NVIDIA GRID M40 vs NVIDIA Tesla K40c
Processeur graphique
| Nom du GPU | GM107 | GK180 |
|---|---|---|
| Architecture | Maxwell | Kepler |
| Fonderie | TSMC | TSMC |
| Taille du processus | 28 nm | 28 nm |
| Transistors | 1,870 million | 7,080 million |
| Taille des matrices | 148 mm² | 561 mm² |
| GPU variant | — | GK180-890-A1 |
Carte graphique
| Date de publication | May 18th, 2016 | Oct 8th, 2013 |
|---|---|---|
| Génération | GRID | Tesla |
| Production | End-of-life | End-of-life |
| Bus interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Prix de lancement | — | 7,699 USD |
Vitesse clock
| GPU clock | 1033 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 | 8 GB | 12 GB |
|---|---|---|
| Type de mémoire | GDDR5 | GDDR5 |
| Bus mémoire | 128 bit | 384 bit |
| Bande passante | 83.20 GB/s | 288.4 GB/s |
Render Config
| Shading units | 384 | 2880 |
|---|---|---|
| TMUs | 32 | 240 |
| ROPs | 16 | 48 |
| Comptage SMM | 3 | — |
| Cache L1 | 64 KB (per SMM) | 16 KB (per SMX) |
| Cache L2 | 2 MB | 1536 KB |
| Comptage SMX | — | 15 |
Performance théorique
| Taux de pixel | 16.53 GPixel/s | 52.56 GPixel/s |
|---|---|---|
| Taux de texture | 33.06 GTexel/s | 210.2 GTexel/s |
| FP32 (float) performance | 793.3 GFLOPS | 5.046 TFLOPS |
| FP64 (double) performance | 24.79 GFLOPS (1:32) | 1.682 TFLOPS (1:3) |
Board Design
| Taille Slot | Dual-slot | Dual-slot |
|---|---|---|
| TDP | 50 W | 245 W |
| Suggestions pour le PSU | 250 W | 550 W |
| Sorties | No outputs | No outputs |
| Longueur | — | 267 mm 10.5 inches |
| 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 | 5.0 | 3.5 |
| Shader model | 5.1 | 5.1 |
