GPU Name | Polaris 20 | TU106 |
---|---|---|
GPU Variante | Polaris 20 | N18E-G1 |
Architektur | GCN 4.0 | Turing |
Hersteller | GlobalFoundries | TSMC |
Prozessgröße | 14 nm | 12 nm |
Transistoren | 5,700 million | 10,800 million |
Chipgröße | 232 mm² | 445 mm² |
Veröffentlichungsdatum | Jun 5th, 2017 | Jan 29th, 2020 |
---|---|---|
Generation | Radeon Pro Mac (500 Series) | GeForce 20 Mobile |
Produktion | Active | Active |
Businterface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Vorgänger | — | GeForce 10 Mobile |
Nachfolger | — | GeForce 30 Mobile |
Basis-Taktfrequenz | 1000 MHz | 975 MHz |
---|---|---|
Boost-Takt | 1105 MHz | 1185 MHz |
Speicher-Taktung | 1695 MHz 6.8 Gbps effective | 1375 MHz 11 Gbps effective |
Speichergröße | 4 GB | 6 GB |
---|---|---|
Speichertyp | GDDR5 | GDDR6 |
Speicherbus | 256 bit | 192 bit |
Bandbreite | 217.0 GB/s | 264.0 GB/s |
Shading-Einheiten | 1792 | 1920 |
---|---|---|
TMUs | 112 | 120 |
ROPs | 32 | 48 |
Compute Units | 28 | — |
Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
Cache L2 | 2 MB | 3 MB |
Anzahl SM | — | 30 |
Tensor Cores | — | 240 |
RT-Kerne | — | 30 |
Pixelrate | 35.36 GPixel/s | 56.88 GPixel/s |
---|---|---|
Texturrate | 123.8 GTexel/s | 142.2 GTexel/s |
FP16 (half) Leistung | 3.960 TFLOPS (1:1) | 9.101 TFLOPS (2:1) |
FP32 (float) Leistung | 3.960 TFLOPS | 4.550 TFLOPS |
FP64 (double) Leistung | 247.5 GFLOPS (1:16) | 142.2 GFLOPS (1:32) |
Steckplatzbreite | IGP | MXM Module |
---|---|---|
TDP | 150 W | 65 W |
Ausgabe | No outputs | No outputs |
Stromverbindung | None | None |
Board-Nummer | — | E4914 SKU 31 |
DirectX | 12 (12_0) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader-Modell | 6.4 | 6.6 |
CUDA | — | 7.5 |