Nom du GPU | GK208B | GP107 |
---|---|---|
GPU variant | N16V-GM | — |
Architecture | Kepler 2.0 | Pascal |
Fonderie | TSMC | Samsung |
Taille du processus | 28 nm | 14 nm |
Transistors | 1,020 million | 3,300 million |
Taille des matrices | 87 mm² | 132 mm² |
Date de publication | Mar 13th, 2015 | Feb 23rd, 2019 |
---|---|---|
Génération | GeForce 900M | GeForce MX (1xx) |
Production | Active | End-of-life |
Bus interface | PCIe 3.0 x8 | PCIe 3.0 x4 |
Prédécesseur | GeForce 800M | — |
Successeur | GeForce 10 Mobile | — |
GPU clock | 954 MHz | — |
---|---|---|
Mémoire clock | 900 MHz 1800 Mbps effective | 1502 MHz 6 Gbps effective |
Base clock | — | 1469 MHz |
Boost clock | — | 1532 MHz |
Taille de la mémoire | 2 GB | 2 GB |
---|---|---|
Type de mémoire | DDR3 | GDDR5 |
Bus mémoire | 64 bit | 64 bit |
Bande passante | 14.40 GB/s | 48.06 GB/s |
Shading units | 384 | 384 |
---|---|---|
TMUs | 32 | 24 |
ROPs | 8 | 16 |
Comptage SMX | 2 | — |
Cache L1 | 16 KB (per SMX) | 48 KB (per SM) |
Cache L2 | 512 KB | 512 KB |
Comptage SM | — | 3 |
Taux de pixel | 7.632 GPixel/s | 24.51 GPixel/s |
---|---|---|
Taux de texture | 30.53 GTexel/s | 36.77 GTexel/s |
FP32 (float) performance | 732.7 GFLOPS | 1,177 GFLOPS |
FP64 (double) performance | 30.53 GFLOPS (1:24) | 36.77 GFLOPS (1:32) |
FP16 (half) performance | — | 18.38 GFLOPS (1:64) |
Taille Slot | IGP | IGP |
---|---|---|
TDP | 33 W | 25 W |
Sorties | No outputs | No outputs |
Connecteurs de puissance | — | None |
DirectX | 12 (11_0) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.1 | 1.2 |
CUDA | 3.5 | 6.1 |
Shader model | 5.1 | 6.4 |