GPU Name | Vega 10 | TU117 |
---|---|---|
GPU Variante | Vega 10 XT (215-0894200) | N18P-G62 |
Architektur | GCN 5.0 | Turing |
Hersteller | GlobalFoundries | TSMC |
Prozessgröße | 14 nm | 12 nm |
Transistoren | 12,500 million | 4,700 million |
Chipgröße | 495 mm² | 200 mm² |
Veröffentlichungsdatum | Mar 19th, 2019 | Apr 2nd, 2020 |
---|---|---|
Generation | Radeon Pro Mac (Vega Series) | GeForce 16 Mobile |
Produktion | Active | Active |
Businterface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Vorgänger | — | GeForce 10 Mobile |
Nachfolger | — | GeForce 20 Mobile |
Basis-Taktfrequenz | 1250 MHz | 1035 MHz |
---|---|---|
Boost-Takt | 1468 MHz | 1200 MHz |
Speicher-Taktung | 1000 MHz 2 Gbps effective | 1250 MHz 10 Gbps effective |
Speichergröße | 16 GB | 4 GB |
---|---|---|
Speichertyp | HBM2 | GDDR6 |
Speicherbus | 2048 bit | 128 bit |
Bandbreite | 512.0 GB/s | 160.0 GB/s |
Shading-Einheiten | 4096 | 1024 |
---|---|---|
TMUs | 256 | 64 |
ROPs | 64 | 32 |
Compute Units | 64 | — |
Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
Cache L2 | 4 MB | 1024 KB |
Anzahl SM | — | 16 |
Pixelrate | 93.95 GPixel/s | 38.40 GPixel/s |
---|---|---|
Texturrate | 375.8 GTexel/s | 76.80 GTexel/s |
FP16 (half) Leistung | 24.05 TFLOPS (2:1) | 4.915 TFLOPS (2:1) |
FP32 (float) Leistung | 12.03 TFLOPS | 2.458 TFLOPS |
FP64 (double) Leistung | 751.6 GFLOPS (1:16) | 76.80 GFLOPS (1:32) |
Steckplatzbreite | IGP | — |
---|---|---|
TDP | 250 W | 50 W |
Ausgabe | No outputs | No outputs |
Stromverbindung | None | None |
Board-Nummer | — | E4904 SKU 11 |
DirectX | 12 (12_1) | 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 |