AMD Radeon Pro Vega 56 vs NVIDIA Quadro P5200 Max-Q
Grafikprozessor
| GPU Name | Vega 10 | GP104 |
|---|---|---|
| GPU Variante | Vega 10 XL (215-0894216) | — |
| Architektur | GCN 5.0 | Pascal |
| Hersteller | GlobalFoundries | TSMC |
| Prozessgröße | 14 nm | 16 nm |
| Transistoren | 12,500 million | 7,200 million |
| Chipgröße | 495 mm² | 314 mm² |
Mobile Grafik
| Veröffentlichungsdatum | Aug 14th, 2017 | Feb 21st, 2018 |
|---|---|---|
| Generation | Radeon Pro Mac (Vega Series) | Quadro Mobile (Px200) |
| Produktion | Active | End-of-life |
| Businterface | PCIe 3.0 x16 | MXM-B (3.0) |
Takt-Geschwindigkeiten
| Basis-Taktfrequenz | 1138 MHz | 1316 MHz |
|---|---|---|
| Boost-Takt | 1250 MHz | 1569 MHz |
| Speicher-Taktung | 786 MHz 1572 Mbps effective | 1804 MHz 7.2 Gbps effective |
Speicher
| Speichergröße | 8 GB | 16 GB |
|---|---|---|
| Speichertyp | HBM2 | GDDR5 |
| Speicherbus | 2048 bit | 256 bit |
| Bandbreite | 402.4 GB/s | 230.9 GB/s |
Render-Konfiguration
| Shading-Einheiten | 3584 | 2560 |
|---|---|---|
| TMUs | 224 | 160 |
| ROPs | 64 | 64 |
| Compute Units | 56 | — |
| Cache L1 | 16 KB (per CU) | 48 KB (per SM) |
| Cache L2 | 4 MB | 2 MB |
| Anzahl SM | — | 20 |
Theoretische Leistung
| Pixelrate | 80.00 GPixel/s | 100.4 GPixel/s |
|---|---|---|
| Texturrate | 280.0 GTexel/s | 251.0 GTexel/s |
| FP16 (half) Leistung | 17.92 TFLOPS (2:1) | 125.5 GFLOPS (1:64) |
| FP32 (float) Leistung | 8.960 TFLOPS | 8.033 TFLOPS |
| FP64 (double) Leistung | 560.0 GFLOPS (1:16) | 251.0 GFLOPS (1:32) |
Boarddesign
| Steckplatzbreite | IGP | MXM Module |
|---|---|---|
| TDP | 210 W | 100 W |
| Ausgabe | 1x HDMI3x DisplayPort | No outputs |
| Stromverbindung | None | None |
Grafik-Features
| DirectX | 12 (12_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.1 | 3.0 |
| Vulkan | 1.2 | 1.2 |
| Shader-Modell | 6.4 | 6.4 |
| CUDA | — | 6.1 |
