Intel UHD Graphics P630 vs NVIDIA Jetson Xavier NX GPU
Grafikprozessor
| GPU Name | Coffee Lake GT2 | GV10B |
|---|---|---|
| Architektur | Generation 9.5 | Volta |
| Hersteller | Intel | TSMC |
| Prozessgröße | 14 nm+++ | 12 nm |
| Transistoren | unknown | 9,000 million |
| Chipgröße | unknown | 350 mm² |
Integrierter Grafikprozessor
| Veröffentlichungsdatum | May 24th, 2018 | May 14th, 2020 |
|---|---|---|
| Generation | HD Graphics-W (Coffee Lake) | Tegra |
| Produktion | Active | End-of-life |
| Businterface | Ring Bus | IGP |
| Reviews | 1 in our database | — |
| Originalpreis | — | 399 USD |
Takt-Geschwindigkeiten
| Basis-Taktfrequenz | 350 MHz | 854 MHz |
|---|---|---|
| Boost-Takt | 1100 MHz | 1377 MHz |
| Speicher-Taktung | System Shared | System Shared |
Speicher
| Speichergröße | System Shared | System Shared |
|---|---|---|
| Speichertyp | System Shared | System Shared |
| Speicherbus | System Shared | System Shared |
| Bandbreite | System Dependent | System Dependent |
Render-Konfiguration
| Shading-Einheiten | 192 | 384 |
|---|---|---|
| TMUs | 24 | 24 |
| ROPs | 3 | 16 |
| Execution Units | 24 | — |
| Anzahl SM | — | 6 |
| Tensor Cores | — | 48 |
| Cache L1 | — | 128 KB (per SM) |
| Cache L2 | — | 256 KB |
Theoretische Leistung
| Pixelrate | 3.300 GPixel/s | 22.03 GPixel/s |
|---|---|---|
| Texturrate | 26.40 GTexel/s | 33.05 GTexel/s |
| FP16 (half) Leistung | 844.8 GFLOPS (2:1) | 2.115 TFLOPS (2:1) |
| FP32 (float) Leistung | 422.4 GFLOPS | 1,058 GFLOPS |
| FP64 (double) Leistung | 105.6 GFLOPS (1:4) | 528.8 GFLOPS (1:2) |
Boarddesign
| Steckplatzbreite | IGP | IGP |
|---|---|---|
| TDP | 15 W | 15 W |
| Ausgabe | No outputs | No outputs |
| Länge | — | 70 mm 2.8 inches |
| Breite | — | 45 mm 1.8 inches |
Grafik-Features
| DirectX | 12 (12_1) | 12 (12_1) |
|---|---|---|
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 1.2 |
| Vulkan | 1.2 | 1.2 |
| Shader-Modell | 6.4 | 6.4 |
| CUDA | — | 7.2 |
