Nom du GPU | GP104 | TU106 |
---|---|---|
GPU variant | N17E-G2-A1 | — |
Architecture | Pascal | Turing |
Fonderie | TSMC | TSMC |
Taille du processus | 16 nm | 12 nm |
Transistors | 7,200 million | 10,800 million |
Taille des matrices | 314 mm² | 445 mm² |
Date de publication | Aug 15th, 2016 | Apr 10th, 2020 |
---|---|---|
Génération | GeForce 10 Mobile | GeForce 20 Mobile |
Production | Active | Active |
Bus interface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Critiques | 124 in our database | 40 in our database |
Base clock | 1442 MHz | 1305 MHz |
---|---|---|
Boost clock | 1645 MHz | 1485 MHz |
Mémoire clock | 2002 MHz 8008 MHz effective | 1750 MHz 14000 MHz effective |
Taille de la mémoire | 8 GB | 8 GB |
---|---|---|
Type de mémoire | GDDR5 | GDDR6 |
Bus mémoire | 256 bit | 256 bit |
Bande passante | 256.3 GB/s | 448.0 GB/s |
Shading units | 2048 | 2176 |
---|---|---|
TMUs | 128 | 136 |
ROPs | 64 | 64 |
Comptage SM | 16 | 34 |
Cache L1 | 48 KB (per SM) | 64 KB (per SM) |
Cache L2 | 2 MB | 4 MB |
Tensor cores | — | 272 |
RT cores | — | 34 |
Taux de pixel | 105.3 GPixel/s | 95.04 GPixel/s |
---|---|---|
Taux de texture | 210.6 GTexel/s | 202.0 GTexel/s |
FP16 (half) performance | 105.3 GFLOPS (1:64) | 12.93 TFLOPS (2:1) |
FP32 (float) performance | 6.738 TFLOPS | 6.463 TFLOPS |
FP64 (double) performance | 210.6 GFLOPS (1:32) | 202.0 GFLOPS (1:32) |
Taille Slot | MXM Module | MXM Module |
---|---|---|
TDP | 120 W | 100 W |
Sorties | No outputs | No outputs |
Connecteurs de puissance | None | None |
DirectX | 12 (12_1) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 1.2 | 1.2 |
Vulkan | 1.2.131 | 1.2.140 |
CUDA | 6.1 | 7.5 |
Shader model | 6.4 | 6.5 |