NVIDIA GTC
About the event
NVIDIA's conference on AI and accelerated computing, useful for data centre architects tracking high-density rack, power and liquid-cooling requirements for AI factories.
Venue
This event has ended. The page is kept in the archive with its details and related technical reading.
Read before you go
Explore the libraryHuawei Digital Power 2025
Huawei AI Data Center Reference Design
Import RD 01-21 as parametric AI-hall templates (rack kW, racks per module, module kW, redundancy of fan walls/TMUs/towers, generator and transformer counts) and as golden test cases for capacity math.
- Power distribution supports 2N, DR and BR architectures.
Vertiv 2026
Transforming Colocation Facilities to Meet Demand for AI Compute
Give the rack/pod model a liquid fraction (default about 70% for direct-to-chip) so residual air load is computed automatically.
- Average multi-node AI pod density is projected to rise from 40-100 kW to 100-250 kW.
Vertiv 2025
Vertiv 360AI High Density Reference Design #006: 2x 1.28 MW NVIDIA Blackwell DGX SuperPODs
Seed an AI-hall wizard template with: compute rack 73 kW, support rack 14 kW, liquid fraction 0.78, power 4N/3, cooling N+1, mechanical UPS 2N.
- Total IT load 2,560 kW = 2 pods x 1,280 kW.
SoSo CAD
Check cooling capacity alongside your design
Review zone heat loads, available capacity and the capacity balance after the largest unit is lost in SoSo CAD.
Request a demo