Nom du GPU | M98 | GK208B |
---|---|---|
Architecture | TeraScale | Kepler 2.0 |
Fonderie | TSMC | TSMC |
Taille du processus | 55 nm | 28 nm |
Transistors | 956 million | 1,020 million |
Taille des matrices | 256 mm² | 87 mm² |
GPU variant | — | N16V-GM |
Date de publication | Aug 28th, 2009 | Mar 13th, 2015 |
---|---|---|
Génération | M9x (Mobility HD 4800) | GeForce 900A |
Production | End-of-life | Active |
Bus interface | PCIe 2.0 x16 | PCIe 3.0 x8 |
Critiques | 2 in our database | — |
Prédécesseur | M8x | GeForce 800A |
Successeur | Manhattan | — |
GPU clock | 503 MHz | 954 MHz |
---|---|---|
Mémoire clock | 850 MHz 1700 Mbps effective | 1001 MHz 2 Gbps effective |
Taille de la mémoire | 512 MB | 2 GB |
---|---|---|
Type de mémoire | GDDR3 | DDR3 |
Bus mémoire | 256 bit | 64 bit |
Bande passante | 54.40 GB/s | 16.02 GB/s |
Shading units | 800 | 384 |
---|---|---|
TMUs | 40 | 32 |
ROPs | 16 | 8 |
Compute units | 10 | — |
Cache L1 | 16 KB (per CU) | 16 KB (per SMX) |
Cache L2 | 256 KB | 512 KB |
Comptage SMX | — | 2 |
Taux de pixel | 8.048 GPixel/s | 7.632 GPixel/s |
---|---|---|
Taux de texture | 20.12 GTexel/s | 30.53 GTexel/s |
FP32 (float) performance | 804.8 GFLOPS | 732.7 GFLOPS |
FP64 (double) performance | 161.0 GFLOPS (1:5) | 30.53 GFLOPS (1:24) |
TDP | unknown | 33 W |
---|---|---|
Sorties | No outputs | No outputs |
Taille Slot | — | IGP |
DirectX | 10.1 (10_1) | 12 (11_0) |
---|---|---|
OpenGL | 3.3 | 4.6 |
OpenCL | 1.1 | 3.0 |
Vulkan | — | 1.1 |
Shader model | 4.1 | 5.1 |
CUDA | — | 3.5 |