GPU Name | Polaris 22 | TU117 |
---|---|---|
GPU Variante | VegaM XT (C7398773) | — |
Architektur | GCN 4.0 | Turing |
Hersteller | GlobalFoundries | TSMC |
Prozessgröße | 14 nm | 12 nm |
Transistoren | 5,000 million | 4,700 million |
Chipgröße | 208 mm² | 200 mm² |
Veröffentlichungsdatum | Feb 1st, 2018 | May 27th, 2019 |
---|---|---|
Generation | Vega (Vega M) | Quadro Mobile (Tx000) |
Produktion | Active | Active |
Businterface | IGP | PCIe 3.0 x16 |
Basis-Taktfrequenz | 1063 MHz | 1395 MHz |
---|---|---|
Boost-Takt | 1190 MHz | 1455 MHz |
Speicher-Taktung | 800 MHz 1600 Mbps effective | 2001 MHz 8 Gbps effective |
Speichergröße | 4 GB | 4 GB |
---|---|---|
Speichertyp | HBM2 | GDDR5 |
Speicherbus | 1024 bit | 128 bit |
Bandbreite | 204.8 GB/s | 128.1 GB/s |
Shading-Einheiten | 1536 | 896 |
---|---|---|
TMUs | 96 | 56 |
ROPs | 64 | 32 |
Compute Units | 24 | — |
Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
Cache L2 | 1024 KB | 1024 KB |
Anzahl SM | — | 14 |
Pixelrate | 76.16 GPixel/s | 46.56 GPixel/s |
---|---|---|
Texturrate | 114.2 GTexel/s | 81.48 GTexel/s |
FP16 (half) Leistung | 3.656 TFLOPS (1:1) | 5.215 TFLOPS (2:1) |
FP32 (float) Leistung | 3.656 TFLOPS | 2.607 TFLOPS |
FP64 (double) Leistung | 228.5 GFLOPS (1:16) | 81.48 GFLOPS (1:32) |
Steckplatzbreite | IGP | IGP |
---|---|---|
TDP | 100 W | 50 W |
Ausgabe | No outputs | No outputs |
Stromverbindung | — | 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 |