Scaling Compute

Our Creators are driving towards one goal – dropping the hardware costs required to train large AI models by >1000x – but as AI hardware and techniques advance rapidly, our baseline metrics and the computational cost of MLPerf benchmark workloads shift, requiring a constant recalibration of our targets. We sought a team to help track these moving targets and publish their findings to the research community.

This solicitation sought to fund individuals and teams in a coordinated effort to redefine our current compute paradigm. If successful, this programme will unlock a new technological lever for next-generation AI hardware, alleviate dependence on leading-edge chip manufacturing, and open up new avenues to scale AI hardware.