Nom du GPU | Mars | GK208 |
---|---|---|
GPU variant | Mars LE | — |
Architecture | GCN 1.0 | Kepler 2.0 |
Fonderie | TSMC | TSMC |
Taille du processus | 28 nm | 28 nm |
Transistors | 950 million | 1,020 million |
Taille des matrices | 77 mm² | 87 mm² |
Date de publication | Apr 1st, 2013 | Jan 27th, 2014 |
---|---|---|
Génération | Solar System (HD 8700M) | GeForce 800M |
Production | End-of-life | End-of-life |
Bus interface | PCIe 3.0 x8 | PCIe 3.0 x8 |
Prédécesseur | London | GeForce 700M |
Successeur | Crystal System | GeForce 900M |
Base clock | 650 MHz | 850 MHz |
---|---|---|
Boost clock | 700 MHz | 941 MHz |
Mémoire clock | 900 MHz 1800 Mbps effective | 900 MHz 1800 Mbps effective |
Taille de la mémoire | 2 GB | 1024 MB |
---|---|---|
Type de mémoire | DDR3 | DDR3 |
Bus mémoire | 128 bit | 64 bit |
Bande passante | 28.80 GB/s | 14.40 GB/s |
Shading units | 384 | 384 |
---|---|---|
TMUs | 24 | 32 |
ROPs | 8 | 8 |
Compute units | 6 | — |
Cache L1 | 16 KB (per CU) | 16 KB (per SMX) |
Cache L2 | 256 KB | 512 KB |
Comptage SMX | — | 2 |
Taux de pixel | 5.600 GPixel/s | 7.528 GPixel/s |
---|---|---|
Taux de texture | 16.80 GTexel/s | 30.11 GTexel/s |
FP32 (float) performance | 537.6 GFLOPS | 722.7 GFLOPS |
FP64 (double) performance | 33.60 GFLOPS (1:16) | 30.11 GFLOPS (1:24) |
TDP | unknown | 33 W |
---|---|---|
Sorties | No outputs | No outputs |
Taille Slot | — | IGP |
Connecteurs de puissance | — | None |
DirectX | 12 (11_1) | 12 (11_0) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 1.2 | 3.0 |
Vulkan | 1.2 | 1.1 |
Shader model | 5.1 | 5.1 |
CUDA | — | 3.5 |