GPU Name | Vega 20 | TU102 |
---|---|---|
GPU Variante | Vega 20 XT | TU102-875-A1 |
Architektur | GCN 5.1 | Turing |
Hersteller | TSMC | TSMC |
Prozessgröße | 7 nm | 12 nm |
Transistoren | 13,230 million | 18,600 million |
Chipgröße | 331 mm² | 754 mm² |
Veröffentlichungsdatum | Jun 3rd, 2019 | Aug 13th, 2018 |
---|---|---|
Generation | Radeon Pro Mac | Quadro |
Produktion | Active | Active |
Businterface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Originalpreis | — | 6,299 USD |
Basis-Taktfrequenz | 1574 MHz | 1305 MHz |
---|---|---|
Boost-Takt | 1720 MHz | 1560 MHz |
Speicher-Taktung | 806 MHz 1612 Mbps effective | 1750 MHz 14 Gbps effective |
Speichergröße | 32 GB | 24 GB |
---|---|---|
Speichertyp | HBM2 | GDDR6 |
Speicherbus | 4096 bit | 384 bit |
Bandbreite | 825.3 GB/s | 672.0 GB/s |
Shading-Einheiten | 4096 | 4608 |
---|---|---|
TMUs | 256 | 288 |
ROPs | 64 | 96 |
Compute Units | 64 | — |
Cache L1 | 16 KB (per CU) | 64 KB (per SM) |
Cache L2 | 4 MB | 6 MB |
Anzahl SM | — | 72 |
Tensor Cores | — | 576 |
RT-Kerne | — | 72 |
Pixelrate | 110.1 GPixel/s | 149.8 GPixel/s |
---|---|---|
Texturrate | 440.3 GTexel/s | 449.3 GTexel/s |
FP16 (half) Leistung | 28.18 TFLOPS (2:1) | 28.75 TFLOPS (2:1) |
FP32 (float) Leistung | 14.09 TFLOPS | 14.38 TFLOPS |
FP64 (double) Leistung | 880.6 GFLOPS (1:16) | 449.3 GFLOPS (1:32) |
Steckplatzbreite | Quad-slot | Dual-slot |
---|---|---|
TDP | 475 W | 260 W |
Vorgeschlagenes Netzteil | 850 W | 600 W |
Ausgabe | 1x HDMI4x Thunderbolt | No outputs |
Stromverbindung | None | 1x 6-pin + 1x 8-pin |
Board-Nummer | MW672ZM/A | PG150 SKU 510 |
Länge | — | 267 mm 10.5 inches |
Breite | — | 111 mm 4.4 inches |
DirectX | 12 (12_1) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader-Modell | 6.4 | 6.6 |
CUDA | — | 7.5 |