Systems and methods for performing a fast simulation

A non-transitory machine-readable storage medium encoded with instructions executable by a plurality of hardware processors of a computing component to perform a fast simulation using test parameter vectors as inputs, the machine-readable storage medium comprising instructions to cause the hardware processors to:

• retrieve precomputed samples from a sample repository stored in a non-volatile memory, the precomputed samples being precomputed using a simulated model, predetermined parameter vectors, and random inputs;
• store respective subsets of the precomputed samples in local memories of respective ones of the hardware processors;
• store the test parameter vectors in the local memories of the hardware processors;
• at each of the hardware processors,
• select a subset of the precomputed samples stored in the local memory of the hardware processor based on the test parameter vectors, and
• compute test samples by executing the simulated model using the test parameter vectors and the random inputs used to precompute the precomputed samples retrieved from the sample repository;
• and
• combine the subset of the precomputed samples and the test samples to produce a simulation result.

A system comprising:

• a plurality of hardware processors;
• and
• a non-transitory machine-readable storage medium encoded with instructions executable by the hardware processors to:
• retrieve precomputed samples from a sample repository stored in a non-volatile memory, the precomputed samples being precomputed using a simulated model, predetermined parameter vectors, and random inputs;
• store respective subsets of the precomputed samples in local memories of respective ones of the hardware processors;
• store the test parameter vectors in the local memories of the hardware processors;
• at each of the hardware processors,
• select a subset of the precomputed samples stored in the local memory of the hardware processor based on the test parameter vectors, and
• compute test samples by executing the simulated model using the test parameter vectors and the random inputs used to precompute the precomputed samples retrieved from the sample repository;
• and
• combine the subset of the precomputed samples and the test samples to produce a simulation result.