GPU Name | GP100 | TU104 |
---|---|---|
Architektur | Pascal | Turing |
Hersteller | TSMC | TSMC |
Prozessgröße | 16 nm | 12 nm |
Transistoren | 15,300 million | 13,600 million |
Chipgröße | 610 mm² | 545 mm² |
GPU Variante | — | TU104-850-A1 |
Veröffentlichungsdatum | Oct 1st, 2016 | Nov 13th, 2018 |
---|---|---|
Generation | Quadro | Quadro |
Produktion | End-of-life | Active |
Businterface | PCIe 3.0 x16 | PCIe 3.0 x16 |
Originalpreis | — | 899 USD |
Basis-Taktfrequenz | 1304 MHz | 1005 MHz |
---|---|---|
Boost-Takt | 1442 MHz | 1545 MHz |
Speicher-Taktung | 715 MHz 1430 Mbps effective | 1625 MHz 13 Gbps effective |
Speichergröße | 16 GB | 8 GB |
---|---|---|
Speichertyp | HBM2 | GDDR6 |
Speicherbus | 4096 bit | 256 bit |
Bandbreite | 732.2 GB/s | 416.0 GB/s |
Shading-Einheiten | 3584 | 2304 |
---|---|---|
TMUs | 224 | 144 |
ROPs | 96 | 64 |
Anzahl SM | 56 | 36 |
Cache L1 | 24 KB (per SM) | 64 KB (per SM) |
Cache L2 | 4 MB | 4 MB |
Tensor Cores | — | 288 |
RT-Kerne | — | 36 |
Pixelrate | 138.4 GPixel/s | 98.88 GPixel/s |
---|---|---|
Texturrate | 323.0 GTexel/s | 222.5 GTexel/s |
FP16 (half) Leistung | 20.67 TFLOPS (2:1) | 14.24 TFLOPS (2:1) |
FP32 (float) Leistung | 10.34 TFLOPS | 7.119 TFLOPS |
FP64 (double) Leistung | 5.168 TFLOPS (1:2) | 222.5 GFLOPS (1:32) |
Steckplatzbreite | Dual-slot | Single-slot |
---|---|---|
Länge | 267 mm 10.5 inches | 241 mm 9.5 inches |
Breite | 111 mm 4.4 inches | 111 mm 4.4 inches |
TDP | 235 W | 160 W |
Vorgeschlagenes Netzteil | 550 W | 450 W |
Ausgabe | 1x DVI4x DisplayPort | 3x DisplayPort1x USB Type-C |
Stromverbindung | 1x 8-pin | 1x 8-pin |
DirectX | 12 (12_1) | 12 Ultimate (12_2) |
---|---|---|
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 3.0 |
Vulkan | 1.2 | 1.2 |
CUDA | 6.0 | 7.5 |
Shader-Modell | 6.4 | 6.6 |