iOS 12 Core ML Benchmarks
heartbeat.fritz.ai
iOS 12 Core ML Benchmarks
1–10 of 59 posts
Re: iOS 12 Core ML Benchmarks
#2Impressive but with a specialized coprocessor it's not unexpected. It's a bit of a gamble for Apple though, as other ARM SoC's are probably able to bridge the gap in raw single-core and multi-core performance in a year. The whole ML thing is a bit fuzzy for a lot of people even for programmers like me that are still wondering how their regular applications are going to benefit from all this silicon.
Re: iOS 12 Core ML Benchmarks
#3Impressive but with a specialized coprocessor it's not unexpected. It's a bit of a gamble for Apple though, as other ARM SoC's are probably able to bridge the gap in raw single-core and multi-core performance in a year. The whole ML thing is a bit fuzzy for a lot of people even for programmers like me that are still wondering how their regular applications are going to benefit from all this silicon.
Apple doesn't use ARM SoCs. They have their own designs from the PA Semi team and are really just using the ARM instruction set at this point. This is one of the reasons there is such a big performance gap between the top android phones vs the top iPhones.
Re: iOS 12 Core ML Benchmarks
#4Impressive but with a specialized coprocessor it's not unexpected. It's a bit of a gamble for Apple though, as other ARM SoC's are probably able to bridge the gap in raw single-core and multi-core performance in a year. The whole ML thing is a bit fuzzy for a lot of people even for programmers like me that are still wondering how their regular applications are going to benefit from all this silicon.
I think because Apple are dogfooding this ML stuff themselves (camera, face detection, filters, Siri, etc), exposing that API publicly isn't that much more risk to them.
Re: iOS 12 Core ML Benchmarks
#5Original author, when you find this, “Not the” is a typo for “Note the”.
Re: iOS 12 Core ML Benchmarks
#6Impressive but with a specialized coprocessor it's not unexpected. It's a bit of a gamble for Apple though, as other ARM SoC's are probably able to bridge the gap in raw single-core and multi-core performance in a year. The whole ML thing is a bit fuzzy for a lot of people even for programmers like me that are still wondering how their regular applications are going to benefit from all this silicon.
Apple doesn't use ARM SoCs. They have their own designs from the PA Semi team and are really just using the ARM instruction set at this point. This is one of the reasons there is such a big performance gap between the top android phones vs the top iPhones.
I guess the same can be said for AMD's x86_64 CPU's? Still it's fair to compare them to Intel x86_64 CPU's. The big difference is that ARM has something like a reference design where Intel doesn't want to share anything if they don't have to.
Re: iOS 12 Core ML Benchmarks
#7Original author, when you find this, “Not the” is a typo for “Note the”.
Ah! Nice catch. Thanks for this. Fixed!
Re: iOS 12 Core ML Benchmarks
#8Original author, when you find this, “Not the” is a typo for “Note the”.
Good catch. Also taking recommendations for better autocorrecting keyboards :)
Re: iOS 12 Core ML Benchmarks
#9It's interesting to see that ML performance is about equal on iPhone X and older iPhones, considering that iPhone X (and 8) has a neural engine and the other phones do not.
Re: iOS 12 Core ML Benchmarks
#10It's interesting to see that ML performance is about equal on iPhone X and older iPhones, considering that iPhone X (and 8) has a neural engine and the other phones do not.
It's my understanding that the neural engine API wasn't actually exposed to Core ML until the iPhone XS. The GPU is the important factor for performance of those models