NVIDIA Quadro P620 vs NVIDIA Tesla C2050
Processeur graphique
| Nom du GPU | GP107 | GF100 |
|---|---|---|
| Architecture | Pascal | Fermi |
| Fonderie | Samsung | TSMC |
| Taille du processus | 14 nm | 40 nm |
| Transistors | 3,300 million | 3,100 million |
| Taille des matrices | 132 mm² | 529 mm² |
| GPU variant | — | GF100-850-A3 |
Carte graphique
| Date de publication | Feb 1st, 2018 | Jul 25th, 2011 |
|---|---|---|
| Génération | Quadro | Tesla |
| Production | End-of-life | End-of-life |
| Bus interface | PCIe 3.0 x16 | PCIe 2.0 x16 |
Vitesse clock
| Base clock | 1266 MHz | — |
|---|---|---|
| Boost clock | 1354 MHz | — |
| Mémoire clock | 1252 MHz 5 Gbps effective | 750 MHz 3 Gbps effective |
| GPU clock | — | 574 MHz |
| Shader clock | — | 1147 MHz |
Mémoire
| Taille de la mémoire | 2 GB | 3 GB |
|---|---|---|
| Type de mémoire | GDDR5 | GDDR5 |
| Bus mémoire | 128 bit | 384 bit |
| Bande passante | 80.13 GB/s | 144.0 GB/s |
Render Config
| Shading units | 512 | 448 |
|---|---|---|
| TMUs | 32 | 56 |
| ROPs | 16 | 48 |
| Comptage SM | 4 | 14 |
| Cache L1 | 48 KB (per SM) | 64 KB (per SM) |
| Cache L2 | 1024 KB | 768 KB |
Performance théorique
| Taux de pixel | 21.66 GPixel/s | 16.07 GPixel/s |
|---|---|---|
| Taux de texture | 43.33 GTexel/s | 32.14 GTexel/s |
| FP16 (half) performance | 21.66 GFLOPS (1:64) | — |
| FP32 (float) performance | 1,386 GFLOPS | 1,028 GFLOPS |
| FP64 (double) performance | 43.33 GFLOPS (1:32) | 513.9 GFLOPS (1:2) |
Board Design
| Taille Slot | Single-slot | Dual-slot |
|---|---|---|
| Longueur | 145 mm 5.7 inches | 248 mm 9.8 inches |
| Taille | 69 mm 2.7 inches | — |
| TDP | 40 W | 238 W |
| Suggestions pour le PSU | 200 W | 550 W |
| Sorties | 4x mini-DisplayPort | 1x DVI |
| Connecteurs de puissance | None | 1x 6-pin + 1x 8-pin |
Caractéristiques graphiques
| DirectX | 12 (12_1) | 12 (11_0) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 1.1 |
| Vulkan | 1.2 | — |
| CUDA | 6.1 | 2.0 |
| Shader model | 6.4 | 5.1 |
