Examples
Examples
Try the starting example
- Independent suites: ID, duration whole minutes, CPU units, memory units
- A,10,3,4 B,6,2,6 C,8,1,4
- Concurrent CPU capacity units
- 4
- Concurrent memory capacity units
- 8
- Feasible suite start-end minutes
- A: 0-10; C: 0-8; B: 10-16
- Makespan (minutes)
- 16
- Peak concurrent CPU and memory units
- 4, 8
- CPU-unit-time utilization (%)
- 78.125
- Memory-unit-time utilization (%)
- 84.375
Try another scenario
- Independent suites: ID, duration whole minutes, CPU units, memory units
- A,10,3,4 B,6,2,6 C,8,1,4
- Concurrent CPU capacity units
- 5
- Concurrent memory capacity units
- 10
- Feasible suite start-end minutes
- A: 0-10; B: 0-6; C: 6-14
- Makespan (minutes)
- 14
- Peak concurrent CPU and memory units
- 5, 10
- CPU-unit-time utilization (%)
- 71.428571
- Memory-unit-time utilization (%)
- 77.142857
Calculation method
Calculation method
Feasible suite start-end minutes
At each completion launch every input-ordered waiting suite that fits both remaining capacities; jobs are nonpreemptive.
Makespan (minutes)
Latest completion in this feasible first-fit schedule.
Peak concurrent CPU and memory units
Maximum simultaneous assigned demands, respecting both resource limits.
CPU-unit-time utilization (%)
Sum suite CPU×duration/(CPU capacity×makespan)×100.
Memory-unit-time utilization (%)
Sum suite memory×duration/(memory capacity×makespan)×100.
Symbols and units
- a
- Independent suites: ID, duration whole minutes, CPU units, memory units
- b
- Concurrent CPU capacity units
- c
- Concurrent memory capacity units
Use the units shown. A list keeps the order in which you enter its values. The symbol ^ means “raised to the power of”.
Assumptions & limits
Assumptions & limits
- A feasible supplied-resource scheduling heuristic, not an optimal schedule, actual execution or a measurement of real CPU/RAM use. Demands stay constant for each suite and dependencies are excluded.
Are these inputs private?
These calculations run in your browser. A shared link contains the values you choose to share. Only questions submitted to the separate AI finder are sent to OpenAI.
Further reading
NIST: combinatorial testing and coverage measurement; audit rules are explicitly supplied ↗
Background reading; this does not imply endorsement or independent review of SumFizz.