ATI Radeon HD 2900 PRO vs NVIDIA GeForce GT 720
Processeur graphique
| Nom du GPU | R600 | GK208 |
|---|---|---|
| GPU variant | R600 PRO (215RGMDKA13FG) | GK208-320-A1 |
| Architecture | TeraScale | Kepler 2.0 |
| Fonderie | TSMC | TSMC |
| Taille du processus | 80 nm | 28 nm |
| Transistors | 720 million | 1,020 million |
| Taille des matrices | 420 mm² | 87 mm² |
Carte graphique
| Date de publication | Dec 12th, 2007 | Mar 27th, 2014 |
|---|---|---|
| Génération | Radeon R600 | GeForce 700 |
| Production | End-of-life | End-of-life |
| Bus interface | PCIe 1.0 x16 | PCIe 2.0 x8 |
| Critiques | 63 in our database | — |
| Prédécesseur | Radeon R500 PCIe | GeForce 600 |
| Successeur | Radeon R700 | GeForce 900 |
| Prix de lancement | — | 49 USD |
Vitesse clock
| GPU clock | 600 MHz | 967 MHz |
|---|---|---|
| Mémoire clock | 800 MHz 1600 Mbps effective | 900 MHz 1800 Mbps effective |
Mémoire
| Taille de la mémoire | 512 MB | 2 GB |
|---|---|---|
| Type de mémoire | GDDR3 | DDR3 |
| Bus mémoire | 256 bit | 64 bit |
| Bande passante | 51.20 GB/s | 14.40 GB/s |
Render Config
| Shading units | 320 | 384 |
|---|---|---|
| TMUs | 16 | 32 |
| ROPs | 16 | 8 |
| Compute units | 4 | — |
| Cache L2 | 128 KB | 512 KB |
| Comptage SMX | — | 2 |
| Cache L1 | — | 16 KB (per SMX) |
Performance théorique
| Taux de pixel | 9.600 GPixel/s | 7.736 GPixel/s |
|---|---|---|
| Taux de texture | 9.600 GTexel/s | 30.94 GTexel/s |
| FP32 (float) performance | 384.0 GFLOPS | 742.7 GFLOPS |
| FP64 (double) performance | — | 30.94 GFLOPS (1:24) |
Board Design
| Taille Slot | Dual-slot | Single-slot |
|---|---|---|
| Longueur | 241 mm 9.5 inches | 145 mm 5.7 inches |
| TDP | 200 W | 19 W |
| Suggestions pour le PSU | 550 W | 200 W |
| Sorties | 2x DVI1x S-Video | 1x DVI1x HDMI1x VGA |
| Connecteurs de puissance | 1x 8-pin | None |
| Board number | — | P2130 SKU 4 |
Caractéristiques graphiques
| DirectX | 10.0 (10_0) | 12 (11_0) |
|---|---|---|
| OpenGL | 3.3 (full) 4.0 (partial) | 4.6 |
| OpenCL | — | 3.0 |
| Vulkan | — | 1.1 |
| Shader model | 4.0 | 5.1 |
| CUDA | — | 3.5 |
