Nom du GPU | GF108 | GM20B |
---|---|---|
GPU variant | GF108-400-A1 | TM670D-A1 |
Architecture | Fermi | Maxwell 2.0 |
Fonderie | TSMC | TSMC |
Taille du processus | 40 nm | 20 nm |
Transistors | 585 million | 2,000 million |
Taille des matrices | 116 mm² | 118 mm² |
Date de publication | Feb 9th, 2011 | — |
---|---|---|
Génération | GeForce 400 | — |
Production | End-of-life | — |
Bus interface | PCIe 1.0 x16 | — |
Critiques | 5 in our database | — |
Prédécesseur | GeForce 200 | — |
Successeur | GeForce 500 | — |
GPU clock | 810 MHz | 1000 MHz |
---|---|---|
Shader clock | 1620 MHz | — |
Mémoire clock | 667 MHz 1334 Mbps effective | System Shared |
Taille de la mémoire | 1024 MB | System Shared |
---|---|---|
Type de mémoire | DDR3 | System Shared |
Bus mémoire | 128 bit | System Shared |
Bande passante | 21.34 GB/s | System Dependent |
Shading units | 96 | 256 |
---|---|---|
TMUs | 16 | 16 |
ROPs | 4 | 16 |
Comptage SM | 2 | — |
Cache L1 | 64 KB (per SM) | 48 KB (per SMM) |
Cache L2 | 256 KB | 256 KB |
Comptage SMM | — | 2 |
Taux de pixel | 3.240 GPixel/s | 16.00 GPixel/s |
---|---|---|
Taux de texture | 12.96 GTexel/s | 16.00 GTexel/s |
FP32 (float) performance | 311.0 GFLOPS | 512.0 GFLOPS |
FP64 (double) performance | 25.92 GFLOPS (1:12) | 16.00 GFLOPS (1:32) |
FP16 (half) performance | — | 1,024 GFLOPS (2:1) |
Taille Slot | Single-slot | IGP |
---|---|---|
Longueur | 145 mm 5.7 inches | — |
TDP | 65 W | 15 W |
Suggestions pour le PSU | 250 W | — |
Sorties | 1x DVI1x HDMI1x VGA | No outputs |
Connecteurs de puissance | None | — |
Board number | P1071 | — |
DirectX | 12 (11_0) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 1.1 | 1.2 |
Vulkan | — | 1.1 |
CUDA | 2.1 | 5.3 |
Shader model | 5.1 | 6.4 |
Date de publication | — | Jan 4th, 2015 |
---|---|---|
Génération | — | Tegra |
Production | — | End-of-life |
Bus interface | — | IGP |