Nvidia Hopper Sweeps AI Inference Benchmarks in MLPerf Debut

Re:Nvidia Hopper Sweeps AI Inference Benchmarks in MLPerf Debut by Nimitz14 on Friday September 09, 2022 @04:00AM (#32776593)

I have never heard anybody use "x times faster" in the sense you mean here.

To my ears, "3 times faster" has the same meaning as "3 times as fast".

[ Parent | on HN ]

Re:Nvidia Hopper Sweeps AI Inference Benchmarks in MLPerf Debut by benplumley on Friday September 09, 2022 @05:15AM (#32777130)

How about "50% faster" and "50% as fast"? If these are different (which to my ear they clearly are), then "200% faster" and "200% as fast" are different too. Naturally it's all quite ambiguous so whoever's writing the press release can pick the more impressive meaning in each case.

[ Parent | on HN ]

Re:Nvidia Hopper Sweeps AI Inference Benchmarks in MLPerf Debut by mkl on Friday September 09, 2022 @06:28AM (#32777548)

To me percentages behave differently from "times". I agree with you on the percentages but disagree on "times faster" and "times as fast", which I think are the same.

[ Parent | on HN ]

Re:Nvidia Hopper Sweeps AI Inference Benchmarks in MLPerf Debut by IanCal on Friday September 09, 2022 @07:00AM (#32777731)

The key difference in my reading here is the use of percentages or x, where x I read as "times". I would never expect someone to say "half times faster".

[ Parent | on HN ]