AMD Xbox One X GPU vs NVIDIA GeForce RTX 2060
Grafikprozessor
| GPU Name | Scorpio | TU106 |
|---|---|---|
| Architektur | GCN 2.0 | Turing |
| Hersteller | TSMC | TSMC |
| Prozessgröße | 16 nm | 12 nm |
| Transistoren | 7,000 million | 10,800 million |
| Chipgröße | 359 mm² | 445 mm² |
| GPU Variante | — | TU106-200A-KA-A1 |
Grafikkarte
| Veröffentlichungsdatum | Nov 7th, 2017 | Jan 7th, 2019 |
|---|---|---|
| Generation | Console GPU | GeForce 20 |
| Produktion | End-of-life | Active |
| Originalpreis | 499 USD | 349 USD |
| Businterface | IGP | PCIe 3.0 x16 |
| Vorgänger | — | GeForce 10 |
| Reviews | — | 85 in our database |
| Nachfolger | — | GeForce 30 |
Takt-Geschwindigkeiten
| GPU-Taktung | 1172 MHz | — |
|---|---|---|
| Speicher-Taktung | 1700 MHz 6.8 Gbps effective | 1750 MHz 14 Gbps effective |
| Basis-Taktfrequenz | — | 1365 MHz |
| Boost-Takt | — | 1680 MHz |
Speicher
| Speichergröße | 12 GB | 6 GB |
|---|---|---|
| Speichertyp | GDDR5 | GDDR6 |
| Speicherbus | 384 bit | 192 bit |
| Bandbreite | 326.4 GB/s | 336.0 GB/s |
Render-Konfiguration
| Shading-Einheiten | 2560 | 1920 |
|---|---|---|
| TMUs | 160 | 120 |
| ROPs | 32 | 48 |
| Compute Units | 40 | — |
| Anzahl SM | — | 30 |
| Tensor Cores | — | 240 |
| RT-Kerne | — | 30 |
| Cache L1 | — | 64 KB (per SM) |
| Cache L2 | — | 3 MB |
Theoretische Leistung
| Pixelrate | 37.50 GPixel/s | 80.64 GPixel/s |
|---|---|---|
| Texturrate | 187.5 GTexel/s | 201.6 GTexel/s |
| FP16 (half) Leistung | 6.001 TFLOPS (1:1) | 12.90 TFLOPS (2:1) |
| FP32 (float) Leistung | 6.001 TFLOPS | 6.451 TFLOPS |
| FP64 (double) Leistung | — | 201.6 GFLOPS (1:32) |
Boarddesign
| Steckplatzbreite | IGP | Dual-slot |
|---|---|---|
| Länge | 300 mm 11.8 inches | 229 mm 9 inches |
| Breite | 240 mm 9.4 inches | 113 mm 4.4 inches |
| Höhe | 60 mm 2.4 inches | 35 mm 1.4 inches |
| Gewicht | 3.8 kg (8.4 lbs) | — |
| TDP | 150 W | 160 W |
| Vorgeschlagenes Netzteil | 350 W | 450 W |
| Ausgabe | No outputs | 1x DVI1x HDMI2x DisplayPort1x USB Type-C |
| Stromverbindung | — | 1x 8-pin |
| Board-Nummer | — | PG160 SKU 42 |
Grafik-Features
| DirectX | 12 (12_0) | 12 Ultimate (12_2) |
|---|---|---|
| OpenGL | — | 4.6 |
| OpenCL | 1.2 | 3.0 |
| Vulkan | 1.1 | 1.2 |
| Shader-Modell | 6.0 | 6.6 |
| CUDA | — | 7.5 |
