NVIDIA GRID K520Q vs NVIDIA Tesla C2075
Processeur graphique
| Nom du GPU | GK104 | GF110 |
|---|---|---|
| Architecture | Kepler | Fermi 2.0 |
| Fonderie | TSMC | TSMC |
| Taille du processus | 28 nm | 40 nm |
| Transistors | 3,540 million | 3,000 million |
| Taille des matrices | 294 mm² | 520 mm² |
| GPU variant | — | GF110-351-A1 |
Carte graphique
| Date de publication | Jul 2nd, 2014 | Jul 25th, 2011 |
|---|---|---|
| Génération | GRID | Tesla |
| Production | End-of-life | End-of-life |
| Prix de lancement | 3,599 USD | — |
| Bus interface | PCIe 3.0 x16 | PCIe 2.0 x16 |
Vitesse clock
| GPU clock | 745 MHz | 574 MHz |
|---|---|---|
| Mémoire clock | 1250 MHz 5 Gbps effective | 783 MHz 3.1 Gbps effective |
| Shader clock | — | 1147 MHz |
Mémoire
| Taille de la mémoire | 4 GB | 6 GB |
|---|---|---|
| Type de mémoire | GDDR5 | GDDR5 |
| Bus mémoire | 256 bit | 384 bit |
| Bande passante | 160.0 GB/s | 150.3 GB/s |
Render Config
| Shading units | 1536 | 448 |
|---|---|---|
| TMUs | 128 | 56 |
| ROPs | 32 | 48 |
| Comptage SMX | 8 | — |
| Cache L1 | 16 KB (per SMX) | 64 KB (per SM) |
| Cache L2 | 512 KB | 768 KB |
| Comptage SM | — | 14 |
Performance théorique
| Taux de pixel | 23.84 GPixel/s | 16.07 GPixel/s |
|---|---|---|
| Taux de texture | 95.36 GTexel/s | 32.14 GTexel/s |
| FP32 (float) performance | 2.289 TFLOPS | 1,028 GFLOPS |
| FP64 (double) performance | 95.36 GFLOPS (1:24) | 513.9 GFLOPS (1:2) |
Board Design
| Taille Slot | Dual-slot | Dual-slot |
|---|---|---|
| Longueur | 267 mm 10.5 inches | 248 mm 9.8 inches |
| TDP | 225 W | 247 W |
| Suggestions pour le PSU | 550 W | 550 W |
| Sorties | No outputs | 1x DVI |
| Connecteurs de puissance | — | 1x 6-pin + 1x 8-pin |
| Board number | — | P1030 |
Caractéristiques graphiques
| DirectX | 12 (11_0) | 12 (11_0) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 1.1 |
| Vulkan | 1.1 | — |
| CUDA | 3.0 | 2.0 |
| Shader model | 5.1 | 5.1 |
