NVIDIA GeForce4 MX + nForce2 vs NVIDIA Jetson Xavier NX GPU
Grafikprozessor
| GPU Name | Crush17 | GV10B |
|---|---|---|
| Architektur | Celsius | Volta |
| Prozessgröße | 150 nm | 12 nm |
| Transistoren | 29 million | 9,000 million |
| Chipgröße | 65 mm² | 350 mm² |
| Hersteller | — | TSMC |
Integrierter Grafikprozessor
| Veröffentlichungsdatum | Oct 1st, 2002 | May 14th, 2020 |
|---|---|---|
| Generation | GeForce 4 MX IGP | Tegra |
| Produktion | End-of-life | End-of-life |
| Businterface | AGP 4x | IGP |
| Vorgänger | GeForce 2 MX IGP | — |
| Nachfolger | GeForce 6 IGP | — |
| Originalpreis | — | 399 USD |
Takt-Geschwindigkeiten
| GPU-Taktung | 200 MHz | — |
|---|---|---|
| Speicher-Taktung | System Shared | System Shared |
| Basis-Taktfrequenz | — | 854 MHz |
| Boost-Takt | — | 1377 MHz |
Speicher
| Speichergröße | System Shared | System Shared |
|---|---|---|
| Speichertyp | System Shared | System Shared |
| Speicherbus | System Shared | System Shared |
| Bandbreite | System Dependent | System Dependent |
Render-Konfiguration
| Pixelshader | 2 | — |
|---|---|---|
| Vertex-Shader | 0 | — |
| TMUs | 4 | 24 |
| ROPs | 2 | 16 |
| Shading-Einheiten | — | 384 |
| Anzahl SM | — | 6 |
| Tensor Cores | — | 48 |
| Cache L1 | — | 128 KB (per SM) |
| Cache L2 | — | 256 KB |
Theoretische Leistung
| Pixelrate | 400.0 MPixel/s | 22.03 GPixel/s |
|---|---|---|
| Texturrate | 800.0 MTexel/s | 33.05 GTexel/s |
| FP16 (half) Leistung | — | 2.115 TFLOPS (2:1) |
| FP32 (float) Leistung | — | 1,058 GFLOPS |
| FP64 (double) Leistung | — | 528.8 GFLOPS (1:2) |
Boarddesign
| Steckplatzbreite | IGP | IGP |
|---|---|---|
| TDP | unknown | 15 W |
| Ausgabe | No outputs | No outputs |
| Länge | — | 70 mm 2.8 inches |
| Breite | — | 45 mm 1.8 inches |
Grafik-Features
| DirectX | 8.0 | 12 (12_1) |
|---|---|---|
| OpenGL | 1.3 | 4.6 |
| OpenCL | — | 1.2 |
| Vulkan | — | 1.2 |
| Pixelshader | 1.1 | — |
| Vertex-Shader | 1.1 | — |
| CUDA | — | 7.2 |
| Shader-Modell | — | 6.4 |
