Nom du GPU | GF108 | G80 |
---|---|---|
Architecture | Fermi | Tesla |
Fonderie | TSMC | TSMC |
Taille du processus | 40 nm | 90 nm |
Transistors | 585 million | 681 million |
Taille des matrices | 116 mm² | 484 mm² |
GPU variant | — | G80-875-A2 |
Date de publication | Dec 13th, 2010 | Mar 5th, 2007 |
---|---|---|
Génération | Quadro | Quadro FX |
Production | End-of-life | End-of-life |
Prix de lancement | 179 USD | 2,999 USD |
Bus interface | PCIe 2.0 x16 | PCIe 1.0 x16 |
Critiques | 26 in our database | 26 in our database |
GPU clock | 640 MHz | 600 MHz |
---|---|---|
Shader clock | 1280 MHz | 1350 MHz |
Mémoire clock | 800 MHz 1600 Mbps effective | 800 MHz 1600 Mbps effective |
Taille de la mémoire | 1024 MB | 1536 MB |
---|---|---|
Type de mémoire | DDR3 | GDDR3 |
Bus mémoire | 128 bit | 384 bit |
Bande passante | 25.60 GB/s | 76.80 GB/s |
Shading units | 96 | 128 |
---|---|---|
TMUs | 16 | 32 |
ROPs | 8 | 24 |
Comptage SM | 2 | 16 |
Cache L1 | 64 KB (per SM) | — |
Cache L2 | 256 KB | 96 KB |
Taux de pixel | 2.560 GPixel/s | 14.40 GPixel/s |
---|---|---|
Taux de texture | 10.24 GTexel/s | 38.40 GTexel/s |
FP32 (float) performance | 245.8 GFLOPS | 345.6 GFLOPS |
FP64 (double) performance | 20.48 GFLOPS (1:12) | — |
Taille Slot | Single-slot | Dual-slot |
---|---|---|
Longueur | 168 mm 6.6 inches | 254 mm 10 inches |
Taille | 69 mm 2.7 inches | 111 mm 4.4 inches |
TDP | 40 W | 171 W |
Suggestions pour le PSU | 200 W | 450 W |
Sorties | 1x DVI1x DisplayPort | 2x DVI1x S-Video |
Connecteurs de puissance | None | 2x 6-pin |
Board number | P1033 | P357 |
DirectX | 12 (11_0) | 11.1 (10_0) |
---|---|---|
OpenGL | 4.6 | 3.3 |
OpenCL | 1.1 | 1.1 (1.0) |
Vulkan | — | — |
CUDA | 2.1 | 1.0 |
Shader model | 5.1 | 4.0 |