Benchmarks Of 2nd Gen AMD EPYC On Amazon EC2 Against Intel Xeon, Graviton2

[PerformanceExpert]

We don't know how many cores are on those Epyc parts. Assuming it's 64, then the tested configs here would have been ~140w for the Rome config vs ~100w for the ARM config. I also think it's safe to say that a 280w Rome config is being pushed over it's maximal efficiency limit - so a power use comparison would probably make more sense against a lower clocked Rome machine. There's no way of knowing if the same is true for the Graviton machine as well. Those kinds of changes on either side would obviously make the performance analysis here useless, though, so long story short this is a complicated subject and we don't have nearly enough information to draw any firm conclusions.

In general you can't just claim 32 cores use half the power of 64 cores! We don't have enough details on 7R32 (base or turbo), but there are 16-core EPYC parts that have a 240W TDP, so 32 cores could well use 280W. Graviton 2 is likely more power optimized than the 7R32, but using 1/2 to 1/3rd of the power for equivalent performance is very efficient.

[PerformanceExpert]

Prices are more than likely heavily subsidized by Amazon for their own solution.
You can't make your own ultra-high-end CPU, motherboards etc and fab it at low volume thinking it will compete price-wise with families made in counts of millions.
Even if you could make it dirt cheap, RnD costs over units in this volume range is stupid high.

You're grossly underestimating the scale of AWS - they have $35B revenue and many millions of servers. They already design most of the hardware themselves because at this scale it is significantly cheaper. Designing your own server chip is the obvious next step. Even if it costs say $1B, it's just $100 at 10 million units.