NVIDIA GeForce4 MX + nForce2 vs NVIDIA Jetson Xavier NX GPU
Processeur graphique
| Nom du GPU | Crush17 | GV10B |
|---|---|---|
| Architecture | Celsius | Volta |
| Taille du processus | 150 nm | 12 nm |
| Transistors | 29 million | 9,000 million |
| Taille des matrices | 65 mm² | 350 mm² |
| Fonderie | — | TSMC |
Carte graphique intégré
| Date de publication | Oct 1st, 2002 | May 14th, 2020 |
|---|---|---|
| Génération | GeForce 4 MX IGP | Tegra |
| Production | End-of-life | End-of-life |
| Bus interface | AGP 4x | IGP |
| Prédécesseur | GeForce 2 MX IGP | — |
| Successeur | GeForce 6 IGP | — |
| Prix de lancement | — | 399 USD |
Vitesse clock
| GPU clock | 200 MHz | — |
|---|---|---|
| Mémoire clock | System Shared | System Shared |
| Base clock | — | 854 MHz |
| Boost clock | — | 1377 MHz |
Mémoire
| Taille de la mémoire | System Shared | System Shared |
|---|---|---|
| Type de mémoire | System Shared | System Shared |
| Bus mémoire | System Shared | System Shared |
| Bande passante | System Dependent | System Dependent |
Render Config
| Pixel shaders | 2 | — |
|---|---|---|
| Vertex shaders | 0 | — |
| TMUs | 4 | 24 |
| ROPs | 2 | 16 |
| Shading units | — | 384 |
| Comptage SM | — | 6 |
| Tensor cores | — | 48 |
| Cache L1 | — | 128 KB (per SM) |
| Cache L2 | — | 256 KB |
Performance théorique
| Taux de pixel | 400.0 MPixel/s | 22.03 GPixel/s |
|---|---|---|
| Taux de texture | 800.0 MTexel/s | 33.05 GTexel/s |
| FP16 (half) performance | — | 2.115 TFLOPS (2:1) |
| FP32 (float) performance | — | 1,058 GFLOPS |
| FP64 (double) performance | — | 528.8 GFLOPS (1:2) |
Board Design
| Taille Slot | IGP | IGP |
|---|---|---|
| TDP | unknown | 15 W |
| Sorties | No outputs | No outputs |
| Longueur | — | 70 mm 2.8 inches |
| Taille | — | 45 mm 1.8 inches |
Caractéristiques graphiques
| DirectX | 8.0 | 12 (12_1) |
|---|---|---|
| OpenGL | 1.3 | 4.6 |
| OpenCL | — | 1.2 |
| Vulkan | — | 1.2 |
| Pixel shader | 1.1 | — |
| Vertex shader | 1.1 | — |
| CUDA | — | 7.2 |
| Shader model | — | 6.4 |
