GPU Name | GA104 | GV100 |
---|---|---|
GPU Variante | GA104-200-A1 | GV100-875-A1 |
Architektur | Ampere | Volta |
Hersteller | Samsung | TSMC |
Prozessgröße | 8 nm | 12 nm |
Transistoren | 17,400 million | 21,100 million |
Chipgröße | 392 mm² | 815 mm² |
Veröffentlichungsdatum | Dec 1st, 2020 | Mar 27th, 2018 |
---|---|---|
gpu.details.availability | Dec 2nd, 2020 | — |
Generation | GeForce 30 | Quadro |
Vorgänger | GeForce 20 | — |
Produktion | Active | End-of-life |
Originalpreis | 399 USD | 8,999 USD |
Businterface | PCIe 4.0 x16 | PCIe 3.0 x16 |
Reviews | 64 in our database | — |
Basis-Taktfrequenz | 1410 MHz | 1132 MHz |
---|---|---|
Boost-Takt | 1665 MHz | 1627 MHz |
Speicher-Taktung | 1750 MHz 14 Gbps effective | 848 MHz 1696 Mbps effective |
Speichergröße | 8 GB | 32 GB |
---|---|---|
Speichertyp | GDDR6 | HBM2 |
Speicherbus | 256 bit | 4096 bit |
Bandbreite | 448.0 GB/s | 868.4 GB/s |
Shading-Einheiten | 4864 | 5120 |
---|---|---|
TMUs | 152 | 320 |
ROPs | 80 | 128 |
Anzahl SM | 38 | 80 |
Tensor Cores | 152 | 640 |
RT-Kerne | 38 | — |
Cache L1 | 128 KB (per SM) | 128 KB (per SM) |
Cache L2 | 4 MB | 6 MB |
Pixelrate | 133.2 GPixel/s | 208.3 GPixel/s |
---|---|---|
Texturrate | 253.1 GTexel/s | 520.6 GTexel/s |
FP16 (half) Leistung | 16.20 TFLOPS (1:1) | 33.32 TFLOPS (2:1) |
FP32 (float) Leistung | 16.20 TFLOPS | 16.66 TFLOPS |
FP64 (double) Leistung | 253.1 GFLOPS (1:64) | 8.330 TFLOPS (1:2) |
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 | 200 W | 250 W |
Vorgeschlagenes Netzteil | 550 W | 600 W |
Ausgabe | 1x HDMI3x DisplayPort | 4x DisplayPort |
Stromverbindung | 1x 12-pin | 8-pin EPS |
Board-Nummer | PG142 SKU 20 | PG500 SKU 500 |
DirectX | 12 Ultimate (12_2) | 12 (12_1) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 8.6 | 7.0 |
Shader-Modell | 6.6 | 6.6 |