←back to thread

486 points dbreunig | 3 comments | | HN request time: 0s | source
1. m00x ◴[] No.41864797[source]
NPUs are efficient, not especially fast. The CPU is much bigger than the NPU and has better cache access. Of course it'll perform better.
replies(2): >>41865195 #>>41870736 #
2. acdha ◴[] No.41865195[source]
It’s more complicated than that (you’re assuming that the bigger CPU is optimized for the same workload) but it’s also irrelevant to the topic at hand: they’re seeing this NPU within a factor of 2-4 of the CPU, but if it performed half as well as Qualcomm claims it would be an order of magnitude faster. The story here isn’t another round of the specialized versus general debate but that they fell so far short of their marketing claims.
3. llm_nerd ◴[] No.41870736[source]
NPUs are actually incredibly fast for standard inference operations.

This benchmark is horribly flawed in many ways, and was so evidently useless that I'm surprised that they still decided to "publish" this. When your test gets 1% of the published performance, it's a good indication that things aren't being done correctly.