T27.AI

Measured evidence

Every number here was measured.

Hardware claims are cheap to make and hard to check, so this page collects the results behind everything else: what was built, what it measured, and how it was verified. Where something is a submission rather than a win, or a prototype rather than a product, it says so.

Results

GF16 4×4 matmul — 32,252 LUT with zero hard multipliers

A 4×4 matrix multiplier over my own GF16 format, synthesised for Artix-7. It maps into fabric with no DSP48 blocks at all, or 21,223 LUTs if the 64 hard multipliers are allowed. The block is combinational — no registers, so no clock and no frequency figure belongs to it.

100% held-out — a network that trains on the FPGA

Forward pass, gradient and weight update all in RTL with no host in the loop. A 2-layer ReLU network learns XOR on the chip itself, 4 of 4 correct, every node bit-exact from specification to silicon.

SKY130 — tape-out through Tiny Tapeout

The same source that runs on the FPGA went to an open ASIC process: GDS produced, gate-level test passed, precheck passed.

2.84× / 5.53× — GF-T beats tekum16

A float whose exponent is a balanced-ternary number and whose fields are fixed: no regime decode to pay for, and on a ternary fabric the exponent add is native. Against tekum16, whose stated advantage is exactly that fabric — a tie near unity, 2.84× lower error at |e| 8–20, 5.53× lower at |e| 20–38, with a uniform 9-bit mantissa where tekum16 tapers to four. Range is bounded at ±40 in powers of two where tekum16's regime is not; that is the trade.

Over the air — tri-net, a full ternary network stack

133 formal specifications: GF16 physical layer, BPSK modem on AD9361, ETX mesh routing, ChaCha20-Poly1305 / X25519 crypto. Text and images carried between physically separate boards.

83 formats — a conformance catalogue

Bit-exact test vectors for FP8, BF16, MXFP4 and microscaling formats: a vendor-neutral reference for verifying low-precision arithmetic.

How any of this is checked

Independent model, not a mirror

The reference model is written from the specification, never from the RTL.

Per-stage vectors

Known-answer vectors at every pipeline stage, so a regression points at the stage that broke.

Hardware replay

The same vectors run again on the physical board. Simulation agreement does not prove silicon agreement.

Open toolchain

Yosys, nextpnr-xilinx, prjxray, openFPGALoader, iverilog. No proprietary licence stands between a claim here and someone reproducing it.

What these results are not

Entries are entries

A DARPA CLARA submission and an OpenAI Parameter Golf entry are submitted work, not awarded contracts or won prizes.

One device family

Measurements come from a Xilinx Artix-7 and are not multi-corner characterisation.

Training is a primitive

The on-chip training result is proven at small scale: a real network learning on real silicon, not a production training accelerator.

Estimates are labelled

Anything estimated rather than measured is labelled as estimated.

A figure withdrawn

This page previously reported 323 MHz and 41.2 GOPS for the GF16 matmul. Re-checking the RTL on 8 August 2026 showed the block holds no registers, so it has no clock and no frequency can belong to it. Withdrawn rather than explained away.

The papers, the source and a full example report are all public. A claim you cannot verify is just a sentence.