Nom du GPU | G92B | GF116 |
---|---|---|
GPU variant | G92-426-B1 | GF116-400-A1 |
Architecture | Tesla | Fermi 2.0 |
Fonderie | TSMC | TSMC |
Taille du processus | 55 nm | 40 nm |
Transistors | 754 million | 1,170 million |
Taille des matrices | 260 mm² | 238 mm² |
Date de publication | Mar 4th, 2009 | Mar 15th, 2011 |
---|---|---|
Génération | GeForce 200 | GeForce 500 |
Production | End-of-life | End-of-life |
Prix de lancement | 199 USD | 149 USD |
Bus interface | PCIe 2.0 x16 | PCIe 2.0 x16 |
Critiques | 58 in our database | 62 in our database |
Prédécesseur | GeForce 9 | GeForce 400 |
Successeur | GeForce 400 | GeForce 600 |
GPU clock | 675 MHz | 900 MHz |
---|---|---|
Shader clock | 1620 MHz | 1800 MHz |
Mémoire clock | 1008 MHz 2 Gbps effective | 1026 MHz 4.1 Gbps effective |
Taille de la mémoire | 1024 MB | 1024 MB |
---|---|---|
Type de mémoire | GDDR3 | GDDR5 |
Bus mémoire | 256 bit | 192 bit |
Bande passante | 64.51 GB/s | 98.50 GB/s |
Shading units | 128 | 192 |
---|---|---|
TMUs | 64 | 32 |
ROPs | 16 | 24 |
Comptage SM | 16 | 4 |
Cache L2 | 64 KB | 384 KB |
Cache L1 | — | 64 KB (per SM) |
Taux de pixel | 10.80 GPixel/s | 7.200 GPixel/s |
---|---|---|
Taux de texture | 43.20 GTexel/s | 28.80 GTexel/s |
FP32 (float) performance | 414.7 GFLOPS | 691.2 GFLOPS |
FP64 (double) performance | — | 57.60 GFLOPS (1:12) |
Taille Slot | Dual-slot | Dual-slot |
---|---|---|
Longueur | 229 mm 9 inches | 210 mm 8.3 inches |
TDP | 150 W | 116 W |
Suggestions pour le PSU | 450 W | 300 W |
Sorties | 2x DVI | 2x DVI1x mini-HDMI |
Connecteurs de puissance | 1x 6-pin | 1x 6-pin |
Board number | P365 | P1050 |
DirectX | 11.1 (10_0) | 12 (11_0) |
---|---|---|
OpenGL | 3.3 | 4.6 |
OpenCL | 1.1 | 1.1 |
Vulkan | — | — |
CUDA | 1.1 | 2.1 |
Shader model | 4.0 | 5.1 |