Unterschiede hervorheben | Nvidia T400 mit 4 GB GDDR6-RAM |
Nvidia RTX A400 mit 4 GB GDDR6-RAM |
Nvidia T1000 mit 8 GB GDDR6-RAM |
Nvidia RTX A1000 mit 8 GB GDDR6-RAM |
Nvidia RTX A2000 mit 12 GB GDDR6 ECC-RAM |
Chipsatz | T400 | RTX A400 | T1000 | RTX A1000 | RTX A2000 |
GPU Architektur | Turing | Ampere | Turing | Ampere | Ampere |
Speicher | 4 GB | 4 GB | 8 GB | 8 GB | 12 GB |
Speicherart | GDDR6 | GDDR6 | GDDR6 | GDDR6 | GDDR6 ECC |
Speicheranbindung | 64 Bit | 64 Bit | 128 Bit | 128 Bit | 192 Bit |
Speicherbandbreite | 80 GB/s | 96 GB/s | 160 GB/s | 192 GB/s | 288 GB/s |
GPU-Taktung | 1070 MHz | 727 MHz | 1395 MHz | 727 MHz | 1200 MHz |
CUDA / Streamprozessoren | 384 | 768 | 896 | 2304 | 3328 |
Gleitkomma-Rechenleistung (FP32) | 1,094 TFLOPs | 2,706 TFLOPS | 2,50 TFLOPs | 6,737 TFLOPS | 7,987 TFLOPS |
Steckplatz | PCIe 3.0 x16 | PCIe 4.0 x16 (x8) | PCIe 3.0 x16 | PCIe 4.0 x16 (x8) | PCIe 4.0 x16 |
Slotbreite | 1 Slot | 1-Slot LP | 1 Slot | 1-Slot LP | 2 Slot LP |
Anschlüsse | 3x mDP 1.4a | 4x mDP 1.4a | 4x mDP 1.4a | 4x mDP 1.4a | 4x mDP 1.4a |
Kühlung | active | active | active | active | active |
Verbrauch (Watt) | 30W | 50W | 50W | 50W | 70W |
DirectX | 12 | 12_2 Ultimate | 12 | 12_2 Ultimate | 12.2 |
Open-GL | 4.5 | 4.6 | 4.5 | 4.6 | 4.68 |
Open-CL | 2.0 | 3.0 | 2.0 | 3.0 | 3.0 |
Vulkan | 1.0 | 1.3 | 1.0 | 1.3 | 1.3 |
Shader Model | 5.1 | 6.8 | 5.1 | 6.8 | 6.6 |
Max. Auflösung (Pixel) | 5120×2880 | 5120×2880 | 7680x4320 | 5120×2880 | 7680x4320 |
Max. Anzahl Monitore | 3 | 4 | 4 | 4 | 4 |
Zusatzfunktionen | Nvidia CUDA C, CUDA C++, DirectCompute 5.0, OpenCL, Java, Python, and Fortran | 6 RT Cores, 16 ROPs, 24 Tensor Cores, 6 SM Count, 24 TMUs, RTX IO, DirectCompute, Mosaic, 1x encode/decode (+AV1) | Nvidia CUDA C, CUDA C++, DirectCompute 5.0, OpenCL, Java, Python, and Fortran | 18 RT Cores, 32 ROPs, 72 Tensor Cores, 18 SM Count, 72 TMUs, RTX IO, DirectCompute, Mosaic, 1x encode, 2x decode (+AV1 decode) | 26 RT Cores, 104 Tensor Cores, CUDA, DirectCompute, OpenCL, Mosaic, 1x encode/decode (+AV1 decode) |