Nom du GPU | GF100 | GP108 |
---|---|---|
GPU variant | N11E-GTX-A3 | — |
Architecture | Fermi | Pascal |
Fonderie | TSMC | Samsung |
Taille du processus | 40 nm | 14 nm |
Transistors | 3,100 million | 1,800 million |
Taille des matrices | 529 mm² | 74 mm² |
Date de publication | May 25th, 2010 | Jan 5th, 2018 |
---|---|---|
Génération | GeForce 400M | Quadro Mobile (Px000) |
Production | End-of-life | End-of-life |
Bus interface | MXM-B (3.0) | PCIe 3.0 x16 |
Critiques | 3 in our database | — |
Prédécesseur | GeForce 300M | — |
Successeur | GeForce 500M | — |
GPU clock | 425 MHz | — |
---|---|---|
Shader clock | 850 MHz | — |
Mémoire clock | 600 MHz 2.4 Gbps effective | 1253 MHz 5 Gbps effective |
Base clock | — | 1455 MHz |
Boost clock | — | 1518 MHz |
Taille de la mémoire | 2 GB | 2 GB |
---|---|---|
Type de mémoire | GDDR5 | GDDR5 |
Bus mémoire | 256 bit | 64 bit |
Bande passante | 76.80 GB/s | 40.10 GB/s |
Shading units | 352 | 256 |
---|---|---|
TMUs | 44 | 16 |
ROPs | 32 | 16 |
Comptage SM | 11 | 2 |
Cache L1 | 64 KB (per SM) | 48 KB (per SM) |
Cache L2 | 512 KB | 512 KB |
Taux de pixel | 9.350 GPixel/s | 24.29 GPixel/s |
---|---|---|
Taux de texture | 18.70 GTexel/s | 24.29 GTexel/s |
FP32 (float) performance | 598.4 GFLOPS | 777.2 GFLOPS |
FP64 (double) performance | 74.80 GFLOPS (1:8) | 24.29 GFLOPS (1:32) |
FP16 (half) performance | — | 12.14 GFLOPS (1:64) |
Taille Slot | MXM Module | — |
---|---|---|
TDP | 100 W | 18 W |
Sorties | No outputs | No outputs |
Connecteurs de puissance | None | None |
Board number | P1028 | — |
DirectX | 12 (11_0) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 1.1 | 3.0 |
Vulkan | — | 1.2 |
CUDA | 2.0 | 6.1 |
Shader model | 5.1 | 6.4 |