How big a keyword-spotting model fits a real Tiny Tapeout tile once the hidden layer goes past 64 units?

What it found

accel-ttsizes stopped its sweep at H = 64 so larger tiles had nothing to hold. This project synthesises the same streaming engine at H = 96, 128, 192 and 256 (weights of 2, 3, 4 and 8 bits, 70 and 120 inputs, 64 synthesis runs with the RTL checked against the integer reference in Icarus Verilog) and finds the smallest of Tiny Tapeout's 12 real tile sizes that holds each at 100, 70 and 50% utilisation. Area is roughly linear at about 250 µm² per hidden unit (H = 128: 36,411–40,747 µm²; H = 256: 68,606–72,897). The most accurate model, H = 128 with 4-bit weights (0.752, from accel-kws, which had trained it), needs a 2x2 tile; the best 1x2 model (H = 64, 0.737) is 0.015 less accurate, and a 2x2 is 2.08× the area of a 1x2. A 24-bit accumulator adds 0.1–2.1% area. At H = 256 with 8-bit weights, a random model overflows the 20-bit accumulator, so larger models need a wider one or a trained-model check. Utilisation is assumed, area is synthesis-only, and accuracy above H = 64 was not retrained here (the dataset host was unreachable) and has not been checked against the tile's bias and accumulator limits.

Paper, code and results

• README and method
• Experiments and results
• Tests

More in Task-specific AI accelerators

• Do trained keyword-spotting models fit a Tiny Tapeout tile's 16-bit bias and 20-bit accumulator?All 96 retrained keyword-spotting models fit the Tiny Tapeout engine's 16-bit bias and 20-bit accumulator limits (worst use 43% and 30%), accuracy through the tile contract equals the reference, and 32 trained models run bit-exact in RTL.
• Does Tiny Tapeout's real tile-size table change which keyword-spotting model fits a tile?Tiny Tapeout's real SKY130 tile sizes (1x1 is 161 × 111.52 µm = 17,955 µm², 0.43% below the value assumed earlier) applied to the synthesised keyword-spotting engine and the retrained models: the best 1x1 model is unchanged at 100% and 50% utilisation and flips at 70% (H = 16, 4-bit, 0.596 instead of 8-bit, 0.616, a 29 µm² miss); H = 64 with 8-bit weights (0.737) fits a 1x2 tile.
• How small can a keyword-spotting accelerator get, and what does each bit of precision cost?Keyword-spotting accelerator: quantised MLP on Speech Commands, serial-MAC RTL bit-exact against an integer reference, accuracy vs cycles, cells and modelled energy over width and weight bits (stylised).
• Does a keyword-spotting accelerator fit in a Tiny Tapeout tile, and how accurate can it be?A streaming keyword-spotting engine with no weight memory, exact against an integer reference and synthesised to SKY130 on 32 geometries (6,300 to 24,500 um2); 16 hidden units at 8-bit weights is the most accurate (0.616) that fits one assumed 1x1 Tiny Tapeout tile at 70% utilisation, 64 units at 4 bits (0.738) needs two. Stylised: synthesis only.
• Under a latency deadline, how much engine area does picking the most accurate model first cost, compared with choosing model and lane count together?Model-first vs joint choice of model and MAC lane count under a latency deadline, on the 40 measured accel-kws models; accepting 2 validation points less cuts engine area 31–42% (stylised, table-based, cycles for more than one lane analytic).
• Does NSGA-II find a keyword-spotting accelerator's Pareto front faster than random search at equal budgets?NSGA-II against random search at equal budgets on a 3,840-design keyword-spotting accelerator space with exact ground truth; NSGA-II finds 54 to 89% of the exact front at 20.8% of the space against 19 to 21% for random search, though hypervolume is 0.97 to 1.00 for both. Stylised.

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.