July 17, 2026 · 8 min read

NeuroCUDA SpiNNaker Silicon Confirmed

Two independent SUCCESS runs on two different physical SpiNNaker-1 boards at the University of Manchester. This is neuromorphic silicon - not a simulator.

TL;DR - Physical silicon

NeuroCUDA SpiNNaker physical silicon is confirmed. Job #420148 (13 Jul 2026, board 10.11.242.169, 43 chips) and job #420186 (17 Jul 2026, board 10.11.196.49, 48 chips / 851 cores) both returned SUCCESS with neuron 0 = 2 spikes and neuron 1 = 2 spikes. Platform: EBRAINS Neuromorphic Computing Service, Manchester. Source: github.com/Krishnav1/neurocuda.

NeuroCUDA SpiNNaker physical silicon validation - two confirmed runs on separate boards

For months, neuromorphic tooling conversations blurred simulators and chips. NeuroCUDA already shipped GPU, CPU, and a Loihi 2 simulator. Today the SpiNNaker path is different: it executed on physical SpiNNaker-1 silicon through the EBRAINS queue - twice, on two boards, on two dates.

Confirmed SpiNNaker physical silicon runs

JobDateBoard IPHardwareResult
#4201482026-07-1310.11.242.16943 chips, 766 coresSUCCESS
#4201862026-07-1710.11.196.4948 chips, 851 coresSUCCESS

Both runs produced identical spike counts: neuron 0: 2 spikes, neuron 1: 2 spikes, total 4 spikes. Same network, different boards, same outcome. That is the point of repeating the experiment - a single lucky queue slot is no longer a plausible explanation.

What ran on the silicon

Job #420186 used a minimal PyNN validation network designed to prove the hardware path:

A cosmetic log warning (cfg has no version) appeared and does not affect the neural computation. Status remained SUCCESS.

Physical SpiNNaker silicon: confirmed. Loihi 2: still a simulator. GPU/CPU accuracy numbers: still the software-backend evidence. Label each backend honestly.

Why "not silicon" still appears for Loihi

Older NeuroCUDA pages said backends were not claimed on physical neuromorphic silicon. That sentence covered the general case and especially Loihi 2, which remains an IF-neuron simulator checked against Intel's published equations - not Intel silicon, not Lava. SpiNNaker is now the exception that is proven: real boards at Manchester.

Do not rewrite Loihi claims as silicon. Do not hide SpiNNaker silicon behind simulator language either. The honest matrix is:

BackendStatus (July 2026)
GPU / CPUShipped - multi-seed accuracy published
SpiNNaker-1Physical silicon confirmed (2 boards, 2 jobs)
Loihi 2Simulator only (equation validation)
NIR exportShipped - ResNet-18 residual bit-exact
FPGAHLS C++ proof of concept

What this does and does not prove

It proves

It does not prove

Calling a 4-neuron SUCCESS run "ResNet silicon accuracy" would be false marketing. Calling it "SpiNNaker physical silicon confirmed" is accurate and citable.

Where to verify

Primary sources

  1. NeuroCUDA GitHub - SpiNNaker physical silicon section and job #420186 result file
  2. EBRAINS Neuromorphic Computing Service - SpiNNaker-1 job queue (jobs #420148, #420186)
  3. University of Manchester / SpiNNaker project - SC&MP firmware and sPyNNaker stack
  4. QuantaraCore NeuroCUDA product page - backend honesty labels

Frequently asked questions

Has NeuroCUDA run on physical SpiNNaker silicon?

Yes. Two SUCCESS jobs on two different SpiNNaker-1 boards (#420148 and #420186) via EBRAINS Manchester.

Is Loihi 2 also physical silicon now?

No. Loihi 2 in NeuroCUDA is still a simulator. Only SpiNNaker-1 is confirmed on physical boards in this announcement.

What network ran on SpiNNaker?

A 4-neuron PyNN LIF validation network (2 sources, 2 IF_curr_exp, OneToOne weight 5.0), 10 ms @ 1 ms.

Does this prove ResNet accuracy on SpiNNaker?

No. It confirms the silicon execution path. Full-model accuracy remains published for GPU/CPU backends.

Next: pip install neurocuda · Product page · GitHub