GPU Name | M98 | GM108 |
---|---|---|
Architektur | TeraScale | Maxwell |
Hersteller | TSMC | TSMC |
Prozessgröße | 55 nm | 28 nm |
Transistoren | 956 million | unknown |
Chipgröße | 256 mm² | unknown |
GPU Variante | — | N15M-Q3 |
Veröffentlichungsdatum | Jan 9th, 2009 | Apr 27th, 2016 |
---|---|---|
Generation | M9x (Mobility HD 4800) | Quadro Mobile (Mx000M) |
Produktion | End-of-life | End-of-life |
Businterface | PCIe 2.0 x16 | MXM-A (3.0) |
Reviews | 2 in our database | 26 in our database |
Vorgänger | M8x | — |
Nachfolger | Manhattan | — |
GPU-Taktung | 500 MHz | — |
---|---|---|
Speicher-Taktung | 700 MHz 2.8 Gbps effective | 900 MHz 1800 Mbps effective |
Basis-Taktfrequenz | — | 1029 MHz |
Boost-Takt | — | 1124 MHz |
Speichergröße | 1024 MB | 2 GB |
---|---|---|
Speichertyp | GDDR5 | DDR3 |
Speicherbus | 256 bit | 64 bit |
Bandbreite | 89.60 GB/s | 14.40 GB/s |
Shading-Einheiten | 800 | 384 |
---|---|---|
TMUs | 40 | 16 |
ROPs | 16 | 8 |
Compute Units | 10 | — |
Cache L1 | 16 KB (per CU) | 64 KB (per SMM) |
Cache L2 | 256 KB | 1024 KB |
Anzahl SMM | — | 2 |
Pixelrate | 8.000 GPixel/s | 8.992 GPixel/s |
---|---|---|
Texturrate | 20.00 GTexel/s | 17.98 GTexel/s |
FP32 (float) Leistung | 800.0 GFLOPS | 863.2 GFLOPS |
FP64 (double) Leistung | 160.0 GFLOPS (1:5) | 26.98 GFLOPS (1:32) |
TDP | unknown | 30 W |
---|---|---|
Ausgabe | No outputs | No outputs |
Steckplatzbreite | — | MXM Module |
Stromverbindung | — | None |
DirectX | 10.1 (10_1) | 12 (11_0) |
---|---|---|
OpenGL | 3.3 | 4.6 |
OpenCL | 1.1 | 3.0 |
Vulkan | — | 1.1 |
Shader-Modell | 4.1 | 5.1 |
CUDA | — | 5.0 |