NVIDIA GeForce GTX 1650 Max-Q vs NVIDIA GeForce GTX 1660 Mobile
Processeur graphique
| Nom du GPU | TU117 | TU116B |
|---|---|---|
| GPU variant | N18P-G61-MP2 | — |
| Architecture | Turing | Turing |
| Fonderie | TSMC | TSMC |
| Taille du processus | 12 nm | 12 nm |
| Transistors | 4,700 million | 6,600 million |
| Taille des matrices | 200 mm² | 284 mm² |
Graphiques mobiles
| Date de publication | Apr 15th, 2020 | May 15th, 2019 |
|---|---|---|
| Génération | GeForce 16 Mobile | GeForce 16 Mobile |
| Production | Active | Active |
| Bus interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
| Critiques | 45 in our database | — |
| Prédécesseur | GeForce 10 Mobile | — |
| Successeur | GeForce 20 Mobile | — |
Vitesse clock
| Base clock | 930 MHz | 1455 MHz |
|---|---|---|
| Boost clock | 1125 MHz | 1590 MHz |
| Mémoire clock | 1250 MHz 10 Gbps effective | 2000 MHz 16000 MHz effective |
Mémoire
| Taille de la mémoire | 4 GB | 6 GB |
|---|---|---|
| Type de mémoire | GDDR6 | GDDR6 |
| Bus mémoire | 128 bit | 192 bit |
| Bande passante | 160.0 GB/s | 384.0 GB/s |
Render Config
| Shading units | 1024 | 1280 |
|---|---|---|
| TMUs | 64 | 80 |
| ROPs | 32 | 48 |
| Comptage SM | 16 | 20 |
| Cache L1 | 64 KB (per SM) | 64 KB (per SM) |
| Cache L2 | 1024 KB | 1536 KB |
Performance théorique
| Taux de pixel | 36.00 GPixel/s | 76.32 GPixel/s |
|---|---|---|
| Taux de texture | 72.00 GTexel/s | 127.2 GTexel/s |
| FP16 (half) performance | 4.608 TFLOPS (2:1) | 8.141 TFLOPS (2:1) |
| FP32 (float) performance | 2.304 TFLOPS | 4.070 TFLOPS |
| FP64 (double) performance | 72.00 GFLOPS (1:32) | 127.2 GFLOPS (1:32) |
Board Design
| TDP | 50 W | unknown |
|---|---|---|
| Sorties | No outputs | 1x DVI1x HDMI3x DisplayPort |
| Connecteurs de puissance | None | None |
| Board number | E4904 SKU 11 | — |
| Longueur | — | 229 mm 9 inches |
Caractéristiques graphiques
| DirectX | 12 (12_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 1.2 |
| Vulkan | 1.2 | 1.2.140 |
| CUDA | 7.5 | 7.5 |
| Shader model | 6.6 | 6.5 |
