GPU Name | Polaris 20 | TU116 |
---|---|---|
GPU Variante | Polaris 20M XT | N18P-G61 |
Architektur | GCN 4.0 | Turing |
Hersteller | GlobalFoundries | TSMC |
Prozessgröße | 14 nm | 12 nm |
Transistoren | 5,700 million | 6,600 million |
Chipgröße | 232 mm² | 284 mm² |
Veröffentlichungsdatum | Apr 11th, 2018 | Apr 23rd, 2020 |
---|---|---|
Generation | Mobility Radeon (RX M500X) | GeForce 16 Mobile |
Produktion | Active | Active |
Businterface | MXM-B (3.0) | PCIe 3.0 x16 |
Vorgänger | Crystal System | GeForce 10 Mobile |
Nachfolger | — | GeForce 20 Mobile |
Basis-Taktfrequenz | 1000 MHz | 1350 MHz |
---|---|---|
Boost-Takt | 1077 MHz | 1485 MHz |
Speicher-Taktung | 2000 MHz 8 Gbps effective | 1500 MHz 12 Gbps effective |
Speichergröße | 8 GB | 4 GB |
---|---|---|
Speichertyp | GDDR5 | GDDR6 |
Speicherbus | 256 bit | 128 bit |
Bandbreite | 256.0 GB/s | 192.0 GB/s |
Shading-Einheiten | 2304 | 1024 |
---|---|---|
TMUs | 144 | 64 |
ROPs | 32 | 32 |
Compute Units | 36 | — |
Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
Cache L2 | 2 MB | 1024 KB |
Anzahl SM | — | 16 |
Pixelrate | 34.46 GPixel/s | 47.52 GPixel/s |
---|---|---|
Texturrate | 155.1 GTexel/s | 95.04 GTexel/s |
FP16 (half) Leistung | 4.963 TFLOPS (1:1) | 6.083 TFLOPS (2:1) |
FP32 (float) Leistung | 4.963 TFLOPS | 3.041 TFLOPS |
FP64 (double) Leistung | 310.2 GFLOPS (1:16) | 95.04 GFLOPS (1:32) |
Steckplatzbreite | MXM Module | — |
---|---|---|
TDP | 100 W | 50 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 | 6.6 |
CUDA | — | 7.5 |