Skip to content
ENExplore Calculators

vCPU To Core Mapping Calculator

Work out vcpu to core mapping instantly with clear inputs, formula shown and shareable results.

About vCPU To Core Mapping Calculator

On most x86 cloud instances a vCPU is one hardware thread, so 32 vCPUs are 16 physical cores. That distinction matters for two reasons: per-core software licensing is charged on physical cores, and a second thread on a core adds only 20 to 30 percent throughput rather than doubling it — so a vCPU is roughly 0.6 of a core, not one.

Formula

vCPU mapping

physical cores = ceil(vCPUs / threads per core); effective throughput = cores x (1 + SMT gain); performance per vCPU = effective / vCPUs

Worked example

With the default values below, vCPU To Core Mapping Calculator returns Physical cores behind the vCPUs of 16. Change any input above and every figure here is recalculated in your browser.

Inputs used

vCPUs allocatedminimum 1
32
Threads per coreone of 2 - simultaneous multithreading enabled, 1 - SMT disabled or ARM core
2 - simultaneous multithreading enabled
Annual licence cost per coreminimum 0
3,800
Performance gain from SMTaccepts 0–100 %
25 %

Results

Physical cores behind the vCPUs
16
Annual per-core licence cost
$60,800.00
Effective core-equivalent throughput
20.00
Performance per vCPU relative to a full core
0.625

Step by step

  1. 1Values used
  2. 2vCPU mapping
  3. 3Physical cores behind the vCPUs= 16
  4. 4Annual per-core licence cost= 60,800.00
  5. 5Effective core-equivalent throughput= 20.00
  6. 6Performance per vCPU relative to a full core= 0.625

Assumptions and limits

  • The result is derived only from the 4 inputs listed above. Anything not among them is not part of the calculation.
  • In particular, this calculator does not take inflation or tax into account.
  • Figures are rounded for display to 3 decimal places, so totals built from several rounded parts can differ slightly from the unrounded arithmetic.

How these calculators are built and tested is described on the Methodology page. If a figure looks wrong, please report it.

Frequently Asked Questions

Are all cloud vCPUs hardware threads?

No. AWS Graviton and some other ARM instances give one vCPU per physical core with no SMT, which is why their per-vCPU performance is noticeably higher.

Does disabling SMT ever help?

For latency-sensitive or licence-constrained workloads, yes. It removes thread contention and can reduce the licensable core count on some models.

Related Calculators

vCPU To Core Mapping Calculator | Calcrivo