Lab 03

Stochastic Computing Lab

Computing with probability as the primitive.

Hardware and algorithms in which randomness is not noise to suppress but the substrate itself — for ultra-low-power inference and neuromorphic systems.

§ 01

Open problems

Where a well-posed attempt could move the frontier.

  • 01Noise-native inference on edge hardware
  • 02Stochastic primitives for probabilistic programming
  • 03Energy-proportional computing for always-on sensing
§ 03

Publications from this lab

  • IEEE Trans. VLSI Systems · Under review · APR 30, 2026
    StochastiCore: A Complete GPU Architecture Based on Stochastic Computing

    Graphics and inference accelerators are built from binary multipliers and adders whose area and switching cost grow with operand width. Stochastic computing (SC) encodes a value as the probability of a bit being one in a random stream, reducing multiplication to a single AND gate and scaled addition to a multiplexer, with intrinsic tolerance to bit errors. We present StochastiCore, the first synthesizable GPU pipeline whose arithmetic datapath is stochastic — command processing, SC vertex transform, binary rasterization, SC fragment shading, and framebuffer/VGA output in open-source Verilog. Beyond integration we contribute a theoretical analysis of SC graphics, a reproducible Yosys gate-level power and area characterization, and a deterministic low-discrepancy bitstream generator that cuts generator area 7.5× and switching energy 15.4×. Bit-accurate rendering on the verified LFSR model reaches 36.7 dB PSNR; we report honestly that SC's advantage is area parity at higher functional density, graceful degradation, and free anti-banding rather than a per-operation energy win.

§ 04

Releases from this lab

  • hardware · alpha · APR 30, 2026
    StochastiCore v0.1

    An open-source GPU architecture whose arithmetic datapath runs on stochastic computing — multiplication becomes a single AND gate, scaled addition a multiplexer.