GPU Name | GM108 | GP107 |
---|---|---|
GPU Variante | N16S-GTR-A1 | — |
Architektur | Maxwell | Pascal |
Hersteller | TSMC | Samsung |
Prozessgröße | 28 nm | 14 nm |
Transistoren | unknown | 3,300 million |
Chipgröße | unknown | 132 mm² |
Veröffentlichungsdatum | Nov 17th, 2017 | Feb 7th, 2017 |
---|---|---|
Generation | GeForce MX (1xx) | Quadro Mobile (Px000) |
Produktion | End-of-life | End-of-life |
Businterface | PCIe 3.0 x4 | PCIe 3.0 x16 |
Basis-Taktfrequenz | 1109 MHz | 1430 MHz |
---|---|---|
Boost-Takt | 1189 MHz | 1557 MHz |
Speicher-Taktung | 1253 MHz 5 Gbps effective | 1253 MHz 5 Gbps effective |
Speichergröße | 2 GB | 4 GB |
---|---|---|
Speichertyp | GDDR5 | GDDR5 |
Speicherbus | 64 bit | 128 bit |
Bandbreite | 40.10 GB/s | 80.19 GB/s |
Shading-Einheiten | 384 | 384 |
---|---|---|
TMUs | 24 | 24 |
ROPs | 8 | 16 |
Anzahl SMM | 3 | — |
Cache L1 | 64 KB (per SMM) | 48 KB (per SM) |
Cache L2 | 1024 KB | 1024 KB |
Anzahl SM | — | 3 |
Pixelrate | 9.512 GPixel/s | 24.91 GPixel/s |
---|---|---|
Texturrate | 28.54 GTexel/s | 37.37 GTexel/s |
FP32 (float) Leistung | 913.2 GFLOPS | 1,196 GFLOPS |
FP64 (double) Leistung | 28.54 GFLOPS (1:32) | 37.37 GFLOPS (1:32) |
FP16 (half) Leistung | — | 18.68 GFLOPS (1:64) |
Steckplatzbreite | IGP | — |
---|---|---|
TDP | 30 W | 25 W |
Ausgabe | No outputs | No outputs |
Stromverbindung | None | None |
DirectX | 12 (11_0) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.1 | 1.2 |
CUDA | 5.0 | 6.1 |
Shader-Modell | 5.1 | 6.4 |