GPU Name | TU106 | GA106 |
---|---|---|
GPU Variante | N18E-G1-KD-A1 | — |
Architektur | Turing | Ampere |
Hersteller | TSMC | Samsung |
Prozessgröße | 12 nm | 8 nm |
Transistoren | 10,800 million | 13,250 million |
Chipgröße | 445 mm² | 276 mm² |
Veröffentlichungsdatum | Jan 29th, 2019 | May 11th, 2021 |
---|---|---|
Generation | GeForce 20 Mobile | GeForce 30 Mobile |
Produktion | Active | Active |
Businterface | PCIe 3.0 x16 | PCIe 4.0 x16 |
Vorgänger | GeForce 10 Mobile | GeForce 20 Mobile |
Nachfolger | GeForce 30 Mobile | — |
gpu.details.availability | — | 2021 |
Basis-Taktfrequenz | 960 MHz | 735 MHz |
---|---|---|
Boost-Takt | 1200 MHz | 1035 MHz |
Speicher-Taktung | 1750 MHz 14 Gbps effective | 1500 MHz 12 Gbps effective |
Speichergröße | 6 GB | 4 GB |
---|---|---|
Speichertyp | GDDR6 | GDDR6 |
Speicherbus | 192 bit | 128 bit |
Bandbreite | 336.0 GB/s | 192.0 GB/s |
Shading-Einheiten | 1920 | 2560 |
---|---|---|
TMUs | 120 | 80 |
ROPs | 48 | 48 |
Anzahl SM | 30 | 20 |
Tensor Cores | 240 | 80 |
RT-Kerne | 30 | 20 |
Cache L1 | 64 KB (per SM) | 128 KB (per SM) |
Cache L2 | 3 MB | 2 MB |
Pixelrate | 57.60 GPixel/s | 49.68 GPixel/s |
---|---|---|
Texturrate | 144.0 GTexel/s | 82.80 GTexel/s |
FP16 (half) Leistung | 9.216 TFLOPS (2:1) | 5.299 TFLOPS (1:1) |
FP32 (float) Leistung | 4.608 TFLOPS | 5.299 TFLOPS |
FP64 (double) Leistung | 144.0 GFLOPS (1:32) | 82.80 GFLOPS (1:64) |
Steckplatzbreite | MXM Module | IGP |
---|---|---|
TDP | 115 W | 75 W |
Ausgabe | No outputs | No outputs |
Stromverbindung | None | None |
Board-Nummer | E4914 SKU 30 | — |
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 | 7.5 | 8.6 |
Shader-Modell | 6.6 | 6.6 |