Research / Search and reasoning

arXiv 2026 · First and Corresponding Author · HPE Labs

Multi-primitive in-memory computing for Monte Carlo tree search

IMC-MCTS decomposes tree search into the memory and logic operations each phase actually needs, then coordinates them as one accelerator.

IMC-MCTS architecture connecting CAM, SRAM, RRAM, combinational logic, and TCAM control
Each phase of Monte Carlo tree search is mapped to a matching compute or memory primitive and orchestrated through a feedback loop.

124.18 mJ

modeled energy per 9×9 Go move at 5,000 search iterations

60.26 mW

modeled sustained accelerator power in the evaluated setup

1,050 games

9×9 Go round-robin evaluation at 500 simulations per move

8 applications

mapped across four domains to test substrate reuse

Problem

Monte Carlo tree search alternates between irregular tree lookup, expansion, learned evaluation, statistical update, and control. A single conventional compute primitive is poorly matched to all five phases, while moving state among separate accelerators can erase the benefit.

Approach

My Role

I conceived the phase-to-primitive decomposition, designed the architecture, performed RTL synthesis and cycle simulation, ran the Go tournament and cross-domain evaluations, and led the manuscript.

Citation

T. Molom-Ochir, B. F. Morris III, Y. He, A. Gajjar, G. Pedretti, H. Li, Y. Chen, J. Ignowski, and A. Natarajan, "Multi-primitive in-memory computing for Monte Carlo tree search," arXiv:2607.22869, 2026. DOI