So if it's a "Galaxy S3 with 2GB of ram and a quad-core 1.3ghz processor" then this should be the version with the Exynos SOC. That means that these are cores inside are A9s. The Intel cores are from the Westmere generation.
I wonder how much of the difference we're seeing between various languages is the quality of the code their compilers generate for various backends and how much is due to the different languages benefiting more from architectural differences between the two chips.
I imagine that languages that generate code with more indirection are going to excersize the prefetcher and branch predictor of the core they're running on much more than languages that generate code with simpler control flows. Both the A9 and the Nehalem cores are out of order but the Nehalem has a much, much more sophisticated set of facilities for that. I predict that if you were to re-run the benchmarks on an iPhone 5S you'd see much less of a difference between the various ARM times. And if you were to run it on a cheap Android phone with A7 or A53 cores you'd see a much larger difference.
Correct. Not to mention that benchmarking on a mobile phone is tricky. You need to make sure your CPU won't throttle due to heat. Your average mobile CPU can't run at 100% for very long. The more benchmarks you run back to back, the slower you get, so your measurements can easily be completely wrong.
Exactly, the speed of mobiles is limited to short bursts to preserve the battery. And sometimes even the worse code gets more CPU if it hits the right patterns.
The timings presented are also confusingly presented for my taste.
I wonder how much of the difference we're seeing between various languages is the quality of the code their compilers generate for various backends and how much is due to the different languages benefiting more from architectural differences between the two chips.
I imagine that languages that generate code with more indirection are going to excersize the prefetcher and branch predictor of the core they're running on much more than languages that generate code with simpler control flows. Both the A9 and the Nehalem cores are out of order but the Nehalem has a much, much more sophisticated set of facilities for that. I predict that if you were to re-run the benchmarks on an iPhone 5S you'd see much less of a difference between the various ARM times. And if you were to run it on a cheap Android phone with A7 or A53 cores you'd see a much larger difference.