NVIDIA Tesla K20s vs NVIDIA Tesla K40c
Processeur graphique
| Nom du GPU | GK110 | GK180 |
|---|---|---|
| Architecture | Kepler | Kepler |
| Fonderie | TSMC | TSMC |
| Taille du processus | 28 nm | 28 nm |
| Transistors | 7,080 million | 7,080 million |
| Taille des matrices | 561 mm² | 561 mm² |
| GPU variant | — | GK180-890-A1 |
Carte graphique
| Date de publication | Feb 18th, 2013 | Oct 8th, 2013 |
|---|---|---|
| Génération | Tesla | Tesla |
| Production | End-of-life | End-of-life |
| Prix de lancement | 3,199 USD | 7,699 USD |
| Bus interface | PCIe 2.0 x16 | PCIe 3.0 x16 |
Vitesse clock
| GPU clock | 575 MHz | — |
|---|---|---|
| Mémoire clock | 1300 MHz 5.2 Gbps effective | 1502 MHz 6 Gbps effective |
| Base clock | — | 745 MHz |
| Boost clock | — | 876 MHz |
Mémoire
| Taille de la mémoire | 5 GB | 12 GB |
|---|---|---|
| Type de mémoire | GDDR5 | GDDR5 |
| Bus mémoire | 320 bit | 384 bit |
| Bande passante | 208.0 GB/s | 288.4 GB/s |
Render Config
| Shading units | 2496 | 2880 |
|---|---|---|
| TMUs | 208 | 240 |
| ROPs | 40 | 48 |
| Comptage SMX | 13 | 15 |
| Cache L1 | 16 KB (per SMX) | 16 KB (per SMX) |
| Cache L2 | 1280 KB | 1536 KB |
Performance théorique
| Taux de pixel | 29.90 GPixel/s | 52.56 GPixel/s |
|---|---|---|
| Taux de texture | 119.6 GTexel/s | 210.2 GTexel/s |
| FP32 (float) performance | 2.870 TFLOPS | 5.046 TFLOPS |
| FP64 (double) performance | 956.8 GFLOPS (1:3) | 1.682 TFLOPS (1:3) |
Board Design
| Taille Slot | Dual-slot | Dual-slot |
|---|---|---|
| Longueur | 267 mm 10.5 inches | 267 mm 10.5 inches |
| TDP | 225 W | 245 W |
| Suggestions pour le PSU | 550 W | 550 W |
| Sorties | No outputs | No outputs |
| Connecteurs de puissance | — | 1x 6-pin + 1x 8-pin |
Caractéristiques graphiques
| DirectX | 12 (11_0) | 12 (11_0) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.1 | 1.1 |
| CUDA | 3.5 | 3.5 |
| Shader model | 5.1 | 5.1 |
