Nom du GPU | GA106 | TU104 |
---|---|---|
Architecture | Ampere | Turing |
Fonderie | Samsung | TSMC |
Taille du processus | 8 nm | 12 nm |
Transistors | 13,250 million | 13,600 million |
Taille des matrices | 276 mm² | 545 mm² |
GPU variant | — | TU104-895-A1 |
Date de publication | May 11th, 2021 | — |
---|---|---|
gpu.details.availability | 2021 | — |
Génération | GeForce 30 Mobile | — |
Prédécesseur | GeForce 20 Mobile | — |
Production | Active | — |
Bus interface | PCIe 4.0 x16 | — |
Base clock | 735 MHz | 585 MHz |
---|---|---|
Boost clock | 1035 MHz | 1590 MHz |
Mémoire clock | 1500 MHz 12 Gbps effective | 1250 MHz 10 Gbps effective |
Taille de la mémoire | 4 GB | 16 GB |
---|---|---|
Type de mémoire | GDDR6 | GDDR6 |
Bus mémoire | 128 bit | 256 bit |
Bande passante | 192.0 GB/s | 320.0 GB/s |
Shading units | 2560 | 2560 |
---|---|---|
TMUs | 80 | 160 |
ROPs | 48 | 64 |
Comptage SM | 20 | 40 |
Tensor cores | 80 | 320 |
RT cores | 20 | 40 |
Cache L1 | 128 KB (per SM) | 64 KB (per SM) |
Cache L2 | 2 MB | 4 MB |
Taux de pixel | 49.68 GPixel/s | 101.8 GPixel/s |
---|---|---|
Taux de texture | 82.80 GTexel/s | 254.4 GTexel/s |
FP16 (half) performance | 5.299 TFLOPS (1:1) | 65.13 TFLOPS (8:1) |
FP32 (float) performance | 5.299 TFLOPS | 8.141 TFLOPS |
FP64 (double) performance | 82.80 GFLOPS (1:64) | 254.4 GFLOPS (1:32) |
Taille Slot | IGP | Single-slot |
---|---|---|
TDP | 75 W | 70 W |
Sorties | No outputs | No outputs |
Connecteurs de puissance | None | None |
Longueur | — | 168 mm 6.6 inches |
Suggestions pour le PSU | — | 250 W |
Board number | — | PG183 SKU 200 |
DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 8.6 | 7.5 |
Shader model | 6.6 | 6.6 |
Date de publication | — | Sep 13th, 2018 |
---|---|---|
Génération | — | Tesla |
Production | — | Active |
Bus interface | — | PCIe 3.0 x16 |