NVIDIA Quadro Plex 1000 Model IV vs NVIDIA Quadro4 500 XGL
Processeur graphique
| Nom du GPU | G80 | NV17 |
|---|---|---|
| Architecture | Tesla | Celsius |
| Fonderie | TSMC | TSMC |
| Taille du processus | 90 nm | 150 nm |
| Transistors | 681 million | 29 million |
| Taille des matrices | 484 mm² | 65 mm² |
| GPU variant | — | NV17 GL |
Carte graphique
| Date de publication | Jul 25th, 2008 | Feb 19th, 2002 |
|---|---|---|
| Génération | Quadro Plex | Quadro4 XGL |
| Production | End-of-life | End-of-life |
| Bus interface | PCIe 1.0 x16 | AGP 4x |
| Critiques | 26 in our database | 26 in our database |
Vitesse clock
| GPU clock | 600 MHz | 250 MHz |
|---|---|---|
| Shader clock | 1350 MHz | — |
| Mémoire clock | 800 MHz 1600 Mbps effective | 166 MHz |
Mémoire
| Taille de la mémoire | 1536 MB | 128 MB |
|---|---|---|
| Type de mémoire | GDDR3 | SDR |
| Bus mémoire | 384 bit | 128 bit |
| Bande passante | 76.80 GB/s | 2.656 GB/s |
Render Config
| Shading units | 128 | — |
|---|---|---|
| TMUs | 32 | 4 |
| ROPs | 24 | 4 |
| Comptage SM | 16 | — |
| Cache L2 | 96 KB | — |
| Pixel shaders | — | 2 |
| Vertex shaders | — | 0 |
Performance théorique
| Taux de pixel | 14.40 GPixel/s | 1.000 GPixel/s |
|---|---|---|
| Taux de texture | 38.40 GTexel/s | 1.000 GTexel/s |
| FP32 (float) performance | 345.6 GFLOPS | — |
Board Design
| Longueur | 522 mm 20.6 inches | 168 mm 6.6 inches |
|---|---|---|
| TDP | 320 W | unknown |
| Suggestions pour le PSU | 700 W | 200 W |
| Sorties | No outputs | 1x LFH60 |
| Taille Slot | — | Single-slot |
| Connecteurs de puissance | — | None |
Caractéristiques graphiques
| DirectX | 11.1 (10_0) | 7.0 |
|---|---|---|
| OpenGL | 3.3 | 1.5 |
| OpenCL | 1.1 (1.0) | — |
| Vulkan | — | — |
| CUDA | 1.0 | — |
| Shader model | 4.0 | — |
| Pixel shader | — | 1.1 |
| Vertex shader | — | 1.1 |
