Listenly

How does NVLink GPU interconnect technology enable distributed matrix multiplication to reduce latency?

Answered at 18:51 in Ex-NVIDIA Engineer: Why AI Is About to Get 1000x Cheaper · Invest Like The Best

— questions searchable right now

How does NVLink GPU interconnect technology enable distributed matrix multiplication to reduce latency?

NVLink is an NVIDIA innovation that allows large matrix multiplications to be split in half and sharded across up to eight NVIDIA GPUs, with each GPU working on pieces of the larger operation and connecting their results together at the end by reducing results back together. This is an effective way to cut the minimum latency of an operation.

Unknown on Invest Like The BestAll answers from this podcast →
Full answer and detailsRead the whole answer, key facts and every other question from this episode

In short

NVLink is an NVIDIA innovation that allows large matrix multiplications to be split in half and sharded across up to eight NVIDIA GPUs, with each GPU working on pieces of the larger operation and connecting their results together at the end by reducing resu…

Guest · Ex-NVIDIA Engineer: Why AI Is About to Get 1000x Cheaper · Invest Like The Best · answer at 18:51

The full answer · about 1 min

NVLink is an NVIDIA innovation that allows large matrix multiplications to be split in half and sharded across up to eight NVIDIA GPUs, with each GPU working on pieces of the larger operation and connecting their results together at the end by reducing results back together. This is an effective way to cut the minimum latency of an operation.

More answers from this episode

 ·  All answers from Invest Like The Best →
—
—
0:00
0:00