Coherence Energy Labs

Same source, two machines

The same source, two machines. Watch exactly where they diverge.

The same .cl program runs twice here: on your CPU in double precision and your GPU in single precision, both built from one source. They do not agree to the last bit, and you can measure exactly how far single precision drifts, live, below. That drift is the "it worked on my machine" problem, and it is why reproducible results cannot trust floating point. The fix is exact integer arithmetic, which really is bit-identical across machines. See a model that re-runs bit-for-bit →

running...

CPU - WASM (f64)

GPU - WGSL (f32)

the difference (rounding only)

measuring...

Both from field.cl: the CPU kernel tau_cell_step() compiled to WASM sha256 de8da74182e0…, and the GPU shader compiled to WGSL by the Coherence compiler sha256 322f6213fbf2… (only the stencil-gather @compute wrapper is hand-written). WebGPU is f32-only, so the GPU is the single-precision twin of the f64 CPU kernel; the report measures the gap.

Receipts you can re-run

A reproducible result deserves a reproducible receipt: a cryptographic fingerprint of the exact computation. Anyone, on any machine, can re-run it and confirm the same answer, bit for bit. Change a single input and the fingerprint changes. Nothing to trust, everything to check.

kerneltau_cell_step
inputscomputing...
output sha-256computing...
receipt idcomputing...
...

This is a teaser. The forensic-grade version, with signed, re-runnable receipts and court-ready chain-of-custody, is a separate product, Obsign (coming soon).

Coherence Energy Labs™
Get in touch →