← Back to context

Comment by fooker

2 hours ago

SIMD (and especially the modern matrix extensions) can use as much bandwidth you can throw at it.

Without further clarification, that statement seems impossible. "As much" being unbounded and all. You should expand what you mean.

  • This will blow your mind, but it actually is pretty close to being unbounded. :)

    Consider the 'MMA N matrices' primitive modern CPUs are starting to support. For the current generation of CPUs, N is a constant like 16 or 32, but there's nothing preventing it from being 1024 or larger if we have more memory bandwidth.

    All this with a single instruction.