Processor-Node Job Scheduling for Coolant Outlet Temperature Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for regulating coolant flow temperatures in processor-based platforms are energy inefficient, particularly when used to maintain minimum threshold temperatures required by waste heat consumer systems.
Innovation Solution
A computer system employs job scheduling to regulate coolant flow temperatures by partitioning processor-based nodes into cooling domains and adjusting job execution to maintain coolant flow temperatures at or above a minimum threshold, potentially combined with volume flow-based regulation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Temperature
If conventional temperature regulation methods are used to maintain minimum coolant temperatures, then the minimum threshold temperature can be maintained, but energy efficiency deteriorates
Solution Approach 1:
The system dynamically changes the operational parameters of processor-based nodes (workload, power state) to regulate coolant temperature. By adjusting the computational load on processors, the heat generation is controlled, which in turn regulates the coolant temperature without requiring additional energy-intensive heating systems.
Solution Approach 2:
The processor-based nodes serve dual purposes: performing computational tasks and simultaneously generating heat to warm the coolant flow. The waste heat that would normally be discarded is utilized to maintain the minimum temperature requirement, making the system self-sufficient for temperature regulation without external energy input.
2Temperature
If coolant flow rate is increased to remove more heat, then heat dissipation improves, but energy consumption increases
Solution Approach 1:
The system dynamically adjusts the coolant flow rate based on real-time thermal conditions and workload requirements. Rather than maintaining a constant high flow rate, the pump speed is varied to match the actual heat generation from processors, optimizing the balance between heat removal efficiency and pump energy consumption.
Solution Approach 2:
The system employs temperature sensors and control logic to monitor coolant temperature and processor heat generation, using this feedback to adjust pump speed and coolant flow rate. This closed-loop control ensures that the coolant flow is optimized for heat removal while minimizing the energy consumed by the pump.
3Productivity
If processor workload is increased to improve productivity, then more computing tasks are completed, but heat generation increases making temperature control more difficult
Solution Approach 1:
The system segments the processor-based nodes into different groups or domains, allowing independent control of workload distribution and heat generation. By selectively assigning tasks to specific nodes and managing their operational states, the system can maintain high overall productivity while controlling the thermal output to meet coolant temperature requirements.
Solution Approach 2:
The system employs periodic monitoring and adjustment of processor workloads to manage heat generation. By cycling through different workload distributions and power states across processor nodes, the system can maintain high productivity over time while preventing excessive heat accumulation that would compromise coolant temperature control.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances power efficiency, reduces energy consumption, and provides faster transient response times while accommodating a wider range of processing loads.
Implementation Method 1
communicate a coolant flow between an inlet and an outlet... to remove thermal energy from a plurality of processor-based nodes
Implementation Method 2
circulate a liquid coolant flow through coolant flow plates (or 'cold plates') that are located near heat-dissipating components of the platform
Data Source
AI summary
A process includes communicating a coolant flow between an inlet and an outlet of a coolant subsystem that is associated with a cooling domain to remove thermal energy from a plurality of processor-based nodes of the cooling domain. The communication of the coolant flow has associated predefined parameters. The process includes regulating a temperature of the coolant flow at the outlet. In accordance with example implementations, the regulation includes determining, based on the predefined parameters, a minimum collective power consumption by the processor-based nodes to maintain a temperature of the coolant flow at the outlet at or above a minimum threshold temperature, and based on the minimum power consumption, scheduling jobs to be executed by the nodes.