AMD Radeon 550 vs NVIDIA GeForce GT 720
Processeur graphique
| Nom du GPU | Lexa | GK208 |
|---|---|---|
| GPU variant | Lexa PRO (215-0904018) | GK208-320-A1 |
| Architecture | GCN 4.0 | Kepler 2.0 |
| Fonderie | GlobalFoundries | TSMC |
| Taille du processus | 14 nm | 28 nm |
| Transistors | 2,200 million | 1,020 million |
| Taille des matrices | 103 mm² | 87 mm² |
Carte graphique
| Date de publication | Apr 20th, 2017 | Mar 27th, 2014 |
|---|---|---|
| Génération | Polaris | GeForce 700 |
| Production | End-of-life | End-of-life |
| Prix de lancement | 79 USD | 49 USD |
| Bus interface | PCIe 3.0 x8 | PCIe 2.0 x8 |
| Prédécesseur | Arctic Islands | GeForce 600 |
| Successeur | Vega | GeForce 900 |
Vitesse clock
| Base clock | 1100 MHz | — |
|---|---|---|
| Boost clock | 1183 MHz | — |
| Mémoire clock | 1750 MHz 7 Gbps effective | 900 MHz 1800 Mbps effective |
| GPU clock | — | 967 MHz |
Mémoire
| Taille de la mémoire | 2 GB | 2 GB |
|---|---|---|
| Type de mémoire | GDDR5 | DDR3 |
| Bus mémoire | 64 bit | 64 bit |
| Bande passante | 56.00 GB/s | 14.40 GB/s |
Render Config
| Shading units | 512 | 384 |
|---|---|---|
| TMUs | 32 | 32 |
| ROPs | 16 | 8 |
| Compute units | 8 | — |
| Cache L1 | 16 KB (per CU) | 16 KB (per SMX) |
| Cache L2 | 256 KB | 512 KB |
| Comptage SMX | — | 2 |
Performance théorique
| Taux de pixel | 18.93 GPixel/s | 7.736 GPixel/s |
|---|---|---|
| Taux de texture | 37.86 GTexel/s | 30.94 GTexel/s |
| FP16 (half) performance | 1,211 GFLOPS (1:1) | — |
| FP32 (float) performance | 1,211 GFLOPS | 742.7 GFLOPS |
| FP64 (double) performance | 75.71 GFLOPS (1:16) | 30.94 GFLOPS (1:24) |
Board Design
| Taille Slot | Dual-slot | Single-slot |
|---|---|---|
| Longueur | 145 mm 5.7 inches | 145 mm 5.7 inches |
| TDP | 50 W | 19 W |
| Suggestions pour le PSU | 250 W | 200 W |
| Sorties | 1x DVI1x HDMI1x DisplayPort | 1x DVI1x HDMI1x VGA |
| Connecteurs de puissance | None | None |
| Board number | D090-01 | P2130 SKU 4 |
Caractéristiques graphiques
| DirectX | 12 (12_0) | 12 (11_0) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.1 |
| Shader model | 6.4 | 5.1 |
| CUDA | — | 3.5 |
