Sparxity closes Series A for sparse AI computing hardware
ICM HPQC Fund led the round, which brings the former SpiNNcloud team’s cumulative funding to $90 million.
Sparxity has closed a Series A led by ICM HPQC Fund as the Dresden computing company rebrands from SpiNNcloud. The new round’s amount was not disclosed; the company said cumulative funding secured by its team now totals $90 million.
The round includes Lockheed Martin Ventures, GlobalFoundries, GS Futures, Cloudberry Ventures, TGFS and the EIC Fund, together with angel investors Richard Socher and Nancy Xu. The company also cited continued support from Atlantic and Silicon Catalyst.
Sparxity will use the financing to develop specialised chips for fine-grained dynamic sparsity in AI inference. Its systems are designed to avoid unnecessary computation and data movement when a model activates only part of its network for a task.
The company says it has produced more than 70,000 chips and deployed 12 racks, with more than 30 customers worldwide. Its next generation of hardware builds on this existing computing platform.
Use of funds
Specialised chips for fine-grained dynamic sparsity
AI inference hardware development