AMD Radeon HD 6450 vs NVIDIA GeForce 9800 GT
Processeur graphique
| Nom du GPU | Caicos | G92 |
|---|---|---|
| GPU variant | Caicos PRO | G92-270-A2 |
| Architecture | TeraScale 2 | Tesla |
| Fonderie | TSMC | TSMC |
| Taille du processus | 40 nm | 65 nm |
| Transistors | 370 million | 754 million |
| Taille des matrices | 67 mm² | 324 mm² |
Carte graphique
| Date de publication | Apr 7th, 2011 | Jul 21st, 2008 |
|---|---|---|
| Génération | Northern Islands | GeForce 9 |
| Production | End-of-life | End-of-life |
| Prix de lancement | 55 USD | 160 USD |
| Bus interface | PCIe 2.0 x16 | PCIe 2.0 x16 |
| Critiques | 14 in our database | 46 in our database |
| Prédécesseur | Evergreen | GeForce 8 |
| Successeur | Southern Islands | GeForce 200 |
Vitesse clock
| GPU clock | 625 MHz | 600 MHz |
|---|---|---|
| Mémoire clock | 800 MHz 3.2 Gbps effective | 900 MHz 1800 Mbps effective |
| Shader clock | — | 1500 MHz |
Mémoire
| Taille de la mémoire | 512 MB | 512 MB |
|---|---|---|
| Type de mémoire | GDDR5 | GDDR3 |
| Bus mémoire | 64 bit | 256 bit |
| Bande passante | 25.60 GB/s | 57.60 GB/s |
Render Config
| Shading units | 160 | 112 |
|---|---|---|
| TMUs | 8 | 56 |
| ROPs | 4 | 16 |
| Compute units | 2 | — |
| Cache L1 | 8 KB (per CU) | — |
| Cache L2 | 128 KB | 64 KB |
| Comptage SM | — | 14 |
Performance théorique
| Taux de pixel | 2.500 GPixel/s | 9.600 GPixel/s |
|---|---|---|
| Taux de texture | 5.000 GTexel/s | 33.60 GTexel/s |
| FP32 (float) performance | 200.0 GFLOPS | 336.0 GFLOPS |
Board Design
| Taille Slot | Single-slot | Single-slot |
|---|---|---|
| Longueur | 168 mm 6.6 inches | 229 mm 9 inches |
| TDP | 18 W | 125 W |
| Suggestions pour le PSU | 200 W | 300 W |
| Sorties | 1x DVI1x HDMI1x VGA | 2x DVI1x S-Video |
| Connecteurs de puissance | None | 1x 6-pin |
| Board number | C264 | P360, P393 |
| Taille | — | 111 mm 4.4 inches |
Caractéristiques graphiques
| DirectX | 11.2 (11_0) | 11.1 (10_0) |
|---|---|---|
| OpenGL | 4.4 | 3.3 |
| OpenCL | 1.2 | 1.1 |
| Vulkan | — | — |
| Shader model | 5.0 | 4.0 |
| CUDA | — | 1.1 |
