AMD Radeon Pro WX 4130 Mobile vs NVIDIA Quadro RTX 5000 Mobile Refresh
Grafikprozessor
| GPU Name | Baffin | TU104B |
|---|---|---|
| GPU Variante | Baffin LE | — |
| Architektur | GCN 4.0 | Turing |
| Hersteller | GlobalFoundries | TSMC |
| Prozessgröße | 14 nm | 12 nm |
| Transistoren | 3,000 million | 13,600 million |
| Chipgröße | 123 mm² | 545 mm² |
Mobile Grafik
| Veröffentlichungsdatum | Mar 1st, 2017 | Jun 8th, 2020 |
|---|---|---|
| Generation | Radeon Pro Mobile (WX x100) | Quadro Mobile (Tx000) |
| Produktion | Active | Active |
| Businterface | PCIe 3.0 x8 | PCIe 3.0 x16 |
Takt-Geschwindigkeiten
| Basis-Taktfrequenz | 1002 MHz | 1035 MHz |
|---|---|---|
| Boost-Takt | 1053 MHz | 1545 MHz |
| Speicher-Taktung | 1500 MHz 6 Gbps effective | 1750 MHz 14 Gbps effective |
Speicher
| Speichergröße | 4 GB | 16 GB |
|---|---|---|
| Speichertyp | GDDR5 | GDDR6 |
| Speicherbus | 128 bit | 256 bit |
| Bandbreite | 96.00 GB/s | 448.0 GB/s |
Render-Konfiguration
| Shading-Einheiten | 640 | 3072 |
|---|---|---|
| TMUs | 40 | 192 |
| ROPs | 16 | 64 |
| Compute Units | 10 | — |
| Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
| Cache L2 | 1024 KB | 4 MB |
| Anzahl SM | — | 48 |
| Tensor Cores | — | 384 |
| RT-Kerne | — | 48 |
Theoretische Leistung
| Pixelrate | 16.85 GPixel/s | 98.88 GPixel/s |
|---|---|---|
| Texturrate | 42.12 GTexel/s | 296.6 GTexel/s |
| FP16 (half) Leistung | 1,348 GFLOPS (1:1) | 18.98 TFLOPS (2:1) |
| FP32 (float) Leistung | 1,348 GFLOPS | 9.492 TFLOPS |
| FP64 (double) Leistung | 84.24 GFLOPS (1:16) | 296.6 GFLOPS (1:32) |
Boarddesign
| Steckplatzbreite | MXM Module | IGP |
|---|---|---|
| TDP | 50 W | 110 W |
| Ausgabe | No outputs | No outputs |
| Stromverbindung | None | None |
Grafik-Features
| 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 |
