AMD Radeon 520 Mobile vs Intel UHD Graphics
Grafikprozessor
| GPU Name | Banks | Amber Lake GT2 |
|---|---|---|
| GPU Variante | Banks PRO (216-0568010) | — |
| Architektur | GCN 1.0 | Generation 9.5 |
| Hersteller | TSMC | Intel |
| Prozessgröße | 28 nm | 14 nm |
| Transistoren | 690 million | unknown |
| Chipgröße | 56 mm² | unknown |
Mobile Grafik
| Veröffentlichungsdatum | Apr 18th, 2017 | — |
|---|---|---|
| Generation | Mobility Radeon (M500) | — |
| Produktion | End-of-life | — |
| Businterface | PCIe 3.0 x8 | — |
| Vorgänger | Crystal System | — |
Takt-Geschwindigkeiten
| GPU-Taktung | 1030 MHz | — |
|---|---|---|
| Speicher-Taktung | 1000 MHz 2 Gbps effective | System Shared |
| Basis-Taktfrequenz | — | 300 MHz |
| Boost-Takt | — | 1050 MHz |
Speicher
| Speichergröße | 2 GB | System Shared |
|---|---|---|
| Speichertyp | DDR3 | System Shared |
| Speicherbus | 64 bit | System Shared |
| Bandbreite | 16.00 GB/s | System Dependent |
Render-Konfiguration
| Shading-Einheiten | 320 | 192 |
|---|---|---|
| TMUs | 20 | 24 |
| ROPs | 8 | 3 |
| Compute Units | 5 | — |
| Cache L1 | 16 KB (per CU) | — |
| Cache L2 | 128 KB | — |
| Execution Units | — | 24 |
Theoretische Leistung
| Pixelrate | 8.240 GPixel/s | 3.150 GPixel/s |
|---|---|---|
| Texturrate | 20.60 GTexel/s | 25.20 GTexel/s |
| FP32 (float) Leistung | 659.2 GFLOPS | 403.2 GFLOPS |
| FP64 (double) Leistung | 41.20 GFLOPS (1:16) | 100.8 GFLOPS (1:4) |
| FP16 (half) Leistung | — | 806.4 GFLOPS (2:1) |
Boarddesign
| Steckplatzbreite | IGP | IGP |
|---|---|---|
| TDP | 50 W | 15 W |
| Ausgabe | No outputs | No outputs |
| Stromverbindung | None | — |
Grafik-Features
| DirectX | 12 (11_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 1.2 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader-Modell | 5.1 | 6.4 |
ANDERE EIGENSCHAFTEN
Integrierter Grafikprozessor
| Veröffentlichungsdatum | — | Aug 21st, 2019 |
|---|---|---|
| Generation | — | HD Graphics-T (Amber Lake) |
| Produktion | — | Active |
| Businterface | — | Ring Bus |
| Reviews | — | 1 in our database |