GPU Name | Raven | GM108 |
---|---|---|
Architektur | GCN 5.0 | Maxwell |
Hersteller | GlobalFoundries | TSMC |
Prozessgröße | 14 nm | 28 nm |
Transistoren | 4,940 million | unknown |
Chipgröße | 210 mm² | unknown |
GPU Variante | — | N16S-GTR-A1 |
Veröffentlichungsdatum | May 10th, 2018 | — |
---|---|---|
Generation | Raven Ridge (Vega) | — |
Produktion | Active | — |
Businterface | IGP | — |
Vorgänger | Great Horned Owl | — |
Nachfolger | Picasso | — |
Basis-Taktfrequenz | 300 MHz | 1109 MHz |
---|---|---|
Boost-Takt | 1280 MHz | 1189 MHz |
Speicher-Taktung | System Shared | 1253 MHz 5 Gbps effective |
Speichergröße | System Shared | 2 GB |
---|---|---|
Speichertyp | System Shared | GDDR5 |
Speicherbus | System Shared | 64 bit |
Bandbreite | System Dependent | 40.10 GB/s |
Shading-Einheiten | 384 | 384 |
---|---|---|
TMUs | 24 | 24 |
ROPs | 8 | 8 |
Compute Units | 6 | — |
Anzahl SMM | — | 3 |
Cache L1 | — | 64 KB (per SMM) |
Cache L2 | — | 1024 KB |
Pixelrate | 10.24 GPixel/s | 9.512 GPixel/s |
---|---|---|
Texturrate | 30.72 GTexel/s | 28.54 GTexel/s |
FP16 (half) Leistung | 1.966 TFLOPS (2:1) | — |
FP32 (float) Leistung | 983.0 GFLOPS | 913.2 GFLOPS |
FP64 (double) Leistung | 61.44 GFLOPS (1:16) | 28.54 GFLOPS (1:32) |
Steckplatzbreite | IGP | IGP |
---|---|---|
TDP | 15 W | 30 W |
Ausgabe | No outputs | No outputs |
Stromverbindung | — | None |
DirectX | 12 (12_1) | 12 (11_0) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.1 |
Shader-Modell | 6.4 | 5.1 |
CUDA | — | 5.0 |
Veröffentlichungsdatum | — | Nov 17th, 2017 |
---|---|---|
Generation | — | GeForce MX (1xx) |
Produktion | — | End-of-life |
Businterface | — | PCIe 3.0 x4 |