ATI Radeon 9250 PCI vs NVIDIA GeForce GT 640
Processeur graphique
| Nom du GPU | RV280 | GK107 |
|---|---|---|
| Architecture | Rage 7 | Kepler |
| Fonderie | UMC | TSMC |
| Taille du processus | 150 nm | 28 nm |
| Transistors | 36 million | 1,270 million |
| Taille des matrices | 98 mm² | 118 mm² |
| GPU variant | — | GK107-300-A2 |
Carte graphique
| Date de publication | Mar 1st, 2004 | Jun 5th, 2012 |
|---|---|---|
| Génération | Radeon R200 | GeForce 600 |
| Production | End-of-life | End-of-life |
| Bus interface | PCI | PCIe 3.0 x16 |
| Critiques | 7 in our database | — |
| Prédécesseur | Radeon R100 | GeForce 500 |
| Successeur | Radeon R300 | GeForce 700 |
| Prix de lancement | — | 99 USD |
Vitesse clock
| GPU clock | 240 MHz | 902 MHz |
|---|---|---|
| Mémoire clock | 200 MHz 400 Mbps effective | 891 MHz 1782 Mbps effective |
Mémoire
| Taille de la mémoire | 128 MB | 2 GB |
|---|---|---|
| Type de mémoire | DDR | DDR3 |
| Bus mémoire | 64 bit | 128 bit |
| Bande passante | 3.200 GB/s | 28.51 GB/s |
Render Config
| Pixel shaders | 4 | — |
|---|---|---|
| Vertex shaders | 1 | — |
| TMUs | 4 | 32 |
| ROPs | 4 | 16 |
| Shading units | — | 384 |
| Comptage SMX | — | 2 |
| Cache L1 | — | 16 KB (per SMX) |
| Cache L2 | — | 256 KB |
Performance théorique
| Taux de pixel | 960.0 MPixel/s | 7.216 GPixel/s |
|---|---|---|
| Vertex rate | 60.00 MVertices/s | — |
| Taux de texture | 960.0 MTexel/s | 28.86 GTexel/s |
| FP32 (float) performance | — | 692.7 GFLOPS |
| FP64 (double) performance | — | 28.86 GFLOPS (1:24) |
Board Design
| Taille Slot | Single-slot | Single-slot |
|---|---|---|
| TDP | unknown | 65 W |
| Suggestions pour le PSU | 200 W | 250 W |
| Sorties | 1x DVI1x VGA1x S-Video | 1x DVI1x HDMI1x DisplayPort |
| Connecteurs de puissance | None | None |
| Longueur | — | 145 mm 5.7 inches |
| Board number | — | P2011 |
Caractéristiques graphiques
| DirectX | 8.1 | 12 (11_0) |
|---|---|---|
| OpenGL | 1.4 | 4.6 |
| OpenCL | — | 3.0 |
| Vulkan | — | 1.1 |
| Pixel shader | 1.4 | — |
| Vertex shader | 1.1 | — |
| CUDA | — | 3.0 |
| Shader model | — | 5.1 |
