NVIDIA Tesla D870 vs NVIDIA Tesla M10
Processeur graphique
| Nom du GPU | G80 | GM107 |
|---|---|---|
| Architecture | Tesla | Maxwell |
| Fonderie | TSMC | TSMC |
| Taille du processus | 90 nm | 28 nm |
| Transistors | 681 million | 1,870 million |
| Taille des matrices | 484 mm² | 148 mm² |
| GPU variant | — | GM107-570-A2 |
Carte graphique
| Date de publication | May 2nd, 2007 | May 18th, 2016 |
|---|---|---|
| Génération | Tesla | Tesla |
| Production | End-of-life | End-of-life |
| Prix de lancement | 7,499 USD | — |
| Bus interface | PCIe 1.0 x16 | PCIe 3.0 x16 |
Vitesse clock
| GPU clock | 600 MHz | — |
|---|---|---|
| Shader clock | 1350 MHz | — |
| Mémoire clock | 800 MHz 1600 Mbps effective | 1300 MHz 5.2 Gbps effective |
| Base clock | — | 1033 MHz |
| Boost clock | — | 1306 MHz |
Mémoire
| Taille de la mémoire | 1536 MB | 8 GB |
|---|---|---|
| Type de mémoire | GDDR3 | GDDR5 |
| Bus mémoire | 384 bit | 128 bit |
| Bande passante | 76.80 GB/s | 83.20 GB/s |
Render Config
| Shading units | 128 | 640 |
|---|---|---|
| TMUs | 32 | 40 |
| ROPs | 24 | 16 |
| Comptage SM | 16 | — |
| Cache L2 | 96 KB | 2 MB |
| Comptage SMM | — | 5 |
| Cache L1 | — | 64 KB (per SMM) |
Performance théorique
| Taux de pixel | 14.40 GPixel/s | 20.90 GPixel/s |
|---|---|---|
| Taux de texture | 38.40 GTexel/s | 52.24 GTexel/s |
| FP32 (float) performance | 345.6 GFLOPS | 1.672 TFLOPS |
| FP64 (double) performance | — | 52.24 GFLOPS (1:32) |
Board Design
| Taille Slot | Dual-slot | Dual-slot |
|---|---|---|
| TDP | 520 W | 225 W |
| Suggestions pour le PSU | 900 W | 550 W |
| Sorties | No outputs | No outputs |
| Longueur | — | 267 mm 10.5 inches |
| Connecteurs de puissance | — | 1x 8-pin |
| Board number | — | P2405 SKU 70 |
Caractéristiques graphiques
| DirectX | 11.1 (10_0) | 12 (11_0) |
|---|---|---|
| OpenGL | 3.3 | 4.6 |
| OpenCL | 1.1 (1.0) | 3.0 |
| Vulkan | — | 1.1 |
| CUDA | 1.0 | 5.0 |
| Shader model | 4.0 | 5.1 |
