0735033) | GF104-325-A1 |
| Architektur | TeraScale 2 | Fermi |
| Hersteller | TSMC | TSMC |
| Prozessgröße | 40 nm | 40 nm |
| Transistoren | 2,154 million | 1,950 million |
| Chipgröße | 334 mm² | 332 mm² |
Grafikkarte
| Veröffentlichungsdatum | Jan 14th, 2013 | Oct 11th, 2010 |
|---|---|---|
| Generation | Northern Islands | GeForce 400 |
| Produktion | End-of-life | End-of-life |
| Businterface | PCIe 2.0 x16 | PCIe 2.0 x16 |
| Reviews | 170 in our database | 154 in our database |
| Vorgänger | Evergreen | GeForce 200 |
| Nachfolger | Southern Islands | GeForce 500 |
Takt-Geschwindigkeiten
| GPU-Taktung | 850 MHz | 650 MHz |
|---|---|---|
| Speicher-Taktung | 1050 MHz 4.2 Gbps effective | 850 MHz 3.4 Gbps effective |
| Shader-Taktung | — | 1300 MHz |
Speicher
| Speichergröße | 1024 MB | 1024 MB |
|---|---|---|
| Speichertyp | GDDR5 | GDDR5 |
| Speicherbus | 256 bit | 256 bit |
| Bandbreite | 134.4 GB/s | 108.8 GB/s |
Render-Konfiguration
| Shading-Einheiten | 1600 | 336 |
|---|---|---|
| TMUs | 80 | 56 |
| ROPs | 32 | 32 |
| Compute Units | 20 | — |
| Cache L1 | 8 KB (per CU) | 64 KB (per SM) |
| Cache L2 | 512 KB | 512 KB |
| Anzahl SM | — | 7 |
Theoretische Leistung
| Pixelrate | 27.20 GPixel/s | 9.100 GPixel/s |
|---|---|---|
| Texturrate | 68.00 GTexel/s | 36.40 GTexel/s |
| FP32 (float) Leistung | 2.720 TFLOPS | 873.6 GFLOPS |
| FP64 (double) Leistung | 544.0 GFLOPS (1:5) | 72.80 GFLOPS (1:12) |
Boarddesign
| Steckplatzbreite | Dual-slot | Dual-slot |
|---|---|---|
| Länge | 282 mm 11.1 inches | 210 mm 8.3 inches |
| TDP | 175 W | 150 W |
| Vorgeschlagenes Netzteil | 450 W | 450 W |
| Ausgabe | 2x DVI1x HDMI2x mini-DisplayPort | 2x DVI1x mini-HDMI |
| Stromverbindung | 2x 6-pin | 2x 6-pin |
| Board-Nummer | C008, E140 | P1041 |
Grafik-Features
| DirectX | 11.2 (11_0) | 12 (11_0) |
|---|---|---|
| OpenGL | 4.4 | 4.6 |
| OpenCL | 1.2 | 1.1 |
| Vulkan | — | — |
| Shader-Modell | 5.0 | 5.1 |
| CUDA | — | 2.1 |
