Intel Optimizes Facebook DLRM, 8x Speedup (Deep Learning Recommendation Model)

17 points by beluis3d 4 years ago | 2 comments

alpanka 4 years ago |

I thought this was similar to their scikit optimizations, but after a quick look I still can't figure out what is going on here.

Can someone ELI5 this for me?

Rafuino 4 years ago |

So 16x more sockets provided an 8x speedup?

alpanka 4 years ago |

I thought this was similar to their scikit optimizations, but after a quick look I still can't figure out what is going on here.

Can someone ELI5 this for me?

Rafuino 4 years ago |

So 16x more sockets provided an 8x speedup?