Does a wider hidden layer make weight-sharing product-table inference beat an int8 MAC engine?

What it found

Tests the break-even accel-lut predicted analytically, on trained 64-N-10 digits MLPs (N = 32, 128, 512, 10 splits), with the table engine on the wide layer and an int8 MAC on the 10-output layer. Mostly negative: the best table design is 14% below int8 modelled energy at width 512 only if a table read costs a quarter of an array read per bit (assumed), and 2× or worse at the array-cost read. Accuracy cost of sharing shrinks with width (K = 8: 1.6 points at 32, 0.4 at 512). Stylised, modelled energy, no synthesis.

A figure from its own output

Paper, code and results

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

More in Task-specific AI accelerators

• Does fine-tuning the shared weight values rescue low-K lookup-table inference?Fine-tuning the shared values of accel-lut's product-table engine: rescues K=2 in the 75%-pruned digits MLP (14% under int8 energy only at an assumed cheap table read), not the dense network. Stylised, modelled energy.
• What does a product-table inference engine cost in RTL, against a serial MAC engine?The product-table engine and a serial MAC engine in Verilog, bit-exact against NumPy and synthesised with Yosys: negative, the table needs an accumulator per output (stylised)
• Does a tiny always-on keyword model that wakes a bigger one beat the best single model on energy?Classifier-only energy of two-stage keyword-spotting cascades vs 40 single MLPs retrained on the original Speech Commands v0.02 (5 seeds, 200 models, about 41,000 cascades per seed, thresholds chosen on validation): cascades cut modelled energy by 0 to 28% at the same validation target, losing 0.3 to 1.4 test points, and the saving is under 1% of a system whose MFCC front end costs about 50 times the classifier
• Does the MFCC front end cost more than the keyword-spotting network it feeds?An instrumented Q15 MFCC front end (512-point FFT, 40 mel bands, DCT) costs 7,532 multiplies per 20 ms frame against the 5,184-MAC accel-kws classifier per inference; under assumed 45 nm constants the front end is 8 to 150 times the classifier's power, and 16-bit FFT scaling decides its accuracy (synthetic frames, no Speech Commands)
• Does block floating point fix the 16-bit FFT scaling problem in an always-on MFCC front end?A shared data-chosen exponent for the 16-bit FFT in accel-frontend's MFCC path cuts cepstral error to 0.016 to 0.081 of the spread at -60 to -30 dBFS (one shift per stage: 0.35 to 0.72) for about +0.5% modelled energy, but no better than 18 to 20-bit fixed schedules on loud input (synthetic frames, no Speech Commands)
• Do the accel-* energy constants match Horowitz (2014), and does fixing the array-size term change accel-kws's conclusions?All 34 energy constants in the accel-* projects that have a counterpart in Horowitz's Fig. 1.1.9 are within 4% of it; re-costing accel-kws with the figure's array-size law (energy about the square root of size) moves energy to 0.23 to 0.81 of as built but keeps 17 of 18 front designs (Spearman 0.991)

All 40 Task-specific AI accelerators 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.