Nom du GPU | TU106 | GP102 |
---|---|---|
GPU variant | N18E-G2-A1 | — |
Architecture | Turing | Pascal |
Fonderie | TSMC | TSMC |
Taille du processus | 12 nm | 16 nm |
Transistors | 10,800 million | 11,800 million |
Taille des matrices | 445 mm² | 471 mm² |
Date de publication | Jan 29th, 2019 | — |
---|---|---|
Génération | GeForce 20 Mobile | — |
Production | Active | — |
Bus interface | PCIe 3.0 x16 | — |
Prédécesseur | GeForce 10 Mobile | — |
Successeur | GeForce 30 Mobile | — |
Base clock | 885 MHz | 1303 MHz |
---|---|---|
Boost clock | 1185 MHz | 1531 MHz |
Mémoire clock | 1500 MHz 12 Gbps effective | 1808 MHz 14.5 Gbps effective |
Taille de la mémoire | 8 GB | 24 GB |
---|---|---|
Type de mémoire | GDDR6 | GDDR5X |
Bus mémoire | 256 bit | 384 bit |
Bande passante | 384.0 GB/s | 694.3 GB/s |
Shading units | 2304 | 3840 |
---|---|---|
TMUs | 144 | 240 |
ROPs | 64 | 96 |
Comptage SM | 36 | 30 |
Tensor cores | 288 | — |
RT cores | 36 | — |
Cache L1 | 64 KB (per SM) | 48 KB (per SM) |
Cache L2 | 4 MB | 3 MB |
Taux de pixel | 75.84 GPixel/s | 147.0 GPixel/s |
---|---|---|
Taux de texture | 170.6 GTexel/s | 367.4 GTexel/s |
FP16 (half) performance | 10.92 TFLOPS (2:1) | 183.7 GFLOPS (1:64) |
FP32 (float) performance | 5.460 TFLOPS | 11.76 TFLOPS |
FP64 (double) performance | 170.6 GFLOPS (1:32) | 367.4 GFLOPS (1:32) |
Taille Slot | MXM Module | Dual-slot |
---|---|---|
TDP | 90 W | 250 W |
Sorties | No outputs | No outputs |
Connecteurs de puissance | None | 1x 6-pin + 1x 8-pin |
Board number | E4914 SKU 30 | PG610 SKU 200 |
Longueur | — | 267 mm 10.5 inches |
Taille | — | 111 mm 4.4 inches |
Suggestions pour le PSU | — | 600 W |
DirectX | 12 Ultimate (12_2) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 7.5 | 6.1 |
Shader model | 6.6 | 6.4 |
Date de publication | — | Sep 13th, 2016 |
---|---|---|
Génération | — | Tesla |
Production | — | End-of-life |
Prix de lancement | — | 5,699 USD |
Bus interface | — | PCIe 3.0 x16 |