Nom du GPU | GK107 | GF119 |
---|---|---|
Architecture | Kepler | Fermi 2.0 |
Fonderie | TSMC | TSMC |
Taille du processus | 28 nm | 40 nm |
Transistors | 1,270 million | 292 million |
Taille des matrices | 118 mm² | 79 mm² |
GPU variant | — | GF119-825-A1 |
Date de publication | Jul 2nd, 2014 | Mar 10th, 2013 |
---|---|---|
Génération | GRID | NVS |
Production | End-of-life | End-of-life |
Prix de lancement | 125 USD | 159 USD |
Bus interface | PCIe 3.0 x16 | PCIe 2.0 x16 |
Critiques | — | 26 in our database |
GPU clock | 850 MHz | 523 MHz |
---|---|---|
Mémoire clock | 891 MHz 1782 Mbps effective | 875 MHz 1750 Mbps effective |
Shader clock | — | 1046 MHz |
Taille de la mémoire | 512 MB | 1024 MB |
---|---|---|
Type de mémoire | DDR3 | DDR3 |
Bus mémoire | 128 bit | 64 bit |
Bande passante | 28.51 GB/s | 14.00 GB/s |
Shading units | 192 | 48 |
---|---|---|
TMUs | 16 | 8 |
ROPs | 16 | 4 |
Comptage SMX | 1 | — |
Cache L1 | 16 KB (per SMX) | 64 KB (per SM) |
Cache L2 | 256 KB | 128 KB |
Comptage SM | — | 1 |
Taux de pixel | 3.400 GPixel/s | 1.046 GPixel/s |
---|---|---|
Taux de texture | 13.60 GTexel/s | 4.184 GTexel/s |
FP32 (float) performance | 326.4 GFLOPS | 100.4 GFLOPS |
FP64 (double) performance | 13.60 GFLOPS (1:24) | 8.368 GFLOPS (1:12) |
Taille Slot | IGP | Single-slot |
---|---|---|
TDP | 130 W | 19 W |
Suggestions pour le PSU | 300 W | 200 W |
Sorties | No outputs | 1x DMS-59 |
Longueur | — | 145 mm 5.7 inches |
Connecteurs de puissance | — | None |
DirectX | 12 (11_0) | 12 (11_0) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 1.1 |
Vulkan | 1.1 | — |
CUDA | 3.0 | 2.1 |
Shader model | 5.1 | 5.1 |