GPU Name | GA106 | TU104 |
---|---|---|
GPU Variante | GA106-300-A1 | TU104-875-A1 |
Architektur | Ampere | Turing |
Hersteller | Samsung | TSMC |
Prozessgröße | 8 nm | 12 nm |
Transistoren | 13,250 million | 13,600 million |
Chipgröße | 276 mm² | 545 mm² |
Veröffentlichungsdatum | Jan 12th, 2021 | Aug 13th, 2018 |
---|---|---|
gpu.details.availability | Feb 25th, 2021 | — |
Generation | GeForce 30 | Quadro |
Vorgänger | GeForce 20 | — |
Produktion | Active | Active |
Originalpreis | 329 USD | 2,299 USD |
Businterface | PCIe 4.0 x16 | PCIe 3.0 x16 |
Reviews | 60 in our database | — |
Basis-Taktfrequenz | 1320 MHz | 1620 MHz |
---|---|---|
Boost-Takt | 1777 MHz | 1815 MHz |
Speicher-Taktung | 1875 MHz 15 Gbps effective | 1750 MHz 14 Gbps effective |
Speichergröße | 12 GB | 16 GB |
---|---|---|
Speichertyp | GDDR6 | GDDR6 |
Speicherbus | 192 bit | 256 bit |
Bandbreite | 360.0 GB/s | 448.0 GB/s |
Shading-Einheiten | 3584 | 3072 |
---|---|---|
TMUs | 112 | 192 |
ROPs | 48 | 64 |
Anzahl SM | 28 | 48 |
Tensor Cores | 112 | 384 |
RT-Kerne | 28 | 48 |
Cache L1 | 128 KB (per SM) | 64 KB (per SM) |
Cache L2 | 3 MB | 4 MB |
Pixelrate | 85.30 GPixel/s | 116.2 GPixel/s |
---|---|---|
Texturrate | 199.0 GTexel/s | 348.5 GTexel/s |
FP16 (half) Leistung | 12.74 TFLOPS (1:1) | 22.30 TFLOPS (2:1) |
FP32 (float) Leistung | 12.74 TFLOPS | 11.15 TFLOPS |
FP64 (double) Leistung | 199.0 GFLOPS (1:64) | 348.5 GFLOPS (1:32) |
Steckplatzbreite | Dual-slot | Dual-slot |
---|---|---|
Länge | 242 mm 9.5 inches | 267 mm 10.5 inches |
Breite | 112 mm 4.4 inches | 111 mm 4.4 inches |
TDP | 170 W | 230 W |
Vorgeschlagenes Netzteil | 450 W | 550 W |
Ausgabe | 1x HDMI3x DisplayPort | 4x DisplayPort1x USB Type-C |
Stromverbindung | 1x 12-pin | 1x 6-pin + 1x 8-pin |
Board-Nummer | PG190 SKU 60 | — |
DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 8.6 | 7.5 |
Shader-Modell | 6.6 | 6.6 |