GPU Name | GA104 | TU102 |
---|---|---|
GPU Variante | GA104-401-A1 | TU102-875-A1 |
Architektur | Ampere | Turing |
Hersteller | Samsung | TSMC |
Prozessgröße | 8 nm | 12 nm |
Transistoren | 17,400 million | 18,600 million |
Chipgröße | 392 mm² | 754 mm² |
Veröffentlichungsdatum | Jan 2022 | Aug 13th, 2018 |
---|---|---|
gpu.details.availability | Jan 2022 | — |
Generation | GeForce 30 | Quadro |
Vorgänger | GeForce 20 | — |
Produktion | Unreleased | Active |
Originalpreis | 699 USD | 6,299 USD |
Businterface | PCIe 4.0 x16 | PCIe 3.0 x16 |
Reviews | 43 in our database | — |
Basis-Taktfrequenz | 1575 MHz | 1440 MHz |
---|---|---|
Boost-Takt | 1770 MHz | 1770 MHz |
Speicher-Taktung | 1188 MHz 19 Gbps effective | 1750 MHz 14 Gbps effective |
Speichergröße | 16 GB | 24 GB |
---|---|---|
Speichertyp | GDDR6X | GDDR6 |
Speicherbus | 256 bit | 384 bit |
Bandbreite | 608.3 GB/s | 672.0 GB/s |
Shading-Einheiten | 6144 | 4608 |
---|---|---|
TMUs | 192 | 288 |
ROPs | 96 | 96 |
Anzahl SM | 48 | 72 |
Tensor Cores | 192 | 576 |
RT-Kerne | 48 | 72 |
Cache L1 | 128 KB (per SM) | 64 KB (per SM) |
Cache L2 | 4 MB | 6 MB |
Pixelrate | 169.9 GPixel/s | 169.9 GPixel/s |
---|---|---|
Texturrate | 339.8 GTexel/s | 509.8 GTexel/s |
FP16 (half) Leistung | 21.75 TFLOPS (1:1) | 32.62 TFLOPS (2:1) |
FP32 (float) Leistung | 21.75 TFLOPS | 16.31 TFLOPS |
FP64 (double) Leistung | 339.8 GFLOPS (1:64) | 509.8 GFLOPS (1:32) |
Steckplatzbreite | Dual-slot | Dual-slot |
---|---|---|
Länge | 267 mm 10.5 inches | 267 mm 10.5 inches |
Breite | 112 mm 4.4 inches | 111 mm 4.4 inches |
TDP | 290 W | 260 W |
Vorgeschlagenes Netzteil | 600 W | 600 W |
Ausgabe | 1x HDMI3x DisplayPort | 4x DisplayPort1x USB Type-C |
Stromverbindung | 1x 12-pin | 1x 6-pin + 1x 8-pin |
Board-Nummer | — | PG150 SKU 510 |
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 |