GPU Name | Navi 21 | GA102 |
---|---|---|
Architektur | RDNA 2.0 | Ampere |
Hersteller | TSMC | Samsung |
Prozessgröße | 7 nm | 8 nm |
Transistoren | 26,800 million | 28,300 million |
Chipgröße | 520 mm² | 628 mm² |
GPU Variante | — | GA102-350-A1 |
Veröffentlichungsdatum | Unknown | Unknown |
---|---|---|
Generation | Radeon Pro | GeForce 30 |
Produktion | Active | Unreleased |
Originalpreis | 4,999 USD | 1,699 USD |
Businterface | PCIe 4.0 x16 | PCIe 4.0 x16 |
Reviews | 27 in our database | 55 in our database |
gpu.details.availability | — | 2022 |
Vorgänger | — | GeForce 20 |
Basis-Taktfrequenz | 2075 MHz | 1560 MHz |
---|---|---|
Boost-Takt | 2443 MHz | 1860 MHz |
Speicher-Taktung | 2000 MHz 16 Gbps effective | 1325 MHz 21.2 Gbps effective |
Speichergröße | 32 GB | 24 GB |
---|---|---|
Speichertyp | GDDR6 | GDDR6X |
Speicherbus | 256 bit | 384 bit |
Bandbreite | 512.0 GB/s | 1,018 GB/s |
Shading-Einheiten | 5120 | 10752 |
---|---|---|
TMUs | 320 | 336 |
ROPs | 128 | 112 |
Compute Units | 80 | — |
RT-Kerne | 80 | 84 |
gpu.details.l0-cache | 32 KB per WGP | — |
Cache L1 | 128 KB per Array | 128 KB (per SM) |
Cache L2 | 4 MB | 6 MB |
gpu.details.l3-cache | 128 MB | — |
Anzahl SM | — | 84 |
Tensor Cores | — | 336 |
Pixelrate | 312.7 GPixel/s | 208.3 GPixel/s |
---|---|---|
Texturrate | 781.8 GTexel/s | 625.0 GTexel/s |
FP16 (half) Leistung | 50.03 TFLOPS (2:1) | 40.00 TFLOPS (1:1) |
FP32 (float) Leistung | 25.02 TFLOPS | 40.00 TFLOPS |
FP64 (double) Leistung | 1.564 TFLOPS (1:16) | 625.0 GFLOPS (1:64) |
Steckplatzbreite | Dual-slot | Triple-slot |
---|---|---|
Länge | 267 mm 10.5 inches | 336 mm 13.2 inches |
Breite | 120 mm 4.7 inches | 140 mm 5.5 inches |
Höhe | 50 mm 2 inches | 61 mm 2.4 inches |
TDP | 450 W | 450 W |
Vorgeschlagenes Netzteil | 850 W | 850 W |
Ausgabe | 1x HDMI2x DisplayPort1x USB Type-C | 1x HDMI3x DisplayPort |
Stromverbindung | 2x 8-pin | 1x 12-pin |
Teile-Nummer | 102-D412 | — |
Board-Nummer | — | PG132 SKU |
DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 2.1 | 3.0 |
Vulkan | 1.2 | 1.2 |
Shader-Modell | 6.5 | 6.6 |
CUDA | — | 8.6 |