NVIDIA Tesla C870 vs NVIDIA Tesla D870
Processeur graphique
| Nom du GPU | G80 | G80 |
|---|---|---|
| Architecture | Tesla | Tesla |
| Fonderie | TSMC | TSMC |
| Taille du processus | 90 nm | 90 nm |
| Transistors | 681 million | 681 million |
| Taille des matrices | 484 mm² | 484 mm² |
Carte graphique
| Date de publication | May 2nd, 2007 | May 2nd, 2007 |
|---|---|---|
| Génération | Tesla | Tesla |
| Production | End-of-life | End-of-life |
| Prix de lancement | 1,499 USD | 7,499 USD |
| Bus interface | PCIe 1.0 x16 | PCIe 1.0 x16 |
Vitesse clock
| GPU clock | 600 MHz | 600 MHz |
|---|---|---|
| Shader clock | 1350 MHz | 1350 MHz |
| Mémoire clock | 800 MHz 1600 Mbps effective | 800 MHz 1600 Mbps effective |
Mémoire
| Taille de la mémoire | 1536 MB | 1536 MB |
|---|---|---|
| Type de mémoire | GDDR3 | GDDR3 |
| Bus mémoire | 384 bit | 384 bit |
| Bande passante | 76.80 GB/s | 76.80 GB/s |
Render Config
| Shading units | 128 | 128 |
|---|---|---|
| TMUs | 32 | 32 |
| ROPs | 24 | 24 |
| Comptage SM | 16 | 16 |
| Cache L2 | 96 KB | 96 KB |
Performance théorique
| Taux de pixel | 14.40 GPixel/s | 14.40 GPixel/s |
|---|---|---|
| Taux de texture | 38.40 GTexel/s | 38.40 GTexel/s |
| FP32 (float) performance | 345.6 GFLOPS | 345.6 GFLOPS |
Board Design
| Taille Slot | Dual-slot | Dual-slot |
|---|---|---|
| TDP | 171 W | 520 W |
| Suggestions pour le PSU | 450 W | 900 W |
| Sorties | No outputs | No outputs |
| Connecteurs de puissance | 2x 6-pin | — |
| Board number | P357 | — |
Caractéristiques graphiques
| DirectX | 11.1 (10_0) | 11.1 (10_0) |
|---|---|---|
| OpenGL | 3.3 | 3.3 |
| OpenCL | 1.1 (1.0) | 1.1 (1.0) |
| Vulkan | — | — |
| CUDA | 1.0 | 1.0 |
| Shader model | 4.0 | 4.0 |
