Nom du GPU | NV18 | GM20B |
---|---|---|
Architecture | Celsius | Maxwell 2.0 |
Fonderie | TSMC | TSMC |
Taille du processus | 150 nm | 20 nm |
Transistors | 29 million | 2,000 million |
Taille des matrices | 65 mm² | 118 mm² |
GPU variant | — | TM660M-A2 |
Date de publication | Mar 1st, 2002 | — |
---|---|---|
Génération | GeForce4 Go | — |
Production | End-of-life | — |
Bus interface | AGP 8x | — |
Critiques | 2 in our database | — |
Prédécesseur | GeForce2 Go | — |
Successeur | GeForce FX Go 5 | — |
GPU clock | 200 MHz | — |
---|---|---|
Mémoire clock | 200 MHz 400 Mbps effective | System Shared |
Base clock | — | 640 MHz |
Boost clock | — | 921 MHz |
Taille de la mémoire | 64 MB | System Shared |
---|---|---|
Type de mémoire | DDR | System Shared |
Bus mémoire | 128 bit | System Shared |
Bande passante | 6.400 GB/s | System Dependent |
Pixel shaders | 2 | — |
---|---|---|
Vertex shaders | 0 | — |
TMUs | 4 | 16 |
ROPs | 2 | 16 |
Shading units | — | 128 |
Comptage SMM | — | 1 |
Cache L1 | — | 48 KB (per SMM) |
Cache L2 | — | 256 KB |
Taux de pixel | 400.0 MPixel/s | 14.74 GPixel/s |
---|---|---|
Taux de texture | 800.0 MTexel/s | 14.74 GTexel/s |
FP16 (half) performance | — | 471.6 GFLOPS (2:1) |
FP32 (float) performance | — | 235.8 GFLOPS |
FP64 (double) performance | — | 7.368 GFLOPS (1:32) |
TDP | unknown | 10 W |
---|---|---|
Sorties | No outputs | No outputs |
Taille Slot | — | IGP |
Longueur | — | 70 mm 2.8 inches |
Taille | — | 45 mm 1.8 inches |
DirectX | 7.0 | 12 (12_1) |
---|---|---|
OpenGL | 1.5 | 4.6 |
OpenCL | — | 1.2 |
Vulkan | — | 1.1 |
Pixel shader | 1.1 | — |
Vertex shader | 1.1 | — |
CUDA | — | 5.3 |
Shader model | — | 6.4 |
Date de publication | — | Mar 2019 |
---|---|---|
Génération | — | Tegra |
Production | — | End-of-life |
Bus interface | — | IGP |