NVIDIA Quadro K2000M vs NVIDIA Quadro T2000 Mobile
Processeur graphique
| Nom du GPU | GK107 | TU117 |
|---|---|---|
| GPU variant | N14P-Q3-A2 | — |
| Architecture | Kepler | Turing |
| Fonderie | TSMC | TSMC |
| Taille du processus | 28 nm | 12 nm |
| Transistors | 1,270 million | 4,700 million |
| Taille des matrices | 118 mm² | 200 mm² |
Graphiques mobiles
| Date de publication | Jun 1st, 2012 | May 27th, 2019 |
|---|---|---|
| Génération | Quadro Mobile (Kx000M) | Quadro Mobile (Tx000) |
| Production | End-of-life | Active |
| Bus interface | MXM-A (3.0) | PCIe 3.0 x16 |
| Critiques | 26 in our database | — |
Vitesse clock
| GPU clock | 745 MHz | — |
|---|---|---|
| Mémoire clock | 900 MHz 1800 Mbps effective | 2001 MHz 8 Gbps effective |
| Base clock | — | 1575 MHz |
| Boost clock | — | 1785 MHz |
Mémoire
| Taille de la mémoire | 2 GB | 4 GB |
|---|---|---|
| Type de mémoire | DDR3 | GDDR5 |
| Bus mémoire | 128 bit | 128 bit |
| Bande passante | 28.80 GB/s | 128.1 GB/s |
Render Config
| Shading units | 384 | 1024 |
|---|---|---|
| TMUs | 32 | 64 |
| ROPs | 16 | 32 |
| Comptage SMX | 2 | — |
| Cache L1 | 16 KB (per SMX) | 64 KB (per SM) |
| Cache L2 | 256 KB | 1024 KB |
| Comptage SM | — | 16 |
Performance théorique
| Taux de pixel | 5.960 GPixel/s | 57.12 GPixel/s |
|---|---|---|
| Taux de texture | 23.84 GTexel/s | 114.2 GTexel/s |
| FP32 (float) performance | 572.2 GFLOPS | 3.656 TFLOPS |
| FP64 (double) performance | 23.84 GFLOPS (1:24) | 114.2 GFLOPS (1:32) |
| FP16 (half) performance | — | 7.311 TFLOPS (2:1) |
Board Design
| Taille Slot | MXM Module | IGP |
|---|---|---|
| TDP | 55 W | 60 W |
| Sorties | No outputs | No outputs |
| Board number | P2091 SKU 0502 | — |
| Connecteurs de puissance | — | None |
Caractéristiques graphiques
| DirectX | 12 (11_0) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 3.0 |
| Vulkan | 1.1 | 1.2 |
| CUDA | 3.0 | 7.5 |
| Shader model | 5.1 | 6.6 |
