ICEraQ® – Micro-modular, Rack-based Immersion Cooling System
Whether you’re running AI, public cloud computing, private cloud storage, a high-frequency trading operation, or an on-premises data center, ICEraQ micro-modular, liquid cooling solutions from GRC can help you achieve unprecedented cost, performance, and space efficiencies.
With minimal site requirements and a modular design, ICEraQ server cooling systems significantly reduce the expense of building, running, and expanding data centers.
- Additional Information
- Models
- Advantages & Benefits
- Docs & Downloads
ICEraQ®, Micro-Modular Solutions Include:
- CDU (Coolant Distribution Unit) + racks
- Racks filled with our proprietary ElectroSafe™ liquid immersion coolant
- GRC’s Foresight monitoring and alerts application
- Mirrored System, with 2N redundant pumps
- Integrated cable management
- Rack-mounted service rails for easy server maintenance and hot swaps
- One-year limited warranty including 24/7 on-call GRC support staff and 24/7 remote monitoring
ICEraQ One
For extreme high-power GPU computing-, ASIC- and FPGA-based applications, including Artificial Intelligence (AI), High-Performance Computing (HPC) and more.
- 1 immersion-cooled rack supported by 100kW CDU
- The only system in the market handling up to 100 kW/rack
- Enables scaling in single-rack increments
ICEraQ Duo
For most high-GPU server applications including Artificial Intelligence (AI), geosciences (O & G exploration), High-Performance Computing (HPC) and more.
- 2 immersion-cooled racks supported by a 100kW CDU
- Cools high-power GPU servers up to 50 kW/rack (AC max=15 kW)
- Enables scaling in 2-rack increments
ICEraQ Quad
For cloud technology/on-premises data centers and High-Frequency Trading (HFT) data centers.
- 4 immersion-cooled racks supported by a 100kW CDU
- Supports densities up to 25 kW/rack
- Enables scaling in 4-rack increments
Advantages & Benefits of ICEraQ
- Cut cooling energy by up to 95%
- Compatible with leading OEM servers
- Attain an mPUE <1.05
- Lower upfront costs 50%
- Reduce server power draw 10-20%
- Cool up to 100 kW in a single rack
- Enables high-density data center layouts
- CPU-/GPU-agnostic
- Fast deployment: 10-12 weeks
- Enables Scaling in 1-4 Rack Increments.