GPU Name | Polaris 20 | GP104 |
---|---|---|
GPU Variante | Polaris 20 | N17E-Q1-A1 |
Architektur | GCN 4.0 | Pascal |
Hersteller | GlobalFoundries | TSMC |
Prozessgröße | 14 nm | 16 nm |
Transistoren | 5,700 million | 7,200 million |
Chipgröße | 232 mm² | 314 mm² |
Veröffentlichungsdatum | Jun 5th, 2017 | Jan 11th, 2017 |
---|---|---|
Generation | Radeon Pro Mac (500 Series) | Quadro Mobile (Px000) |
Produktion | Active | End-of-life |
Businterface | PCIe 3.0 x16 | MXM-B (3.0) |
Basis-Taktfrequenz | 1000 MHz | 1088 MHz |
---|---|---|
Boost-Takt | 1105 MHz | 1215 MHz |
Speicher-Taktung | 1695 MHz 6.8 Gbps effective | 1753 MHz 7 Gbps effective |
Speichergröße | 4 GB | 6 GB |
---|---|---|
Speichertyp | GDDR5 | GDDR5 |
Speicherbus | 256 bit | 192 bit |
Bandbreite | 217.0 GB/s | 168.3 GB/s |
Shading-Einheiten | 1792 | 1280 |
---|---|---|
TMUs | 112 | 80 |
ROPs | 32 | 48 |
Compute Units | 28 | — |
Cache L1 | 16 KB (per CU) | 48 KB (per SM) |
Cache L2 | 2 MB | 1536 KB |
Anzahl SM | — | 10 |
Pixelrate | 35.36 GPixel/s | 58.32 GPixel/s |
---|---|---|
Texturrate | 123.8 GTexel/s | 97.20 GTexel/s |
FP16 (half) Leistung | 3.960 TFLOPS (1:1) | 48.60 GFLOPS (1:64) |
FP32 (float) Leistung | 3.960 TFLOPS | 3.110 TFLOPS |
FP64 (double) Leistung | 247.5 GFLOPS (1:16) | 97.20 GFLOPS (1:32) |
Steckplatzbreite | IGP | MXM Module |
---|---|---|
TDP | 150 W | 75 W |
Ausgabe | No outputs | No outputs |
Stromverbindung | None | None |
DirectX | 12 (12_0) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader-Modell | 6.4 | 6.4 |
CUDA | — | 6.1 |