Which search method finds a chip design's Pareto front with the fewest evaluations?

What it found

Random search, a grid, simulated annealing, a genetic algorithm, NSGA-II and a TPE-style Bayesian method are compared at equal evaluation budgets on an 80-design space (MAC lanes × bit width × ABC script) of a toy quantised-MLP accelerator, using Pareto hypervolume over 100 seeds. TPE reaches 0.917 of the true-front hypervolume at 16 evaluations against 0.891 for random, and 0.980 against 0.943 at 30; annealing trails random throughout. Stylised: the space is tiny (random search at 40 evaluations already scores 0.965), hyperparameters are untuned, objectives are generic-gate counts, and nothing is said about real chips.

A figure from its own output

Paper, code and results

• README and method
• Experiments and results
• Code
• Tests

More in Algorithmic chip-design loops

• Do cheap rungs of the chip-design tool ladder rank designs like synthesis, and how much synthesis time does screening save?A three-rung fidelity ladder (analytic model, RTL simulation, synthesis) over 40 logged designs: the free rung ranks the objective at Spearman 0.74, and successive halving finds the optimum at 20 s of tool time against 205 s to synthesise everything (stylised, toy design family, no place and route).
• Can cheap word-level RTL features predict synthesised cell counts well enough to screen a design search, and does that survive a new design family?A cell-count surrogate from cheap word-level RTL features over 133 designs in four generator families: 3.9% median error on families it saw (non-negative linear model), 11% to 210% on a held-out family with rank agreement staying at Spearman 0.75 to 1.00, and it cuts syntheses to find a near-best design in a 36-design pool from 12.4 to 1-5 (stylised, synthesis-only target, no place and route).
• How many synthesised designs from a new family does a cell-count surrogate need before it is usable, and is it better to pool them with old families or train on them alone?Few-shot adaptation of the eda-surrogate cell-count model to an unseen design family: one synthesised design from the new family cuts the linear model's median error from 49% to 18%, training on the new family alone beats pooling from about three designs, boosted trees need about 12 (stylised, synthesis-only target, no place and route).
• Which few designs of a new family should you synthesise to adapt a cell-count surrogate, and should they count for more?Which few designs of a new family to synthesise when adapting a cell-count surrogate: a farthest-point spread in feature space roughly halves the linear model's error against random draws at 5 designs (5.3% against 8.5%), the smallest designs are worst, and upweighting new points helps linear and ridge but not boosted trees (stylised, synthesis-only target).
• Does the farthest-point spread still beat random draws when every chooser is scored on the same held-out designs?eda-adaptpick's adaptation-design choosers re-scored on one fixed test set per family (4 families x 5 splits): the farthest-point spread still beats random draws for the linear model at every k (4.8% against 6.0% at 5 designs, w = 5) but wins in only 65% of cells, the smallest-first rule stays worst, and the earlier 'halves the error' margin shrinks to 20-45% at 5 to 8 designs.
• Does a cell-count surrogate used as a screen find a chip design’s Pareto front with fewer syntheses than random search or TPE?A cell-count surrogate used as a screen in the design-search loop: 4 spread syntheses plus a log-linear fit reach 0.990 of the true front's hypervolume at 12 syntheses against 0.860 for random and 0.878 for TPE, of which about +0.05 comes from free cycles/error objectives (stylised, one 80-design space).

All 42 Algorithmic chip-design loops projects →

Other research topics

Proper scoring & elicitation28Effort & peer prediction9Verification games & slashing19Detection & tolerances14Markets as routers13Prediction-market design9Paying contributors8Decentralised training systems23Digital twins & sim-to-real164LLM chip design loops40Robot manufacturing loops53Ambient AI assistant46Self-replicating manufacturing34Simulation-first design64Engineered clothing45Task-specific AI accelerators40Algorithmic chip-design loops42Open-source purpose-built robots44The software-engineering loop43Adversarial human imitation41Open-source residential construction41Autonomous multi-angle capture34Sensing, imaging and 3D31Energy supply and dense energy storage39Robot societies among people31Agentic co-design of low-cost robots27Laundry-hanging robots25Machine learning on qualitative data23Robots on the building site27Civilizations & group psychology1History & human sciences1

Produced with AI assistance (Claude). Results are from the code in this repository and are simulated or stylised unless the abstract says otherwise; nothing here implies affiliation with or endorsement by any lab, researcher or company cited. MIT licensed.