GPU Name | TU104 | TU102 |
---|---|---|
GPU Variante | TU104-410-A1 | TU102-875-A1 |
Architektur | Turing | Turing |
Hersteller | TSMC | TSMC |
Prozessgröße | 12 nm | 12 nm |
Transistoren | 13,600 million | 18,600 million |
Chipgröße | 545 mm² | 754 mm² |
Veröffentlichungsdatum | Jul 9th, 2019 | Aug 13th, 2018 |
---|---|---|
Generation | GeForce 20 | Quadro |
Vorgänger | GeForce 10 | — |
Produktion | Active | Active |
Originalpreis | 499 USD | 6,299 USD |
Businterface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Reviews | 78 in our database | — |
Nachfolger | GeForce 30 | — |
Basis-Taktfrequenz | 1605 MHz | 1440 MHz |
---|---|---|
Boost-Takt | 1770 MHz | 1770 MHz |
Speicher-Taktung | 1750 MHz 14 Gbps effective | 1750 MHz 14 Gbps effective |
Speichergröße | 8 GB | 24 GB |
---|---|---|
Speichertyp | GDDR6 | GDDR6 |
Speicherbus | 256 bit | 384 bit |
Bandbreite | 448.0 GB/s | 672.0 GB/s |
Shading-Einheiten | 2560 | 4608 |
---|---|---|
TMUs | 160 | 288 |
ROPs | 64 | 96 |
Anzahl SM | 40 | 72 |
Tensor Cores | 320 | 576 |
RT-Kerne | 40 | 72 |
Cache L1 | 64 KB (per SM) | 64 KB (per SM) |
Cache L2 | 4 MB | 6 MB |
Pixelrate | 113.3 GPixel/s | 169.9 GPixel/s |
---|---|---|
Texturrate | 283.2 GTexel/s | 509.8 GTexel/s |
FP16 (half) Leistung | 18.12 TFLOPS (2:1) | 32.62 TFLOPS (2:1) |
FP32 (float) Leistung | 9.062 TFLOPS | 16.31 TFLOPS |
FP64 (double) Leistung | 283.2 GFLOPS (1:32) | 509.8 GFLOPS (1:32) |
Steckplatzbreite | Dual-slot | Dual-slot |
---|---|---|
Länge | 267 mm 10.5 inches | 267 mm 10.5 inches |
Breite | 116 mm 4.6 inches | 111 mm 4.4 inches |
Höhe | 35 mm 1.4 inches | — |
TDP | 215 W | 260 W |
Vorgeschlagenes Netzteil | 550 W | 600 W |
Ausgabe | 1x HDMI3x DisplayPort1x USB Type-C | 4x DisplayPort1x USB Type-C |
Stromverbindung | 1x 6-pin + 1x 8-pin | 1x 6-pin + 1x 8-pin |
Board-Nummer | PG180 SKU 12 | 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 | 7.5 | 7.5 |
Shader-Modell | 6.6 | 6.6 |