AMD Radeon Pro WX Vega M GL vs NVIDIA Quadro P3000 Mobile
Grafikprozessor
| GPU Name | Polaris 22 | GP104 |
|---|---|---|
| GPU Variante | VegaM MGL XL | N17E-Q1-A1 |
| Architektur | GCN 4.0 | Pascal |
| Hersteller | GlobalFoundries | TSMC |
| Prozessgröße | 14 nm | 16 nm |
| Transistoren | 5,000 million | 7,200 million |
| Chipgröße | 208 mm² | 314 mm² |
Mobile Grafik
| Veröffentlichungsdatum | Apr 24th, 2018 | Jan 11th, 2017 |
|---|---|---|
| Generation | Vega (Vega M) | Quadro Mobile (Px000) |
| Produktion | Active | End-of-life |
| Businterface | IGP | MXM-B (3.0) |
Takt-Geschwindigkeiten
| Basis-Taktfrequenz | 931 MHz | 1088 MHz |
|---|---|---|
| Boost-Takt | 1011 MHz | 1215 MHz |
| Speicher-Taktung | 700 MHz 1400 Mbps effective | 1753 MHz 7 Gbps effective |
Speicher
| Speichergröße | 4 GB | 6 GB |
|---|---|---|
| Speichertyp | HBM2 | GDDR5 |
| Speicherbus | 1024 bit | 192 bit |
| Bandbreite | 179.2 GB/s | 168.3 GB/s |
Render-Konfiguration
| Shading-Einheiten | 1280 | 1280 |
|---|---|---|
| TMUs | 80 | 80 |
| ROPs | 32 | 48 |
| Compute Units | 20 | — |
| Cache L1 | 16 KB (per CU) | 48 KB (per SM) |
| Cache L2 | 1024 KB | 1536 KB |
| Anzahl SM | — | 10 |
Theoretische Leistung
| Pixelrate | 32.35 GPixel/s | 58.32 GPixel/s |
|---|---|---|
| Texturrate | 80.88 GTexel/s | 97.20 GTexel/s |
| FP16 (half) Leistung | 2.588 TFLOPS (1:1) | 48.60 GFLOPS (1:64) |
| FP32 (float) Leistung | 2.588 TFLOPS | 3.110 TFLOPS |
| FP64 (double) Leistung | 161.8 GFLOPS (1:16) | 97.20 GFLOPS (1:32) |
Boarddesign
| Steckplatzbreite | IGP | MXM Module |
|---|---|---|
| TDP | 65 W | 75 W |
| Ausgabe | No outputs | No outputs |
| Board-Nummer | D136 | — |
| Stromverbindung | — | None |
Grafik-Features
| DirectX | 12 (12_0) | 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 |
