Nom du GPU | TU116B | GP104 |
---|---|---|
Architecture | Turing | Pascal |
Fonderie | TSMC | TSMC |
Taille du processus | 12 nm | 16 nm |
Transistors | 6,600 million | 7,200 million |
Taille des matrices | 284 mm² | 314 mm² |
GPU variant | — | N17E-Q3-A1 |
Date de publication | May 15th, 2019 | Jan 11th, 2017 |
---|---|---|
Génération | GeForce 16 Mobile | Quadro Mobile (Px000) |
Production | Active | End-of-life |
Bus interface | PCIe 3.0 x16 | MXM-B (3.0) |
Base clock | 1455 MHz | — |
---|---|---|
Boost clock | 1590 MHz | — |
Mémoire clock | 2000 MHz 16000 MHz effective | 1502 MHz 6 Gbps effective |
GPU clock | — | 1227 MHz |
Taille de la mémoire | 6 GB | 8 GB |
---|---|---|
Type de mémoire | GDDR6 | GDDR5 |
Bus mémoire | 192 bit | 256 bit |
Bande passante | 384.0 GB/s | 192.3 GB/s |
Shading units | 1280 | 1792 |
---|---|---|
TMUs | 80 | 112 |
ROPs | 48 | 64 |
Comptage SM | 20 | 14 |
Cache L1 | 64 KB (per SM) | 48 KB (per SM) |
Cache L2 | 1536 KB | 2 MB |
Taux de pixel | 76.32 GPixel/s | 78.53 GPixel/s |
---|---|---|
Taux de texture | 127.2 GTexel/s | 137.4 GTexel/s |
FP16 (half) performance | 8.141 TFLOPS (2:1) | 68.71 GFLOPS (1:64) |
FP32 (float) performance | 4.070 TFLOPS | 4.398 TFLOPS |
FP64 (double) performance | 127.2 GFLOPS (1:32) | 137.4 GFLOPS (1:32) |
Longueur | 229 mm 9 inches | — |
---|---|---|
TDP | unknown | 100 W |
Sorties | 1x DVI1x HDMI3x DisplayPort | No outputs |
Connecteurs de puissance | None | None |
Taille Slot | — | MXM Module |
DirectX | 12 (12_1) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 1.2 | 3.0 |
Vulkan | 1.2.140 | 1.2 |
CUDA | 7.5 | 6.1 |
Shader model | 6.5 | 6.4 |