GPU Name | TU106 | TU104 |
---|---|---|
GPU Variante | N18E-G2-A1 | N18E-G3-A1 |
Architektur | Turing | Turing |
Hersteller | TSMC | TSMC |
Prozessgröße | 12 nm | 12 nm |
Transistoren | 10,800 million | 13,600 million |
Chipgröße | 445 mm² | 545 mm² |
Veröffentlichungsdatum | Jan 29th, 2019 | Jan 29th, 2019 |
---|---|---|
Generation | GeForce 20 Mobile | GeForce 20 Mobile |
Produktion | Active | Active |
Businterface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Vorgänger | GeForce 10 Mobile | GeForce 10 Mobile |
Nachfolger | GeForce 30 Mobile | GeForce 30 Mobile |
Basis-Taktfrequenz | 885 MHz | 735 MHz |
---|---|---|
Boost-Takt | 1185 MHz | 1095 MHz |
Speicher-Taktung | 1500 MHz 12 Gbps effective | 1500 MHz 12 Gbps effective |
Speichergröße | 8 GB | 8 GB |
---|---|---|
Speichertyp | GDDR6 | GDDR6 |
Speicherbus | 256 bit | 256 bit |
Bandbreite | 384.0 GB/s | 384.0 GB/s |
Shading-Einheiten | 2304 | 2944 |
---|---|---|
TMUs | 144 | 184 |
ROPs | 64 | 64 |
Anzahl SM | 36 | 46 |
Tensor Cores | 288 | 368 |
RT-Kerne | 36 | 46 |
Cache L1 | 64 KB (per SM) | 64 KB (per SM) |
Cache L2 | 4 MB | 4 MB |
Pixelrate | 75.84 GPixel/s | 70.08 GPixel/s |
---|---|---|
Texturrate | 170.6 GTexel/s | 201.5 GTexel/s |
FP16 (half) Leistung | 10.92 TFLOPS (2:1) | 12.89 TFLOPS (2:1) |
FP32 (float) Leistung | 5.460 TFLOPS | 6.447 TFLOPS |
FP64 (double) Leistung | 170.6 GFLOPS (1:32) | 201.5 GFLOPS (1:32) |
Steckplatzbreite | MXM Module | Dual-slot |
---|---|---|
TDP | 90 W | 80 W |
Ausgabe | No outputs | No outputs |
Stromverbindung | None | None |
Board-Nummer | E4914 SKU 30 | E4914 SKU 10 |
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 | 7.5 |
Shader-Modell | 6.6 | 6.6 |