@chrisvest @whitequark Something needs to parse your command buffers, handle scheduling, initiate interrupts and deal with other plumbing etc., and it's not going to be your matrix multiply unit.
For the AMD GPU equivalent, https://gpuopen.com/download/micro_engine_scheduler.pdf "The GPU frontend has three micro-processors meant to execute scheduling, compute
and gfx firmware".
It's the things that run the infamous GPU Mystery Firmware Blobs™.