Nom du GPU | NV40 | G86 |
---|---|---|
Architecture | Curie | Tesla |
Fonderie | TSMC | TSMC |
Taille du processus | 130 nm | 80 nm |
Transistors | 222 million | 210 million |
Taille des matrices | 287 mm² | 127 mm² |
GPU variant | — | G86-300-A2 |
Date de publication | Jul 21st, 2004 | Apr 17th, 2007 |
---|---|---|
Génération | GeForce 6 AGP | GeForce 8 |
Production | End-of-life | End-of-life |
Bus interface | AGP 8x | PCIe 1.0 x16 |
Critiques | 115 in our database | 33 in our database |
Prédécesseur | GeForce FX | GeForce 7 PCIe |
Successeur | GeForce 7 AGP | GeForce 9 |
Prix de lancement | — | 129 USD |
GPU clock | 300 MHz | 459 MHz |
---|---|---|
Mémoire clock | 350 MHz 700 Mbps effective | 400 MHz 800 Mbps effective |
Shader clock | — | 918 MHz |
Taille de la mémoire | 128 MB | 256 MB |
---|---|---|
Type de mémoire | DDR | GDDR3 |
Bus mémoire | 256 bit | 128 bit |
Bande passante | 22.40 GB/s | 12.80 GB/s |
Pixel shaders | 8 | — |
---|---|---|
Vertex shaders | 4 | — |
TMUs | 8 | 8 |
ROPs | 8 | 4 |
Shading units | — | 16 |
Comptage SM | — | 2 |
Cache L2 | — | 32 KB |
Taux de pixel | 2.400 GPixel/s | 1.836 GPixel/s |
---|---|---|
Vertex rate | 300.0 MVertices/s | — |
Taux de texture | 2.400 GTexel/s | 3.672 GTexel/s |
FP32 (float) performance | — | 29.38 GFLOPS |
Taille Slot | Single-slot | Single-slot |
---|---|---|
TDP | unknown | 30 W |
Suggestions pour le PSU | 200 W | 200 W |
Sorties | 1x DVI1x VGA1x S-Video | 1x DVI1x VGA1x S-Video |
Connecteurs de puissance | 1x Molex | None |
Board number | P212 | P403 |
Longueur | — | 229 mm 9 inches |
DirectX | 9.0c (9_3) | 11.1 (10_0) |
---|---|---|
OpenGL | 2.1 | 3.3 |
OpenCL | — | 1.1 |
Vulkan | — | — |
Shader model | 3.0 | 4.0 |
CUDA | — | 1.1 |