Nom du GPU | G98 | TU106 |
---|---|---|
GPU variant | NB9M-GE | N19E-Q1-KA-K1 |
Architecture | Tesla | Turing |
Fonderie | TSMC | TSMC |
Taille du processus | 65 nm | 12 nm |
Transistors | 210 million | 10,800 million |
Taille des matrices | 86 mm² | 445 mm² |
Date de publication | Aug 15th, 2008 | May 27th, 2019 |
---|---|---|
Génération | NVS Mobile | Quadro Mobile (Tx000) |
Production | End-of-life | Active |
Bus interface | MXM-I | PCIe 3.0 x16 |
Critiques | 26 in our database | — |
GPU clock | 530 MHz | — |
---|---|---|
Shader clock | 1300 MHz | — |
Mémoire clock | 700 MHz 1400 Mbps effective | 1750 MHz 14 Gbps effective |
Base clock | — | 945 MHz |
Boost clock | — | 1380 MHz |
Taille de la mémoire | 256 MB | 6 GB |
---|---|---|
Type de mémoire | GDDR3 | GDDR6 |
Bus mémoire | 64 bit | 192 bit |
Bande passante | 11.20 GB/s | 336.0 GB/s |
Shading units | 8 | 1920 |
---|---|---|
TMUs | 4 | 120 |
ROPs | 4 | 64 |
Comptage SM | 1 | 30 |
Cache L2 | 16 KB | 3 MB |
Tensor cores | — | 240 |
RT cores | — | 30 |
Cache L1 | — | 64 KB (per SM) |
Taux de pixel | 2.120 GPixel/s | 88.32 GPixel/s |
---|---|---|
Taux de texture | 2.120 GTexel/s | 165.6 GTexel/s |
FP32 (float) performance | 20.80 GFLOPS | 5.299 TFLOPS |
FP16 (half) performance | — | 10.60 TFLOPS (2:1) |
FP64 (double) performance | — | 165.6 GFLOPS (1:32) |
Taille Slot | MXM Module | IGP |
---|---|---|
TDP | 10 W | 80 W |
Sorties | No outputs | No outputs |
Connecteurs de puissance | — | None |
DirectX | 11.1 (10_0) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 3.3 | 4.6 |
OpenCL | 1.1 | 3.0 |
Vulkan | — | 1.2 |
CUDA | 1.1 | 7.5 |
Shader model | 4.0 | 6.6 |